{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T00:47:49Z","timestamp":1780966069325,"version":"3.54.1"},"reference-count":179,"publisher":"Association for Computing Machinery (ACM)","issue":"6","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Comput. Surv."],"published-print":{"date-parts":[[2026,4,30]]},"abstract":"<jats:p>This survey provides a comprehensive review of research on multi-turn dialogue systems, with a particular focus on multi-turn dialogue systems based on large language models (LLMs). This article aims to (a) giving a summary of existing LLMs and approaches for adapting LLMs to downstream tasks; (b) elaborate recent advances in multi-turn dialogue systems, covering both LLM-based open-domain dialogue (ODD) and task-oriented dialogue (TOD) systems, along with datasets and evaluation metrics; (c) discuss some future emphasis and recent research problems arising from the development of LLMs and the increasing demands on multi-turn dialogue systems.<\/jats:p>","DOI":"10.1145\/3771090","type":"journal-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T09:25:55Z","timestamp":1761816355000},"page":"1-38","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":31,"title":["A Survey on Recent Advances in LLM-Based Multi-turn Dialogue Systems"],"prefix":"10.1145","volume":"58","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-8656-6374","authenticated-orcid":false,"given":"Zihao","family":"Yi","sequence":"first","affiliation":[{"name":"Sun Yat-Sen University","place":["Guangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-4716-4235","authenticated-orcid":false,"given":"Jiarui","family":"Ouyang","sequence":"additional","affiliation":[{"name":"Sun Yat-Sen University","place":["Guangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-9669-1966","authenticated-orcid":false,"given":"Zhe","family":"Xu","sequence":"additional","affiliation":[{"name":"Sun Yat-Sen University","place":["Guangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-5452-8430","authenticated-orcid":false,"given":"Yuwen","family":"Liu","sequence":"additional","affiliation":[{"name":"Sun Yat-Sen University","place":["Guangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-0425-8567","authenticated-orcid":false,"given":"Tianhao","family":"Liao","sequence":"additional","affiliation":[{"name":"Sun Yat-Sen University","place":["Guangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-9714-0434","authenticated-orcid":false,"given":"Haohao","family":"Luo","sequence":"additional","affiliation":[{"name":"Sun Yat-Sen University","place":["Shenzhen, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3220-904X","authenticated-orcid":false,"given":"Ying","family":"Shen","sequence":"additional","affiliation":[{"name":"Sun Yat-Sen University","place":["Shenzhen, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,12,8]]},"reference":[{"issue":"1","key":"e_1_3_1_2_2","doi-asserted-by":"crossref","first-page":"36","DOI":"10.1145\/365153.365168","article-title":"ELIZA\u2013a computer program for the study of natural language communication between man and machine","volume":"9","author":"Weizenbaum Joseph","year":"1966","unstructured":"Joseph Weizenbaum. 1966. ELIZA\u2013a computer program for the study of natural language communication between man and machine. Communications of the ACM 9, 1 (1966), 36\u201345.","journal-title":"Communications of the ACM"},{"issue":"1","key":"e_1_3_1_3_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/0004-3702(71)90002-6","article-title":"Artificial paranoia","volume":"2","author":"Colby Kenneth Mark","year":"1971","unstructured":"Kenneth Mark Colby, Sylvia Weber, and Franklin Dennis Hilf. 1971. Artificial paranoia. Artificial intelligence 2, 1 (1971), 1\u201325.","journal-title":"Artificial intelligence"},{"key":"e_1_3_1_4_2","first-page":"701","volume-title":"Proceeding of the 4th International Conference on Spoken Language Processing","author":"al. David Goddeau et","year":"1996","unstructured":"David Goddeau et al.1996. A form-based dialogue manager for spoken language applications. In Proceeding of the 4th International Conference on Spoken Language Processing. IEEE, 701\u2013704."},{"key":"e_1_3_1_5_2","first-page":"496","volume-title":"Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","year":"2017","unstructured":"Yu Wu, Wei Wu, Chen Xing, Can Xu, Zhoujun Li, and Ming Zhou. 2017. Sequential matching network: A new architecture for multi-turn response selection in retrieval-based chatbots. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Association for Computational Linguistics, Vancouver, Canada, 496\u2013505. DOI:10.18653\/v1\/P17-1046"},{"key":"e_1_3_1_6_2","first-page":"1","volume-title":"Proceedings of the 17th Annual Meeting of the Special Interest Group on Discourse and Dialogue","author":"Zhao Tiancheng","year":"2016","unstructured":"Tiancheng Zhao and Maxine Eskenazi. 2016. Towards end-to-end learning for dialog state tracking and management using deep reinforcement learning. In Proceedings of the 17th Annual Meeting of the Special Interest Group on Discourse and Dialogue. Association for Computational Linguistics, Los Angeles, 1\u201310. DOI:10.18653\/v1\/W16-3601"},{"key":"e_1_3_1_7_2","first-page":"737","volume-title":"Proceedings of the 23rd Conference on Computational Natural Language Learning. Association for Computational Linguistics","year":"2019","unstructured":"Wentao Ma, Yiming Cui, Nan Shao, Su He, Wei-Nan Zhang, Ting Liu, Shijin Wang, and Guoping Hu. 2019. TripleNet: Triple attention network for multi-turn response selection in retrieval-based chatbots. In Proceedings of the 23rd Conference on Computational Natural Language Learning. Association for Computational Linguistics, Hong Kong, China, 737\u2013746. DOI:10.18653\/v1\/K19-1069"},{"key":"e_1_3_1_8_2","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","year":"2016","unstructured":"Iulian Serban, Alessandro Sordoni, Yoshua Bengio, Aaron Courville, and Joelle Pineau. 2016. Building end-to-end dialogue systems using generative hierarchical neural network models. In Proceedings of the AAAI Conference on Artificial Intelligence."},{"key":"e_1_3_1_9_2","first-page":"3498","volume-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing","year":"2020","unstructured":"Wanwei He, Min Yang, Rui Yan, Chengming Li, Ying Shen, and Ruifeng Xu. 2020. Amalgamating knowledge from two teachers for task-oriented dialogue system with adversarial training. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing. 3498\u20133507."},{"key":"e_1_3_1_10_2","doi-asserted-by":"crossref","first-page":"3826","DOI":"10.18653\/v1\/P19-1372","volume-title":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","year":"2019","unstructured":"Lisong Qiu, Juntao Li, Wei Bi, Dongyan Zhao, and Rui Yan. 2019. Are training samples correlated? learning to generate dialogue responses with multiple references. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. 3826\u20133835."},{"key":"e_1_3_1_11_2","unstructured":"Wayne Xin Zhao Kun Zhou Junyi Li Tianyi Tang Xiaolei Wang Yupeng Hou Yingqian Min Beichen Zhang Junjie Zhang Zican Dong et\u00a0al. 2023. A survey of large language models. arXiv:2303.18223. Retrieved from https:\/\/arxiv.org\/abs\/2303.18223"},{"key":"e_1_3_1_12_2","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale et\u00a0al. 2023. Llama 2: Open Foundation and Fine-Tuned Chat Models. arXiv:2307.09288. Retrieved from https:\/\/arxiv.org\/abs\/2307.09288"},{"key":"e_1_3_1_13_2","unstructured":"Yunfan Gao Tao Sheng Youlin Xiang Yun Xiong Haofen Wang and Jiawei Zhang. 2023. Chat-rec: Towards interactive and explainable llms-augmented recommender system. arXiv:2303.14524. Retrieved from https:\/\/arxiv.org\/abs\/2303.14524"},{"key":"e_1_3_1_14_2","unstructured":"Andrea Madotto Zihan Liu Zhaojiang Lin and Pascale Fung. 2020. Language models as few-shot learner for task-oriented dialogue systems. arXiv:2008.06239. Retrieved from https:\/\/arxiv.org\/abs\/2008.06239"},{"key":"e_1_3_1_15_2","unstructured":"Suket Arora Kamaljeet Batra and Sarabjit Singh. 2013. Dialogue system: A brief review. arXiv:1306.4134. Retrieved from https:\/\/arxiv.org\/abs\/1306.4134"},{"issue":"2","key":"e_1_3_1_16_2","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1145\/3166054.3166058","article-title":"A survey on dialogue systems: Recent advances and new frontiers","volume":"19","year":"2017","unstructured":"Hongshen Chen, Xiaorui Liu, Dawei Yin, and Jiliang Tang. 2017. A survey on dialogue systems: Recent advances and new frontiers. Acm Sigkdd Explorations Newsletter 19, 2 (2017), 25\u201335.","journal-title":"Acm Sigkdd Explorations Newsletter"},{"issue":"4","key":"e_1_3_1_17_2","doi-asserted-by":"crossref","first-page":"3055","DOI":"10.1007\/s10462-022-10248-8","article-title":"Recent advances in deep learning based dialogue systems: A systematic survey","volume":"56","year":"2023","unstructured":"Jinjie Ni, Tom Young, Vlad Pandelea, Fuzhao Xue, and Erik Cambria. 2023. Recent advances in deep learning based dialogue systems: A systematic survey. Artificial Intelligence Review 56, 4 (2023), 3055\u20133155.","journal-title":"Artificial Intelligence Review"},{"key":"e_1_3_1_18_2","doi-asserted-by":"crossref","first-page":"5925","DOI":"10.18653\/v1\/2023.emnlp-main.363","volume-title":"Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing","year":"2023","unstructured":"Libo Qin, Wenbo Pan, Qiguang Chen, Lizi Liao, Zhou Yu, Yue Zhang, Wanxiang Che, and Min Li. 2023. End-to-end task-oriented dialogue: A survey of tasks, methods, and future directions. