{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T00:53:12Z","timestamp":1774399992781,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":61,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,7,10]],"date-time":"2024-07-10T00:00:00Z","timestamp":1720569600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,7,10]]},"DOI":"10.1145\/3626772.3657760","type":"proceedings-article","created":{"date-parts":[[2024,7,11]],"date-time":"2024-07-11T12:40:05Z","timestamp":1720701605000},"page":"730-740","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":30,"title":["IM-RAG: Multi-Round Retrieval-Augmented Generation Through Learning Inner Monologues"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-1591-4846","authenticated-orcid":false,"given":"Diji","family":"Yang","sequence":"first","affiliation":[{"name":"University of California Santa Cruz, Santa Cruz, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2370-5129","authenticated-orcid":false,"given":"Jinmeng","family":"Rao","sequence":"additional","affiliation":[{"name":"Mineral.ai, Mountain View, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-2980-9339","authenticated-orcid":false,"given":"Kezhen","family":"Chen","sequence":"additional","affiliation":[{"name":"Together AI, San Francisco, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-8074-8399","authenticated-orcid":false,"given":"Xiaoyuan","family":"Guo","sequence":"additional","affiliation":[{"name":"Google, Mountain View, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5692-4147","authenticated-orcid":false,"given":"Yawen","family":"Zhang","sequence":"additional","affiliation":[{"name":"Mineral.ai, Mountain View, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-5313-4612","authenticated-orcid":false,"given":"Jie","family":"Yang","sequence":"additional","affiliation":[{"name":"Cybever, Mountain View, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4299-1511","authenticated-orcid":false,"given":"Yi","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of California Santa Cruz, Santa Cruz, CA, USA"}]}],"member":"320","published-online":{"date-parts":[[2024,7,11]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2023.08.001"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","unstructured":"Edward Beeching Younes Belkada Kashif Rasul Lewis Tunstall Leandro von Werra Nazneen Rajani and Nathan Lambert. 2023. StackLLaMA: An RL Fine-tuned LLaMA Model for Stack Exchange Question and Answering. https:\/\/doi.org\/10.57967\/hf\/0513","DOI":"10.57967\/hf\/0513"},{"key":"e_1_3_2_1_3_1","unstructured":"K Cherney. 2023. Everything to Know About Your Internal Monologue."},{"key":"e_1_3_2_1_4_1","volume-title":"Xing","author":"Chiang Wei-Lin","year":"2023","unstructured":"Wei-Lin Chiang, Zhuohan Li, Zi Lin, Ying Sheng, Zhanghao Wu, Hao Zhang, Lianmin Zheng, Siyuan Zhuang, Yonghao Zhuang, Joseph E. Gonzalez, Ion Stoica, and Eric P. Xing. 2023. Vicuna: An Open-Source Chatbot Impressing GPT-4 with 90%* ChatGPT Quality. https:\/\/lmsys.org\/blog\/2023-03--30-vicuna\/"},{"key":"e_1_3_2_1_5_1","unstructured":"Aakanksha Chowdhery Sharan Narang Jacob Devlin Maarten Bosma Gaurav Mishra Adam Roberts Paul Barham et al. 2022. PaLM: Scaling Language Modeling with Pathways. arXiv preprint arXiv:2204.02311 (2022)."},{"key":"e_1_3_2_1_6_1","unstructured":"Hyung Won Chung Le Hou Shayne Longpre Barret Zoph Yi Tay William Fedus Eric Li Xuezhi Wang Mostafa Dehghani Siddhartha Brahma et al. 2022. Scaling instruction-finetuned language models. arXiv preprint arXiv:2210.11416 (2022)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/1076034.1076103"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2023.08.014"},{"key":"e_1_3_2_1_9_1","volume-title":"Accelerate: Training and inference at scale made simple, efficient and adaptable. https:\/\/github.com\/huggingface\/accelerate.","author":"Gugger Sylvain","year":"2022","unstructured":"Sylvain Gugger, Lysandre Debut, Thomas Wolf, Philipp Schmid, Zachary Mueller, Sourab Mangrulkar, Marc Sun, and Benjamin Bossan. 2022. Accelerate: Training and inference at scale made simple, efficient and adaptable. https:\/\/github.com\/huggingface\/accelerate."},{"key":"e_1_3_2_