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Singapore, 5925\u20135941. DOI:10.18653\/v1\/2023.emnlp-main.363"},{"key":"e_1_3_1_19_2","unstructured":"Jared Kaplan Sam McCandlish Tom Henighan Tom B. Brown Benjamin Chess Rewon Child Scott Gray Alec Radford Jeffrey Wu and Dario Amodei. 2020. Scaling laws for neural language models. arXiv:2001.08361. Retrieved from https:\/\/arxiv.org\/abs\/2001.08361"},{"key":"e_1_3_1_20_2","unstructured":"Jason Wei Yi Tay Rishi Bommasani Colin Raffel Barret Zoph Sebastian Borgeaud Dani Yogatama Maarten Bosma Denny Zhou Donald Metzler et\u00a0al. 2022. Emergent abilities of large language models. arXiv:2206.07682. Retrieved from https:\/\/arxiv.org\/abs\/2206.07682"},{"issue":"10","key":"e_1_3_1_21_2","doi-asserted-by":"crossref","first-page":"1872","DOI":"10.1007\/s11431-020-1647-3","article-title":"Pre-trained models for natural language processing: A survey","volume":"63","year":"2020","unstructured":"Xipeng Qiu, Tianxiang Sun, Yige Xu, Yunfan Shao, Ning Dai, and Xuanjing Huang. 2020. Pre-trained models for natural language processing: A survey. Science China Technological Sciences 63, 10 (2020), 1872\u20131897.","journal-title":"Science China Technological Sciences"},{"key":"e_1_3_1_22_2","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N. Gomez \u0141ukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. Advances in Neural Information Processing Systems 30 (2017) 6000\u20136010."},{"key":"e_1_3_1_23_2","unstructured":"Alec Radford Karthik Narasimhan Tim Salimans Ilya Sutskever et\u00a0al. 2018. Improving language understanding by generative pre-training."},{"issue":"8","key":"e_1_3_1_24_2","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","year":"2019","unstructured":"Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, and Ilya Sutskever, et\u00a0al. 2019. Language models are unsupervised multitask learners. OpenAI Blog 1, 8 (2019), 9.","journal-title":"OpenAI Blog"},{"key":"e_1_3_1_25_2","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","year":"2020","unstructured":"Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D. Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et\u00a0al. 2020. Language models are few-shot learners. Advances in Neural Information Processing Systems 33 (2020), 1877\u20131901.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_26_2","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume":"35","year":"2022","unstructured":"Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, et\u00a0al. 2022. Training language models to follow instructions with human feedback. Advances in Neural Information Processing Systems 35 (2022), 27730\u201327744.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_27_2","unstructured":"OpenAI. 2022. Introducing ChatGPT. Retrieved February 22 2024 from https:\/\/www.openai.com\/blog\/chatgpt"},{"key":"e_1_3_1_28_2","unstructured":"OpenAI. 2023. GPT-4 Technical Report. arXiv:2303.08774. Retrieved from https:\/\/arxiv.org\/abs\/2303.08774"},{"key":"e_1_3_1_29_2","unstructured":"OpenAI. 2023. Introducing GPTs. Retrieved February 22 2024 from https:\/\/openai.com\/blog\/introducing-gpts"},{"key":"e_1_3_1_30_2","unstructured":"Hugo Touvron Thibaut Lavril Gautier Izacard Xavier Martinet Marie-Anne Lachaux Timoth\u00e9e Lacroix Baptiste Rozi\u00e8re Naman Goyal Eric Hambro Faisal Azhar et\u00a0al. 2023. Llama: Open and efficient foundation language models. arXiv:2302.13971. Retrieved from https:\/\/arxiv.org\/abs\/2302.13971"},{"key":"e_1_3_1_31_2","unstructured":"Jordan Hoffmann Sebastian Borgeaud Arthur Mensch Elena Buchatskaya Trevor Cai and Eliza Rutherford. 2022. Training compute-optimal large language models. arXiv:2203.15556. Retrieved from https:\/\/arxiv.org\/abs\/2203.15556"},{"key":"e_1_3_1_32_2","unstructured":"Jack W. Rae Sebastian Borgeaud Trevor Cai Katie Millican Jordan Hoffmann Francis Song John Aslanides Sarah Henderson Roman Ring Susannah Young et\u00a0al. 2021. Scaling language models: Methods analysis and insights from training gopher. arXiv:2112.11446. Retrieved from https:\/\/arxiv.org\/abs\/2112.11446"},{"key":"e_1_3_1_33_2","unstructured":"Meta. 2023. Meta and microsoft introduce the next generation of LLaMA. Retrieved 21 July 2023 from https:\/\/about.fb.com\/news\/2023\/07\/llama-2\/"},{"key":"e_1_3_1_34_2","unstructured":"Baptiste Roziere Jonas Gehring Fabian Gloeckle Sten Sootla Itai Gat Xiaoqing Ellen Tan Yossi Adi Jingyu Liu Romain Sauvestre Tal Remez et\u00a0al. 2023. Code Llama: Open Foundation Models for Code. arXiv:2308.12950. Retrieved from https:\/\/arxiv.org\/abs\/2308.12950"},{"issue":"1","key":"e_1_3_1_35_2","first-page":"5485","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","year":"2020","unstructured":"Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J. Liu. 2020. Exploring the limits of transfer learning with a unified text-to-text transformer. The Journal of Machine Learning Research 21, 1 (2020), 5485\u20135551.","journal-title":"The Journal of Machine Learning Research"},{"key":"e_1_3_1_36_2","unstructured":"Zhengxiao Du Yujie Qian Xiao Liu Ming Ding Jiezhong Qiu Zhilin Yang and Jie Tang. 2021. Glm: General language model pretraining with autoregressive blank infilling. arXiv:2103.10360. Retrieved from https:\/\/arxiv.org\/abs\/2103.10360"},{"key":"e_1_3_1_37_2","unstructured":"Aohan Zeng Xiao Liu Zhengxiao Du Zihan Wang Hanyu Lai Ming Ding Zhuoyi Yang Yifan Xu Wendi Zheng Xiao Xia et\u00a0al. 2022. Glm-130b: An open bilingual pre-trained model. arXiv:2210.02414. Retrieved from https:\/\/arxiv.org\/abs\/2210.02414"},{"key":"e_1_3_1_38_2","article-title":"ChatGLM2-6B","year":"2022","unstructured":"THUDM. 2022. ChatGLM2-6B. Retrieved February 22, 2024 from https:\/\/github.com\/thudm\/chatglm2-6b","journal-title":"Retrieved February 22, 2024 from https:\/\/github.com\/thudm\/chatglm2-6b"},{"key":"e_1_3_1_39_2","article-title":"ChatGLM3","year":"2023","unstructured":"THUDM. 2023. ChatGLM3. Retrieved February 22, 2024 from https:\/\/github.com\/THUDM\/ChatGLM3","journal-title":"Retrieved February 22, 2024 from https:\/\/github.com\/THUDM\/ChatGLM3"},{"key":"e_1_3_1_40_2","doi-asserted-by":"crossref","unstructured":"Jacob Devlin Ming-Wei Chang Kenton Lee and Kristina Toutanova. 2019. BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies volume 1 (Long and Short Papers). 4171\u20134186.","DOI":"10.18653\/v1\/N19-1423"},{"key":"e_1_3_1_41_2","unstructured":"Yinhan Liu Myle Ott Naman Goyal Jingfei Du Mandar Joshi Danqi Chen Omer Levy Mike Lewis Luke Zettlemoyer and Veselin Stoyanov. 2019. Roberta: A robustly optimized bert pretraining approach. arXiv:1907.11692. Retrieved from https:\/\/arxiv.org\/abs\/1907.11692"},{"key":"e_1_3_1_42_2","unstructured":"Li Dong Nan Yang Wenhui Wang Furu Wei Xiaodong Liu Yu Wang Jianfeng Gao Ming Zhou and Hsiao-Wuen Hon. 2019. Unified language model pre-training for natural language understanding and generation. Advances in Neural Information Processing Systems 32 (2019) 13063\u201313075."},{"key":"e_1_3_1_43_2","doi-asserted-by":"crossref","unstructured":"Mike Lewis Yinhan Liu Naman Goyal Marjan Ghazvininejad Abdelrahman Mohamed Omer Levy Ves Stoyanov and Luke Zettlemoyer. 2019. Bart: Denoising sequence-to-sequence pre-training for natural language generation translation and comprehension. arXiv:1910.13461. Retrieved from https:\/\/arxiv.org\/abs\/1910.13461","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"e_1_3_1_44_2","first-page":"2790","volume-title":"Proceedings of the International Conference on Machine Learning","year":"2019","unstructured":"Neil Houlsby, Andrei Giurgiu, Stanislaw Jastrzebski, Bruna Morrone, Quentin De Laroussilhe, Andrea Gesmundo, Mona Attariyan, and Sylvain Gelly. 2019. Parameter-efficient transfer learning for NLP. In Proceedings of the International Conference on Machine Learning. PMLR, 2790\u20132799."},{"key":"e_1_3_1_45_2","unstructured":"Jason Wei Maarten Bosma Vincent Y. Zhao Kelvin Guu Adams Wei Yu Brian Lester Nan Du Andrew M. Dai and Quoc V. Le. 2021. Finetuned language models are zero-shot learners. arXiv:2109.01652. Retrieved from https:\/\/arxiv.org\/abs\/2109.01652"},{"key":"e_1_3_1_46_2","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2022.FINDINGS-ACL.252"},{"key":"e_1_3_1_47_2","first-page":"4395","volume-title":"Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","year":"2021","unstructured":"Edward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen, et\u00a0al. 2021. LoRA: Low-rank adaptation of large language models. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 4395\u20134409."},{"key":"e_1_3_1_48_2","unstructured":"Tim Dettmers Artidoro Pagnoni Ari Holtzman and Luke Zettlemoyer. 2023. Qlora: Efficient finetuning of quantized llms. arXiv:2305.14314. Retrieved from https:\/\/arxiv.org\/abs\/2305.14314"},{"key":"e_1_3_1_49_2","unstructured":"Tianyi Zhang Felix Wu Arzoo Katiyar Kilian Q. Weinberger and Yoav Artzi. 2020. Revisiting few-sample BERT fine-tuning. arXiv:2006.05987. Retrieved from https:\/\/arxiv.org\/abs\/2006.05987"},{"key":"e_1_3_1_50_2","unstructured":"Marius Mosbach Maksym Andriushchenko and Dietrich Klakow. 2021. On the stability of fine-tuning BERT: Misconceptions explanations and strong baselines. arXiv:2006.04884. Retrieved from https:\/\/arxiv.org\/abs\/2006.04884"},{"key":"e_1_3_1_51_2","unstructured":"Armen Aghajanyan Akshat Shrivastava Anchit Gupta Naman Goyal Luke Zettlemoyer and Sonal Gupta. 2020. Better fine-tuning by reducing representational collapse. arXiv:2008.03156. Retrieved from https:\/\/arxiv.org\/abs\/2008.03156"},{"key":"e_1_3_1_52_2","unstructured":"Jesse Dodge Gabriel Ilharco Roy Schwartz Ali Farhadi Hannaneh Hajishirzi and Noah A Smith. 2020. Fine-tuning pretrained language models: Weight initializations data orders and early stopping. arXiv:2002.06305. Retrieved from https:\/\/arxiv.org\/abs\/2002.06305"},{"key":"e_1_3_1_53_2","doi-asserted-by":"crossref","first-page":"2177","DOI":"10.18653\/v1\/2020.acl-main.197","volume-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics","year":"2020","unstructured":"Haoming Jiang, Pengcheng He, Weizhu Chen, Xiaodong Liu, Jianfeng Gao, and Tuo Zhao. 2020. SMART: Robust and efficient fine-tuning for pre-trained natural language models through principled regularized optimization. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, Online, 2177\u20132190. DOI:10.18653\/v1\/2020.acl-main.197"},{"key":"e_1_3_1_54_2","unstructured":"Chen Zhu Yu Cheng Zhe Gan Siqi Sun Tom Goldstein and Jingjing Liu. 2019. FreeLB: Enhanced adversarial training for natural language understanding. arXiv:1909.11764. Retrieved from https:\/\/arxiv.org\/abs\/1909.11764"},{"key":"e_1_3_1_55_2","first-page":"100","volume-title":"Proceedings of the Deep Learning Inside Out: The 3rd Workshop on Knowledge Extraction and Integration for Deep Learning Architectures","year":"2022","unstructured":"Jiachang Liu, Dinghan Shen, Yizhe Zhang, Bill Dolan, Lawrence Carin, and Weizhu Chen. 2022. What makes good in-context examples for GPT-3?. In Proceedings of the Deep Learning Inside Out: The 3rd Workshop on Knowledge Extraction and Integration for Deep Learning Architectures. Association for Computational Linguistics, Dublin, Ireland and Online, 100\u2013114. DOI:10.18653\/v1\/2022.deelio-1.10"},{"key":"e_1_3_1_56_2","first-page":"8086","volume-title":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","year":"2022","unstructured":"Yao Lu, Max Bartolo, Alastair Moore, Sebastian Riedel, and Pontus Stenetorp. 2022. Fantastically ordered prompts and where to find them: Overcoming few-shot prompt order sensitivity. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Association for Computational Linguistics, Dublin, Ireland, 8086\u20138098. DOI:10.18653\/v1\/2022.acl-long.556"},{"key":"e_1_3_1_57_2","first-page":"3558","volume-title":"Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","year":"2022","unstructured":"Mingda Chen, Jingfei Du, Ramakanth Pasunuru, Todor Mihaylov, Srini Iyer, Veselin Stoyanov, and Zornitsa Kozareva. 2022. Improving in-context few-shot learning via self-supervised training. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Association for Computational Linguistics, Seattle, United States, 3558\u20133573. DOI:10.18653\/v1\/2022.naacl-main.260"},{"key":"e_1_3_1_58_2","first-page":"719","volume-title":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","year":"2022","unstructured":"Yanda Chen, Ruiqi Zhong, Sheng Zha, George Karypis, and He He. 2022. Meta-learning via language model in-context tuning. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Association for Computational Linguistics, Dublin, Ireland, 719\u2013730. DOI:10.18653\/v1\/2022.acl-long.53"},{"key":"e_1_3_1_59_2","first-page":"2791","volume-title":"Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","year":"2022","unstructured":"Sewon Min, Mike Lewis, Luke Zettlemoyer, and Hannaneh Hajishirzi. 2022. MetaICL: Learning to learn in context. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Association for Computational Linguistics, Seattle, United States, 2791\u20132809. DOI:10.18653\/v1\/2022.naacl-main.201"},{"key":"e_1_3_1_60_2","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume":"35","year":"2022","unstructured":"Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V. Le, Denny Zhou, et\u00a0al. 2022. Chain-of-thought prompting elicits reasoning in large language models. Advances in Neural Information Processing Systems 35 (2022), 24824\u201324837.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_61_2","first-page":"22199","article-title":"Large language models are zero-shot reasoners","volume":"35","year":"2022","unstructured":"Takeshi Kojima, Shixiang Shane Gu, Machel Reid, Yutaka Matsuo, and Yusuke Iwasawa. 2022. Large language models are zero-shot reasoners. Advances in Neural Information Processing Systems 35 (60), 22199\u201322213.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_62_2","unstructured":"Denny Zhou Nathanael Sch\u00e4rli Le Hou Jason Wei Nathan Scales Xuezhi Wang Dale Schuurmans Claire Cui Olivier Bousquet Quoc Le et\u00a0al. 2022. Least-to-most prompting enables complex reasoning in large language models. arXiv:2205.10625. Retrieved from https:\/\/arxiv.org\/abs\/2205.10625"},{"key":"e_1_3_1_63_2","first-page":"7978","volume-title":"Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Bangkok, Thailand, August 11-16, 2024","author":"Luo Haohao","year":"2024","unstructured":"Haohao Luo, Yang Deng, Ying Shen, See-Kiong Ng, and Tat-Seng Chua. 2024. Chain-of-exemplar: Enhancing distractor generation for multimodal educational question generation. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Bangkok, Thailand, August 11-16, 2024, Lun-Wei Ku, Andre Martins, and Vivek Srikumar (Eds.). Association for Computational Linguistics, 7978\u20137993. DOI:10.18653\/V1\/2024.ACL-LONG.432"},{"key":"e_1_3_1_64_2","unstructured":"Zhuosheng Zhang Aston Zhang Mu Li and Alex Smola. 2022. Automatic chain of thought prompting in large language models. arXiv:2210.03493. Retrieved from https:\/\/arxiv.org\/abs\/2210.03493"},{"key":"e_1_3_1_65_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.811"},{"key":"e_1_3_1_66_2","doi-asserted-by":"publisher","DOI":"10.1145\/3711680"},{"key":"e_1_3_1_67_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.826"},{"key":"e_1_3_1_68_2","first-page":"9459","article-title":"Retrieval-augmented generation for knowledge-intensive nlp tasks","volume":"33","author":"Lewis Patrick","year":"2020","unstructured":"Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich K\u00fcttler, Mike Lewis, Wen-tau Yih, Tim Rockt\u00e4schel, et\u00a0al. 2020. Retrieval-augmented generation for knowledge-intensive nlp tasks. Advances in Neural Information Processing Systems 33 (2020), 9459\u20139474.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_69_2","first-page":"5303","volume-title":"Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing","author":"Ma Xinbei","year":"2023","unstructured":"Xinbei Ma, Yeyun Gong, Pengcheng He, Hai Zhao, and Nan Duan. 2023. Query rewriting in retrieval-augmented large language models. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. 5303\u20135315."},{"key":"e_1_3_1_70_2","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1145\/3589335.3648298","volume-title":"Companion Proceedings of the ACM on Web Conference 2024","author":"Peng Wenjun","year":"2024","unstructured":"Wenjun Peng, Guiyang Li, Yue Jiang, Zilong Wang, Dan Ou, Xiaoyi Zeng, Derong Xu, Tong Xu, and Enhong Chen. 2024. Large language model based long-tail query rewriting in taobao search. In Companion Proceedings of the ACM on Web Conference 2024. 20\u201328."},{"key":"e_1_3_1_71_2","article-title":"Generate rather than retrieve: Large language models are strong context generators","author":"Yu Wenhao","year":"2022","unstructured":"Wenhao Yu, Dan Iter, Shuohang Wang, Yichong Xu, Mingxuan Ju, Soumya Sanyal, Chenguang Zhu, Michael Zeng, and Meng Jiang. 2022. Generate rather than retrieve: Large language models are strong context generators. .arXiv:2209.10063. Retrieved from https:\/\/arxiv.org\/abs\/2209.10063","journal-title":"."},{"key":"e_1_3_1_72_2","doi-asserted-by":"crossref","first-page":"9248","DOI":"10.18653\/v1\/2023.findings-emnlp.620","volume-title":"Findings of the Association for Computational Linguistics: EMNLP 2023","author":"Shao Zhihong","year":"2023","unstructured":"Zhihong Shao, Yeyun Gong, Yelong Shen, Minlie Huang, Nan Duan, and Weizhu Chen. 2023. Enhancing retrieval-augmented large language models with iterative retrieval-generation synergy. In Findings of the Association for Computational Linguistics: EMNLP 2023. 9248\u20139274."},{"key":"e_1_3_1_73_2","first-page":"650","volume-title":"Findings of the Association for Computational Linguistics: EMNLP 2023","year":"2023","unstructured":"Daniele Comi, Dimitrios Christofidellis, Pier Francesco Piazza, and Matteo Manica. 2023. Zero-shot-BERT-Adapters: A zero-shot pipeline for unknown intent detection. In Findings of the Association for Computational Linguistics: EMNLP 2023. 650\u2013663."},{"key":"e_1_3_1_74_2","doi-asserted-by":"crossref","first-page":"1463","DOI":"10.18653\/v1\/2023.eacl-main.107","volume-title":"Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics","year":"2023","unstructured":"Yen-Ting Lin, Alexandros Papangelis, Seokhwan Kim, Sungjin Lee, Devamanyu Hazarika, Mahdi Namazifar, Di Jin, Yang Liu, and Dilek Hakkani-Tur. 2023. Selective in-context data augmentation for intent detection using pointwise V-information. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics. Association for Computational Linguistics, Dubrovnik, Croatia, 1463\u20131476. DOI:10.18653\/v1\/2023.eacl-main.107"},{"key":"e_1_3_1_75_2","doi-asserted-by":"crossref","first-page":"107","DOI":"10.18653\/v1\/2020.acl-main.11","volume-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics","year":"2020","unstructured":"Sam Coope, Tyler Farghly, Daniela Gerz, Ivan Vuli\u0107, and Matthew Henderson. 2020. Span-convert: Few-shot span extraction for dialog with pretrained conversational representations. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, Online, 107\u2013121. DOI:10.18653\/v1\/2020.acl-main.11"},{"key":"e_1_3_1_76_2","doi-asserted-by":"crossref","first-page":"3279","DOI":"10.1145\/3442381.3449870","volume-title":"Proceedings of the Web Conference 2021","author":"Siddique AB","year":"2021","unstructured":"AB Siddique, Fuad Jamour, and Vagelis Hristidis. 2021. Linguistically-enriched and context-awarezero-shot slot filling. In Proceedings of the Web Conference 2021. 3279\u20133290."},{"key":"e_1_3_1_77_2","doi-asserted-by":"crossref","first-page":"12109","DOI":"10.18653\/v1\/2023.emnlp-main.743","volume-title":"Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing","year":"2023","unstructured":"Hoang H. Nguyen, Ye Liu, Chenwei Zhang, Tao Zhang, and Philip S. Yu. 2023. CoF-CoT: Enhancing large language models with coarse-to-fine chain-of-thought prompting for multi-domain NLU tasks. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Singapore, 12109\u201312119. DOI:10.18653\/v1\/2023.emnlp-main.743"},{"key":"e_1_3_1_78_2","first-page":"5478","volume-title":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","author":"Lee Hwaran","year":"2019","unstructured":"Hwaran Lee, Jinsik Lee, and Tae-Yoon Kim. 2019. SUMBT: Slot-utterance matching for universal and scalable belief tracking. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, Florence, Italy, 5478\u20135483. DOI:10.18653\/v1\/P19-1546"},{"key":"e_1_3_1_79_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.193"},{"key":"e_1_3_1_80_2","first-page":"3019","volume-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing","author":"Wang Yexiang","year":"2020","unstructured":"Yexiang Wang, Yi Guo, and Siqi Zhu. 2020. Slot attention with value normalization for multi-domain dialogue state tracking. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing. 3019\u20133028."},{"key":"e_1_3_1_81_2","first-page":"3391","volume-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics","year":"2020","unstructured":"Zhaojiang Lin, Andrea Madotto, Genta Indra Winata, and Pascale Fung. 2020. MinTL: Minimalist transfer learning for task-oriented dialogue systems. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Online, 3391\u20133405. DOI:10.18653\/v1\/2020.emnlp-main.273"},{"key":"e_1_3_1_82_2","doi-asserted-by":"crossref","first-page":"739","DOI":"10.18653\/v1\/2023.emnlp-main.48","volume-title":"Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing","year":"2023","unstructured":"Yujie Feng, Zexin Lu, Bo Liu, Liming Zhan, and Xiao-Ming Wu. 2023. Towards LLM-driven dialogue state tracking. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Singapore, 739\u2013755. DOI:10.18653\/v1\/2023.emnlp-main.48"},{"key":"e_1_3_1_83_2","doi-asserted-by":"crossref","first-page":"5570","DOI":"10.18653\/v1\/2023.findings-acl.344","volume-title":"Findings of the Association for Computational Linguistics: ACL 2023","author":"King Brendan","year":"2023","unstructured":"Brendan King and Jeffrey Flanigan. 2023. Diverse retrieval-augmented in-context learning for dialogue state tracking. In Findings of the Association for Computational Linguistics: ACL 2023. 5570\u20135585."},{"key":"e_1_3_1_84_2","first-page":"1","volume-title":"Proceedings of the ICASSP 2025-2025 IEEE International Conference on Acoustics, Speech and Signal Processing","author":"Yi Zihao","year":"2025","unstructured":"Zihao Yi, Zhe Xu, and Ying Shen. 2025. Intent-driven in-context learning for few-shot dialogue state tracking. In Proceedings of the ICASSP 2025-2025 IEEE International Conference on Acoustics, Speech and Signal Processing. IEEE, 1\u20135."},{"key":"e_1_3_1_85_2","first-page":"12211","volume-title":"Proceedings of the ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing","author":"Feng Sijie","year":"2024","unstructured":"Sijie Feng, Haoxiang Su, Hongyan Xie, Di Wu, Hao Huang, and Wushour Silamu. 2024. Fact-aware summarization with contrastive learning for few-shot dialogue state tracking. In Proceedings of the ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing. IEEE, 12211\u201312215."},{"key":"e_1_3_1_86_2","volume-title":"Proceedings of the 10th International Conference on Learning Representations","author":"Jang Youngsoo","year":"2022","unstructured":"Youngsoo Jang, Jongmin Lee, and Kee-Eung Kim. 2022. GPT-critic: Offline reinforcement learning for end-to-end task-oriented dialogue systems. In Proceedings of the 10th International Conference on Learning Representations. International Conference on Learning Representations, ICLR."},{"key":"e_1_3_1_87_2","doi-asserted-by":"crossref","first-page":"92","DOI":"10.18653\/v1\/2022.acl-long.8","volume-title":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Ramachandran Govardana Sachithanandam","year":"2022","unstructured":"Govardana Sachithanandam Ramachandran, Kazuma Hashimoto, and Caiming Xiong. 2022. [CASPI] Causal-aware safe policy improvement for task-oriented dialogue. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Association for Computational Linguistics, Dublin, Ireland, 92\u2013102. DOI:10.18653\/v1\/2022.acl-long.8"},{"key":"e_1_3_1_88_2","first-page":"10749","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","year":"2022","unstructured":"Wanwei He, Yinpei Dai, Yinhe Zheng, Yuchuan Wu, Zheng Cao, Dermot Liu, Peng Jiang, Min Yang, Fei Huang, Luo Si, et\u00a0al. 2022. Galaxy: A generative pre-trained model for task-oriented dialog with semi-supervised learning and explicit policy injection. In Proceedings of the AAAI Conference on Artificial Intelligence. 10749\u201310757."},{"key":"e_1_3_1_89_2","first-page":"7101","volume-title":"Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing","author":"Yu Xiao","year":"2023","unstructured":"Xiao Yu, Maximillian Chen, and Zhou Yu. 2023. Prompt-based monte-carlo tree search for goal-oriented dialogue policy planning. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Singapore, 7101\u20137125. DOI:10.18653\/v1\/2023.emnlp-main.439"},{"key":"e_1_3_1_90_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.17"},{"key":"e_1_3_1_91_2","doi-asserted-by":"crossref","first-page":"183","DOI":"10.18653\/v1\/2020.acl-main.18","volume-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics","year":"2020","unstructured":"Zhiyu Chen, Harini Eavani, Wenhu Chen, Yinyin Liu, and William Yang Wang. 2020. Few-shot NLG with pre-trained language model. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, Online, 183\u2013190. DOI:10.18653\/v1\/2020.acl-main.18"},{"key":"e_1_3_1_92_2","doi-asserted-by":"crossref","first-page":"191","DOI":"10.18653\/v1\/2020.acl-main.19","volume-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics","author":"Baheti Ashutosh","year":"2020","unstructured":"Ashutosh Baheti, Alan Ritter, and Kevin Small. 2020. Fluent response generation for conversational question answering. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, Online, 191\u2013207. DOI:10.18653\/v1\/2020.acl-main.19"},{"key":"e_1_3_1_93_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.229"},{"key":"e_1_3_1_94_2","doi-asserted-by":"crossref","first-page":"807","DOI":"10.1162\/tacl_a_00399","article-title":"Soloist: Building task bots at scale with transfer learning and machine teaching","volume":"9","year":"2021","unstructured":"Baolin Peng, Chunyuan Li, Jinchao Li, Shahin Shayandeh, Lars Liden, and Jianfeng Gao. 2021. Soloist: Building task bots at scale with transfer learning and machine teaching. Transactions of the Association for Computational Linguistics 9 (2021), 807\u2013824.","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"e_1_3_1_95_2","first-page":"20179","article-title":"A simple language model for task-oriented dialogue","volume":"33","year":"2020","unstructured":"Ehsan Hosseini-Asl, Bryan McCann, Chien-Sheng Wu, Semih Yavuz, and Richard Socher. 2020. A simple language model for task-oriented dialogue. Advances in Neural Information Processing Systems 33 (2020), 20179\u201320191.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_96_2","first-page":"14230","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","author":"Yang Yunyi","year":"2021","unstructured":"Yunyi Yang, Yunhao Li, and Xiaojun Quan. 2021. UBAR: Towards fully end-to-end task-oriented dialog system with GPT-2. In Proceedings of the AAAI Conference on Artificial Intelligence. 14230\u201314238."},{"key":"e_1_3_1_97_2","doi-asserted-by":"crossref","first-page":"5596","DOI":"10.18653\/v1\/2024.emnlp-main.320","volume-title":"Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing","author":"Saley Vishal Vivek","year":"2024","unstructured":"Vishal Vivek Saley, Rocktim Jyoti Das, Dinesh Raghu, and Mausam .2024. Synergizing in-context learning with hints for end-to-end task-oriented dialog systems. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, Yaser Al-Onaizan, Mohit Bansal, and Yun-Nung Chen (Eds.). Association for Computational Linguistics, Miami, Florida, USA, 5596\u20135612. DOI:10.18653\/v1\/2024.emnlp-main.320"},{"key":"e_1_3_1_98_2","first-page":"4661","volume-title":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","year":"2022","unstructured":"Yixuan Su, Lei Shu, Elman Mansimov, Arshit Gupta, Deng Cai, Yi-An Lai, and Yi Zhang. 2022. Multi-task pre-training for plug-and-play task-oriented dialogue system. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Association for Computational Linguistics, Dublin, Ireland, 4661\u20134676. DOI:10.18653\/v1\/2022.acl-long.319"},{"key":"e_1_3_1_99_2","first-page":"553","volume-title":"Proceedings of the 29th International Conference on Computational Linguistics","year":"2022","unstructured":"Wanwei He, Yinpei Dai, Binyuan Hui, Min Yang, Zheng Cao, Jianbo Dong, Fei Huang, Luo Si, and Yongbin Li. 2022. SPACE-2: Tree-structured semi-supervised contrastive pre-training for task-oriented dialog understanding. In Proceedings of the 29th International Conference on Computational Linguistics. International Committee on Computational Linguistics, Gyeongju, Republic of Korea, 553\u2013569. Retrieved from https:\/\/aclanthology.org\/2022.coling-1.46"},{"key":"e_1_3_1_100_2","doi-asserted-by":"crossref","first-page":"187","DOI":"10.1145\/3477495.3532069","volume-title":"Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval","year":"2022","unstructured":"Wanwei He, Yinpei Dai, Min Yang, Jian Sun, Fei Huang, Luo Si, and Yongbin Li. 2022. Unified dialog model pre-training for task-oriented dialog understanding and generation. In Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval. 187\u2013200."},{"key":"e_1_3_1_101_2","first-page":"15493","volume-title":"Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation","author":"Chieu Nguyen Quang","year":"2024","unstructured":"Nguyen Quang Chieu, Quang-Minh Tran, and Khac-Hoai Nam Bui. 2024. SynTOD: Augmented response synthesis for robust end-to-end task-oriented dialogue system. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation, Nicoletta Calzolari, Min-Yen Kan, Veronique Hoste, Alessandro Lenci, Sakriani Sakti, and Nianwen Xue (Eds.). ELRA and ICCL, Torino, Italia, 15493\u201315499. Retrieved from https:\/\/aclanthology.org\/2024.lrec-main.1346"},{"key":"e_1_3_1_102_2","first-page":"210","volume-title":"Proceedings of the 2012 IEEE Spoken Language Technology Workshop","year":"2012","unstructured":"Li Deng, Gokhan Tur, Xiaodong He, and Dilek Hakkani-Tur. 2012. Use of kernel deep convex networks and end-to-end learning for spoken language understanding. In Proceedings of the 2012 IEEE Spoken Language Technology Workshop. IEEE, 210\u2013215."},{"key":"e_1_3_1_103_2","first-page":"5045","volume-title":"Proceedings of the 2012 IEEE International Conference on Acoustics, Speech and Signal Processing","year":"2012","unstructured":"Gokhan Tur, Li Deng, Dilek Hakkani-T\u00fcr, and Xiaodong He. 2012. Towards deeper understanding: Deep convex networks for semantic utterance classification. In Proceedings of the 2012 IEEE International Conference on Acoustics, Speech and Signal Processing. IEEE, 5045\u20135048."},{"key":"e_1_3_1_104_2","first-page":"744","volume-title":"Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 5: Industry Track)","year":"2023","unstructured":"Soham Parikh, Quaizar Vohra, Prashil Tumbade, and Mitul Tiwari. 2023. Exploring zero and few-shot techniques for intent classification. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 5: Industry Track). Association for Computational Linguistics, Toronto, Canada, 744\u2013751. DOI:10.18653\/v1\/2023.acl-industry.71"},{"key":"e_1_3_1_105_2","unstructured":"Qian Chen Zhu Zhuo and Wen Wang. 2019. Bert for joint intent classification and slot filling. arXiv. arXiv:1902.10909. Retrieved from https:\/\/arxiv.org\/abs\/1902.10909"},{"key":"e_1_3_1_106_2","doi-asserted-by":"crossref","first-page":"830","DOI":"10.1109\/ASRU46091.2019.9003911","volume-title":"Proceedings of the 2019 IEEE Automatic Speech Recognition and Understanding Workshop","author":"Balaraman Vevake","year":"2019","unstructured":"Vevake Balaraman and Bernardo Magnini. 2019. Scalable neural dialogue state tracking. In Proceedings of the 2019 IEEE Automatic Speech Recognition and Understanding Workshop. IEEE, 830\u2013837."},{"key":"e_1_3_1_107_2","doi-asserted-by":"crossref","first-page":"1458","DOI":"10.18653\/v1\/P18-1135","volume-title":"Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Zhong Victor","year":"2018","unstructured":"Victor Zhong, Caiming Xiong, and Richard Socher. 2018. Global-locally self-attentive encoder for dialogue state tracking. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 1458\u20131467."},{"key":"e_1_3_1_108_2","doi-asserted-by":"crossref","first-page":"625","DOI":"10.18653\/v1\/2020.acl-main.59","volume-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics","author":"Takanobu Ryuichi","year":"2020","unstructured":"Ryuichi Takanobu, Runze Liang, and Minlie Huang. 2020. Multi-agent task-oriented dialog policy learning with role-aware reward decomposition. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, Online, 625\u2013638. DOI:10.18653\/v1\/2020.acl-main.59"},{"key":"e_1_3_1_109_2","first-page":"3461","volume-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing","year":"2020","unstructured":"Sihan Wang, Kaijie Zhou, Kunfeng Lai, and Jianping Shen. 2020. Task-completion dialogue policy learning via Monte Carlo tree search with dueling network. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing. 3461\u20133471."},{"key":"e_1_3_1_110_2","doi-asserted-by":"crossref","first-page":"1394","DOI":"10.18653\/v1\/2020.acl-main.129","volume-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics","author":"Gordon-Hall Gabriel","year":"2020","unstructured":"Gabriel Gordon-Hall, Philip John Gorinski, and Shay B. Cohen. 2020. Learning dialog policies from weak demonstrations. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, Online, 1394\u20131405. DOI:10.18653\/v1\/2020.acl-main.129"},{"key":"e_1_3_1_111_2","doi-asserted-by":"crossref","first-page":"3696","DOI":"10.18653\/v1\/P19-1360","volume-title":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","year":"2019","unstructured":"Wenhu Chen, Jianshu Chen, Pengda Qin, Xifeng Yan, and William Yang Wang. 2019. Semantically conditioned dialog response generation via hierarchical disentangled self-attention. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, Florence, Italy, 3696\u20133709. DOI:10.18653\/v1\/P19-1360"},{"key":"e_1_3_1_112_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.39"},{"key":"e_1_3_1_113_2","doi-asserted-by":"crossref","first-page":"15","DOI":"10.18653\/v1\/D19-5602","volume-title":"Proceedings of the 3rd Workshop on Neural Generation and Translation","author":"Budzianowski Pawe\u0142","year":"2019","unstructured":"Pawe\u0142 Budzianowski and Ivan Vuli\u0107. 2019. Hello, it\u2019s GPT-2 - How can i help you? towards the use of pretrained language models for task-oriented dialogue systems. In Proceedings of the 3rd Workshop on Neural Generation and Translation. Association for Computational Linguistics, Hong Kong, 15\u201322. DOI:10.18653\/v1\/D19-5602"},{"key":"e_1_3_1_114_2","doi-asserted-by":"publisher","DOI":"10.1017\/S1351324997001502"},{"key":"e_1_3_1_115_2","doi-asserted-by":"crossref","first-page":"275","DOI":"10.18653\/v1\/W15-4639","volume-title":"Proceedings of the 16th Annual Meeting of the Special Interest Group on Discourse and Dialogue","year":"2015","unstructured":"Tsung-Hsien Wen, Milica Gasic, Dongho Kim, Nikola Mrksic, Pei-Hao Su, David Vandyke, and Steve Young. 2015. Stochastic language generation in dialogue using recurrent neural networks with convolutional sentence reranking. In Proceedings of the 16th Annual Meeting of the Special Interest Group on Discourse and Dialogue. Association for Computational Linguistics, Prague, Czech Republic, 275\u2013284. DOI:10.18653\/v1\/W15-4639"},{"key":"e_1_3_1_116_2","first-page":"1711","volume-title":"Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing","author":"al. Tsung-Hsien Wen et","year":"2015","unstructured":"Tsung-Hsien Wen et al.2015. Semantically conditioned LSTM-based natural language generation for spoken dialogue systems. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Lisbon, Portugal, 1711\u20131721. DOI:10.18653\/v1\/D15-1199"},{"key":"e_1_3_1_117_2","first-page":"2032","volume-title":"Proceedings of the 26th International Conference on Computational Linguistics: Technical Papers","author":"Zhou Hao","year":"2016","unstructured":"Hao Zhou, Minlie Huang, and Xiaoyan Zhu. 2016. Context-aware natural language generation for spoken dialogue systems. In Proceedings of the 26th International Conference on Computational Linguistics: Technical Papers. 2032\u20132041."},{"key":"e_1_3_1_118_2","doi-asserted-by":"crossref","first-page":"8283","DOI":"10.18653\/v1\/2024.emnlp-main.473","volume-title":"Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing","author":"King Brendan","year":"2024","unstructured":"Brendan King and Jeffrey Flanigan. 2024. Unsupervised end-to-end task-oriented dialogue with LLMs: The power of the noisy channel. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 8283\u20138300."},{"key":"e_1_3_1_119_2","first-page":"6769","volume-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing","author":"al. Vladimir Karpukhin et","year":"2020","unstructured":"Vladimir Karpukhin et al.2020. Dense passage retrieval for open-domain question answering. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Online, 6769\u20136781. DOI:10.18653\/v1\/2020.emnlp-main.550"},{"key":"e_1_3_1_120_2","first-page":"111","volume-title":"Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing","author":"al. Chunyuan Yuan et","year":"2019","unstructured":"Chunyuan Yuan et al.2019. Multi-hop selector network for multi-turn response selection in retrieval-based chatbots. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing. 111\u2013120."},{"key":"e_1_3_1_121_2","first-page":"1","volume-title":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","author":"al. Chongyang Tao et","year":"2019","unstructured":"Chongyang Tao et al.2019. One time of interaction may not be enough: Go deep with an interaction-over-interaction network for response selection in dialogues. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. 1\u201311."},{"key":"e_1_3_1_122_2","unstructured":"Akari Asai Zeqiu Wu Yizhong Wang Avirup Sil and Hannaneh Hajishirzi. 2023. Self-rag: Learning to retrieve generate and critique through self-reflection. arXiv:2310.11511. Retrieved from https:\/\/arxiv.org\/abs\/2310.11511"},{"key":"e_1_3_1_123_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.207"},{"key":"e_1_3_1_124_2","first-page":"5454","volume-title":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","author":"al. Andrea Madotto et","year":"2019","unstructured":"Andrea Madotto et al.2019. Personalizing dialogue agents via meta-learning. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. 5454\u20135459."},{"key":"e_1_3_1_125_2","unstructured":"Ruijun Chen et al.2023. Learning to memorize entailment and discourse relations for persona-consistent dialogues. arXiv:2301.04871. Retrieved from https:\/\/arxiv.org\/abs\/2301.04871"},{"issue":"4","key":"e_1_3_1_126_2","first-page":"1","article-title":"Dialogue history matters! personalized response selection in multi-turn retrieval-based chatbots","author":"al. Juntao Li et","year":"2021","unstructured":"Juntao Li et al.2021. Dialogue history matters! personalized response selection in multi-turn retrieval-based chatbots. ACM Transactions on Information Systems39, 4 (2021), 1\u201325.","journal-title":"ACM Transactions on Information Systems39"},{"key":"e_1_3_1_127_2","first-page":"555","volume-title":"Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval","author":"al. Zhengyi Ma et","year":"2021","unstructured":"Zhengyi Ma et al.2021. One chatbot per person: Creating personalized chatbots based on implicit user profiles. In Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval. 555\u2013564."},{"key":"e_1_3_1_128_2","first-page":"5808","volume-title":"Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","author":"al. Hanxun Zhong et","year":"2022","unstructured":"Hanxun Zhong et al.2022. Less is more: Learning to refine dialogue history for personalized dialogue generation. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Association for Computational Linguistics, Seattle, United States, 5808\u20135820. DOI:10.18653\/v1\/2022.naacl-main.426"},{"key":"e_1_3_1_129_2","first-page":"5821","volume-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics","author":"al. Haoyu Song et","year":"2020","unstructured":"Haoyu Song et al.2020. Generate, delete and rewrite: A three-stage framework for improving persona consistency of dialogue generation. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, Online, 5821\u20135831. DOI:10.18653\/v1\/2020.acl-main.516"},{"key":"e_1_3_1_130_2","first-page":"5456","volume-title":"Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"al. Yihong Tang et","year":"2023","unstructured":"Yihong Tang et al.2023. Enhancing personalized dialogue generation with contrastive latent variables: Combining sparse and dense persona. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Association for Computational Linguistics, Toronto, Canada, 5456\u20135468. DOI:10.18653\/v1\/2023.acl-long.299"},{"key":"e_1_3_1_131_2","article-title":"Leandojo: Theorem proving with retrieval-augmented language models","volume":"36","author":"Yang Kaiyu","year":"2024","unstructured":"Kaiyu Yang, Aidan Swope, Alex Gu, Rahul Chalamala, Peiyang Song, Shixing Yu, Saad Godil, Ryan J. Prenger, and Animashree Anandkumar. 2024. Leandojo: Theorem proving with retrieval-augmented language models. Advances in Neural Information Processing Systems 36 (2024), 21573\u201321612.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_132_2","first-page":"2206","volume-title":"Proceedings of the International Conference on Machine Learning","author":"al. Sebastian Borgeaud et","year":"2022","unstructured":"Sebastian Borgeaud et al.2022. Improving language models by retrieving from trillions of tokens. In Proceedings of the International Conference on Machine Learning. PMLR, 2206\u20132240."},{"key":"e_1_3_1_133_2","first-page":"874","volume-title":"Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume","author":"Izacard Gautier","year":"2021","unstructured":"Gautier Izacard and Edouard Grave. 2021. Leveraging passage retrieval with generative models for open domain question answering. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume. Association for Computational Linguistics, Online, 874\u2013880. DOI:10.18653\/v1\/2021.eacl-main.74"},{"key":"e_1_3_1_134_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.527"},{"key":"e_1_3_1_135_2","first-page":"25968","article-title":"End-to-end training of multi-document reader and retriever for open-domain question answering","volume":"34","author":"al. Devendra Singh et","year":"2021","unstructured":"Devendra Singh et al.2021. End-to-end training of multi-document reader and retriever for open-domain question answering. Advances in Neural Information Processing Systems 34 (2021), 25968\u201325981.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_136_2","first-page":"6086","volume-title":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","author":"Lee Kenton","year":"2019","unstructured":"Kenton Lee, Ming-Wei Chang, and Kristina Toutanova. 2019. Latent retrieval for weakly supervised open domain question answering. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, Florence, Italy, 6086\u20136096. DOI:10.18653\/v1\/P19-1612"},{"key":"e_1_3_1_137_2","doi-asserted-by":"crossref","first-page":"8460","DOI":"10.18653\/v1\/2022.acl-long.579","volume-title":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Komeili Mojtaba","year":"2022","unstructured":"Mojtaba Komeili, Kurt Shuster, and Jason Weston. 2022. Internet-augmented dialogue generation. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Association for Computational Linguistics, Dublin, Ireland, 8460\u20138478. DOI:10.18653\/v1\/2022.acl-long.579"},{"key":"e_1_3_1_138_2","unstructured":"Wenhao Yu Hongming Zhang Xiaoman Pan Kaixin Ma Hongwei Wang and Dong Yu. 2023. Chain-of-note: Enhancing robustness in retrieval-augmented language models. arXiv:2311.09210. Retrieved from https:\/\/arxiv.org\/abs\/2311.09210"},{"key":"e_1_3_1_139_2","unstructured":"Antoine Bordes Y.-Lan Boureau and Jason Weston. 2016. Learning end-to-end goal-oriented dialog. arXiv:1605.07683. Retrieved from https:\/\/arxiv.org\/abs\/1605.07683"},{"key":"e_1_3_1_140_2","unstructured":"Matthew Henderson Rami Al-Rfou Brian Strope Yun-Hsuan Sung L\u00e1szl\u00f3 Luk\u00e1cs Ruiqi Guo Sanjiv Kumar Balint Miklos and Ray Kurzweil. 2017. Efficient natural language response suggestion for smart reply. arXiv:1705.00652. Retrieved from https:\/\/arxiv.org\/abs\/1705.00652"},{"key":"e_1_3_1_141_2","unstructured":"Oriol Vinyals and Quoc Le. 2015. A Neural Conversational Model. arXiv:1506.05869. Retrieved from https:\/\/arxiv.org\/abs\/1506.05869"},{"key":"e_1_3_1_142_2","article-title":"Sequence to sequence learning with neural networks","volume":"27","author":"Sutskever Ilya","year":"2014","unstructured":"Ilya Sutskever, Oriol Vinyals, and Quoc V. Le. 2014. Sequence to sequence learning with neural networks. Advances in Neural Information Processing Systems 27 (2014), 3104\u20133112.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_143_2","first-page":"1577","volume-title":"Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)","author":"Shang Lifeng","year":"2015","unstructured":"Lifeng Shang, Zhengdong Lu, and Hang Li. 2015. Neural responding machine for short-text conversation. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). Association for Computational Linguistics, Beijing, China, 1577\u20131586. DOI:10.3115\/v1\/P15-1152"},{"key":"e_1_3_1_144_2","doi-asserted-by":"crossref","first-page":"3377","DOI":"10.18653\/v1\/2020.emnlp-main.272","volume-title":"Proceedings of the 2020 conference on empirical methods in natural language processing (EMNLP)","year":"2020","unstructured":"Xueliang Zhao, Wei Wu, Can Xu, Chongyang Tao, Dongyan Zhao, and Rui Yan. 2020. Knowledge-grounded dialogue generation with pre-trained language models. In Proceedings of the 2020 conference on empirical methods in natural language processing (EMNLP). Association for Computational Linguistics, Online, 3377\u20133390. DOI:10.18653\/v1\/2020.emnlp-main.272"},{"key":"e_1_3_1_145_2","first-page":"196","volume-title":"Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","year":"2015","unstructured":"Alessandro Sordoni, Michel Galley, Michael Auli, Chris Brockett, Yangfeng Ji, Margaret Mitchell, Jian-Yun Nie, Jianfeng Gao, and Bill Dolan. 2015. A neural network approach to context-sensitive generation of conversational responses. In Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Association for Computational Linguistics, Denver, Colorado, 196\u2013205. DOI:10.3115\/v1\/N15-1020"},{"key":"e_1_3_1_146_2","first-page":"516","volume-title":"Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","year":"2016","unstructured":"Zhao Yan, Nan Duan, Junwei Bao, Peng Chen, Ming Zhou, Zhoujun Li, and Jianshe Zhou. 2016. Docchat: An information retrieval approach for chatbot engines using unstructured documents. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 516\u2013525."},{"key":"e_1_3_1_147_2","first-page":"292","volume-title":"Proceedings of the 15th Annual Meeting of the Special Interest Group on Discourse and Dialogue","author":"Henderson Matthew","year":"2014","unstructured":"Matthew Henderson, Blaise Thomson, and Steve Young. 2014. Word-based dialog state tracking with recurrent neural networks. In Proceedings of the 15th Annual Meeting of the Special Interest Group on Discourse and Dialogue. 292\u2013299."},{"key":"e_1_3_1_148_2","doi-asserted-by":"crossref","first-page":"808","DOI":"10.18653\/v1\/P19-1078","volume-title":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","year":"2019","unstructured":"Chien-Sheng Wu, Andrea Madotto, Ehsan Hosseini-Asl, Caiming Xiong, Richard Socher, and Pascale Fung. 2019. Transferable multi-domain state generator for task-oriented dialogue systems. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, Florence, Italy, 808\u2013819. DOI:10.18653\/v1\/P19-1078"},{"key":"e_1_3_1_149_2","first-page":"8689","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","year":"2020","unstructured":"Abhinav Rastogi, Xiaoxue Zang, Srinivas Sunkara, Raghav Gupta, and Pranav Khaitan. 2020. Towards scalable multi-domain conversational agents: The schema-guided dialogue dataset. In Proceedings of the AAAI Conference on Artificial Intelligence. 8689\u20138696."},{"key":"e_1_3_1_150_2","first-page":"311","volume-title":"Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics","year":"2002","unstructured":"Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. Bleu: A method for automatic evaluation of machine translation. In Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics. 311\u2013318."},{"key":"e_1_3_1_151_2","first-page":"110","volume-title":"Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","year":"2016","unstructured":"Jiwei Li, Michel Galley, Chris Brockett, Jianfeng Gao, and Bill Dolan. 2016. A diversity-promoting objective function for neural conversation models. In Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Association for Computational Linguistics, San Diego, California, 110\u2013119. DOI:10.18653\/v1\/N16-1014"},{"key":"e_1_3_1_152_2","doi-asserted-by":"crossref","first-page":"5016","DOI":"10.18653\/v1\/D18-1547","volume-title":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing","year":"2018","unstructured":"Pawe\u0142 Budzianowski, Tsung-Hsien Wen, Bo-Hsiang Tseng, I\u00f1igo Casanueva, Stefan Ultes, Osman Ramadan, and Milica Ga\u0161i\u0107. 2018. MultiWOZ - A large-scale multi-domain wizard-of-oz dataset for task-oriented dialogue modelling. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Brussels, Belgium, 5016\u20135026. DOI:10.18653\/v1\/D18-1547"},{"key":"e_1_3_1_153_2","first-page":"422","volume-title":"Proceedings of the 12th Language Resources and Evaluation Conference","year":"2020","unstructured":"Mihail Eric, Rahul Goel, Shachi Paul, Adarsh Kumar, Abhishek Sethi, Peter Ku, Anuj Kumar Goyal, Sanchit Agarwal, Shuyang Gao, and Dilek Hakkani-Tur. 2020. MultiWOZ 2.1: A consolidated multi-domain dialogue dataset with state corrections and state tracking baselines. In Proceedings of the 12th Language Resources and Evaluation Conference. European Language Resources Association, Marseille, France, 422\u2013428. https:\/\/aclanthology.org\/2020.lrec-1.53"},{"key":"e_1_3_1_154_2","doi-asserted-by":"crossref","first-page":"109","DOI":"10.18653\/v1\/2020.nlp4convai-1.13","volume-title":"Proceedings of the 2nd Workshop on Natural Language Processing for Conversational AI","year":"2020","unstructured":"Xiaoxue Zang, Abhinav Rastogi, Srinivas Sunkara, Raghav Gupta, Jianguo Zhang, and Jindong Chen. 2020. MultiWOZ 2.2 : A dialogue dataset with additional annotation corrections and state tracking baselines. In Proceedings of the 2nd Workshop on Natural Language Processing for Conversational AI. Association for Computational Linguistics, Online, 109\u2013117. DOI:10.18653\/v1\/2020.nlp4convai-1.13"},{"key":"e_1_3_1_155_2","first-page":"206","volume-title":"Natural Language Processing and Chinese Computing: 10th CCF International Conference, NLPCC 2021, Qingdao, China, October 13\u201317, 2021, Proceedings, Part II 10","year":"2021","unstructured":"Ting Han, Ximing Liu, Ryuichi Takanabu, Yixin Lian, Chongxuan Huang, Dazhen Wan, Wei Peng, and Minlie Huang. 2021. Multiwoz 2.3: A multi-domain task-oriented dialogue dataset enhanced with annotation corrections and co-reference annotation. In Natural Language Processing and Chinese Computing: 10th CCF International Conference, NLPCC 2021, Qingdao, China, October 13\u201317, 2021, Proceedings, Part II 10. Springer, 206\u2013218."},{"key":"e_1_3_1_156_2","first-page":"351","volume-title":"Proceedings of the 23rd Annual Meeting of the Special Interest Group on Discourse and Dialogue","author":"Ye Fanghua","year":"2022","unstructured":"Fanghua Ye, Jarana Manotumruksa, and Emine Yilmaz. 2022. MultiWOZ 2.4: A multi-domain task-oriented dialogue dataset with essential annotation corrections to improve state tracking evaluation. In Proceedings of the 23rd Annual Meeting of the Special Interest Group on Discourse and Dialogue. Association for Computational Linguistics, Edinburgh, UK, 351\u2013360. DOI:10.18653\/v1\/2022.sigdial-1.34"},{"key":"e_1_3_1_157_2","first-page":"930","volume-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing","year":"2020","unstructured":"Jun Quan, Shian Zhang, Qian Cao, Zizhong Li, and Deyi Xiong. 2020. RiSAWOZ: A large-scale multi-domain wizard-of-oz dataset with rich semantic annotations for task-oriented dialogue modeling. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Online, 930\u2013940. DOI:10.18653\/v1\/2020.emnlp-main.67"},{"key":"e_1_3_1_158_2","doi-asserted-by":"crossref","first-page":"281","DOI":"10.1162\/tacl_a_00314","article-title":"Crosswoz: A large-scale chinese cross-domain task-oriented dialogue dataset","volume":"8","year":"2020","unstructured":"Qi Zhu, Kaili Huang, Zheng Zhang, Xiaoyan Zhu, and Minlie Huang. 2020. Crosswoz: A large-scale chinese cross-domain task-oriented dialogue dataset. Transactions of the Association for Computational Linguistics 8 (2020), 281\u2013295.","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"e_1_3_1_159_2","doi-asserted-by":"crossref","first-page":"5635","DOI":"10.18653\/v1\/P19-1566","volume-title":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","year":"2019","unstructured":"Xuewei Wang, Weiyan Shi, Richard Kim, Yoojung Oh, Sijia Yang, Jingwen Zhang, and Zhou Yu. 2019. Persuasion for good: Towards a personalized persuasive dialogue system for social good. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, Florence, Italy, 5635\u20135649. DOI:10.18653\/v1\/P19-1566"},{"key":"e_1_3_1_160_2","first-page":"1777","volume-title":"Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","year":"2017","unstructured":"Nikola Mrk\u0161i\u0107, Diarmuid O. Seaghdha, Tsung-Hsien Wen, Blaise Thomson, and Steve Young. 2017. Neural belief tracker: Data-driven dialogue state tracking. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Association for Computational Linguistics, Vancouver, Canada, 1777\u20131788. DOI:10.18653\/v1\/P17-1163"},{"key":"e_1_3_1_161_2","first-page":"438","volume-title":"Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers","year":"2017","unstructured":"Tsung-Hsien Wen, David Vandyke, Nikola Mrksic, Milica Gasic, Lina M. Rojas-Barahona, Pei-Hao Su, Stefan Ultes, and Steve Young. 2017. A network-based end-to-end trainable task-oriented dialogue system. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers. Valencia, Spain, 438\u2013449. Retrieved from https:\/\/aclanthology.org\/E17-1042"},{"key":"e_1_3_1_162_2","first-page":"37","volume-title":"Proceedings of the 18th Annual SIGdial Meeting on Discourse and Dialogue","year":"2017","unstructured":"Mihail Eric and Christopher D. Manning. 2017. Key-value retrieval networks for task-oriented dialogue. In Proceedings of the 18th Annual SIGdial Meeting on Discourse and Dialogue. Association for Computational Linguistics, Saarbr\u00fccken, Germany, 37\u201349. DOI:10.18653\/v1\/W17-5506"},{"key":"e_1_3_1_163_2","first-page":"2204","volume-title":"Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","year":"2018","unstructured":"Saizheng Zhang, Emily Dinan, Jack Urbanek, Arthur Szlam, Douwe Kiela, and Jason Weston. 2018. Personalizing dialogue agents: I have a dog, do you have pets too?. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Association for Computational Linguistics, Melbourne, Australia, 2204\u20132213. DOI:10.18653\/v1\/P18-1205"},{"key":"e_1_3_1_164_2","first-page":"7348","volume-title":"Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","year":"2023","unstructured":"Jiazhan Feng, Qingfeng Sun, Can Xu, Pu Zhao, Yaming Yang, Chongyang Tao, Dongyan Zhao, and Qingwei Lin. 2023. MMDialog: A large-scale multi-turn dialogue dataset towards multi-modal open-domain conversation. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 7348\u20137363. DOI:10.18653\/v1\/2023.acl-long.405"},{"key":"e_1_3_1_165_2","first-page":"986","volume-title":"Proceedings of the 8th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)","year":"2017","unstructured":"Yanran Li, Hui Su, Xiaoyu Shen, Wenjie Li, Ziqiang Cao, and Shuzi Niu. 2017. Dailydialog: A manually labelled multi-turn dialogue dataset. In Proceedings of the 8th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). Asian Federation of Natural Language Processing, Taipei, Taiwan, 986\u2013995. https:\/\/aclanthology.org\/I17-1099"},{"key":"e_1_3_1_166_2","doi-asserted-by":"crossref","first-page":"2470","DOI":"10.1145\/3404835.3463239","volume-title":"Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval","year":"2021","unstructured":"Hongjin Qian, Xiaohe Li, Hanxun Zhong, Yu Guo, Yueyuan Ma, Yutao Zhu, Zhanliang Liu, Zhicheng Dou, and Ji-Rong Wen. 2021. Pchatbot: A large-scale dataset for personalized chatbot. In Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval. 2470\u20132477."},{"key":"e_1_3_1_167_2","unstructured":"Yinhe Zheng Guanyi Chen Minlie Huang Song Liu and Xuan Zhu. 2019. Personalized dialogue generation with diversified traits. arXiv:1901.09672. Retrieved from https:\/\/arxiv.org\/abs\/1901.09672"},{"key":"e_1_3_1_168_2","first-page":"1","volume-title":"Proceedings of the 2023 IEEE High Performance Extreme Computing Conference","author":"Samsi Siddharth","year":"2023","unstructured":"Siddharth Samsi, Dan Zhao, Joseph McDonald, Baolin Li, Adam Michaleas, Michael Jones, William Bergeron, Jeremy Kepner, Devesh Tiwari, and Vijay Gadepally. 2023. From words to watts: Benchmarking the energy costs of large language model inference. In Proceedings of the 2023 IEEE High Performance Extreme Computing Conference. IEEE, 1\u20139."},{"key":"e_1_3_1_169_2","first-page":"87","article-title":"Awq: Activation-aware weight quantization for on-device llm compression and acceleration","volume":"6","year":"2024","unstructured":"Ji Lin, Jiaming Tang, Haotian Tang, Shang Yang, Wei-Ming Chen, Wei-Chen Wang, Guangxuan Xiao, Xingyu Dang, Chuang Gan, and Song Han. 2024. Awq: Activation-aware weight quantization for on-device llm compression and acceleration. Proceedings of Machine Learning and Systems 6 (2024), 87\u2013100.","journal-title":"Proceedings of Machine Learning and Systems"},{"issue":"8","key":"e_1_3_1_170_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3711121","article-title":"Knowledge distillation on graphs: A survey","volume":"57","author":"Tian Yijun","year":"2025","unstructured":"Yijun Tian, Shichao Pei, Xiangliang Zhang, Chuxu Zhang, and Nitesh V. Chawla. 2025. Knowledge distillation on graphs: A survey. Computing Surveys 57, 8 (2025), 1\u201316.","journal-title":"Computing Surveys"},{"key":"e_1_3_1_171_2","doi-asserted-by":"crossref","unstructured":"Jamin Shin Hangyeol Yu Hyeongdon Moon Andrea Madotto and Juneyoung Park. 2022. Dialogue summaries as dialogue states (DS2) template-guided summarization for few-shot dialogue state tracking. arXiv:2203.01552. Retrieved from https:\/\/arxiv.org\/abs\/2203.01552","DOI":"10.18653\/v1\/2022.findings-acl.302"},{"key":"e_1_3_1_172_2","unstructured":"Ning Shang Li Lyna Zhang Siyuan Wang Gaokai Zhang Gilsinia Lopez Fan Yang Weizhu Chen and Mao Yang. 2025. LongRoPE2: Near-lossless LLM context window scaling. arXiv:2502.20082. Retrieved from https:\/\/arxiv.org\/abs\/2502.20082"},{"key":"e_1_3_1_173_2","unstructured":"Yubo Li Xiaobin Shen Xinyu Yao Xueying Ding Yidi Miao Ramayya Krishnan and Rema Padman. 2025. Beyond single-turn: A survey on multi-turn interactions with large language models. arXiv:2504.04717. Retrieved from https:\/\/arxiv.org\/abs\/2504.04717"},{"key":"e_1_3_1_174_2","article-title":"OmniDialog: An omnipotent pre-training model for task-oriented dialogue system","author":"Yang Mingtao","year":"2025","unstructured":"Mingtao Yang, See-Kiong Ng, and Jinlan Fu. 2025. OmniDialog: An omnipotent pre-training model for task-oriented dialogue system. IEEE Transactions on Audio, Speech and Language Processing. 1\u201311.","journal-title":"IEEE Transactions on Audio, Speech and Language Processing"},{"key":"e_1_3_1_175_2","first-page":"15174","volume-title":"Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2024, Bangkok, Thailand, August 11-16, 2024","author":"Qian Chen","year":"2024","unstructured":"Chen Qian, Wei Liu, Hongzhang Liu, Nuo Chen, Yufan Dang, Jiahao Li, Cheng Yang, Weize Chen, Yusheng Su, Xin Cong, et\u00a0al. 2024. ChatDev: Communicative agents for software development. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2024, Bangkok, Thailand, August 11-16, 2024, Lun-Wei Ku, Andre Martins, and Vivek Srikumar (Eds.). Association for Computational Linguistics, 15174\u201315186. DOI:10.18653\/V1\/2024.ACL-LONG.810"},{"key":"e_1_3_1_176_2","volume-title":"Proceedings of the 12th International Conference on Learning Representations, Vienna, Austria, May 7-11, 2024","author":"Hong Sirui","year":"2024","unstructured":"Sirui Hong, Mingchen Zhuge, Jonathan Chen, Xiawu Zheng, Yuheng Cheng, Jinlin Wang, Ceyao Zhang, Zili Wang, Steven Ka Shing Yau, Zijuan Lin, et\u00a0al. 2024. MetaGPT: Meta programming for a multi-agent collaborative framework. In Proceedings of the 12th International Conference on Learning Representations, Vienna, Austria, May 7-11, 2024. OpenReview.net. Retrieved from https:\/\/openreview.net\/forum?id=VtmBAGCN7o"},{"key":"e_1_3_1_177_2","volume-title":"Proceedings of the 12th International Conference on Learning Representations, Vienna, Austria, May 7-11, 2024","year":"2024","unstructured":"Xiao Liu, Hao Yu, Hanchen Zhang, Yifan Xu, Xuanyu Lei, Hanyu Lai, Yu Gu, Hangliang Ding, Kaiwen Men, Kejuan Yang, et\u00a0al. 2024. AgentBench: Evaluating llms as agents. In Proceedings of the 12th International Conference on Learning Representations, Vienna, Austria, May 7-11, 2024. OpenReview.net. Retrieved from https:\/\/openreview.net\/forum?id=zAdUB0aCTQ"},{"key":"e_1_3_1_178_2","first-page":"14232","volume-title":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Vienna, Austria, July 27 - August 1, 2025","author":"Luo Haohao","year":"2025","unstructured":"Haohao Luo, Jiayi Kuang, Wei Liu, Ying Shen, Jian Luan, and Yang Deng. 2025. Browsing like human: A multimodal web agent with experiential fast-and-slow thinking. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Vienna, Austria, July 27 - August 1, 2025, Wanxiang Che, Joyce Nabende, Ekaterina Shutova, and Mohammad Taher Pilehvar (Eds.). Association for Computational Linguistics, 14232\u201314251. Retrieved from https:\/\/aclanthology.org\/2025.acl-long.697\/"},{"key":"e_1_3_1_179_2","volume-title":"Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, New Orleans, LA, USA, December 10-16, 2023","author":"Oh Alice","year":"2023","unstructured":"Xiang Deng, Yu Gu, Boyuan Zheng, Shijie Chen, Sam Stevens, Boshi Wang, Huan Sun, and Yu Su. 2023. Mind2Web: Towards a generalist agent for the web. In Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, New Orleans, LA, USA, December 10-16, 2023, Alice Oh, Tristan Naumann, Amir Globerson, Kate Saenko, Moritz Hardt, and Sergey Levine (Eds.). Retrieved from http:\/\/papers.nips.cc\/paper_files\/paper\/2023\/hash\/5950bf290a1570ea401bf98882128160-Abstract-Datasets_and_Benchmarks.html"},{"key":"e_1_3_1_180_2","unstructured":"Divyansh Agarwal Alexander R. Fabbri Ben Risher Philippe Laban Shafiq Joty and Chien-Sheng Wu. 2024. Prompt. arXiv:2404.16251. Retrieved from https:\/\/arxiv.org\/abs\/2404.16251"}],"container-title":["ACM Computing Surveys"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3771090","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T14:06:39Z","timestamp":1765202799000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3771090"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,8]]},"references-count":179,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2026,4,30]]}},"alternative-id":["10.1145\/3771090"],"URL":"https:\/\/doi.org\/10.1145\/3771090","relation":{},"ISSN":["0360-0300","1557-7341"],"issn-type":[{"value":"0360-0300","type":"print"},{"value":"1557-7341","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,8]]},"assertion":[{"value":"2024-02-23","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-10-01","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-12-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}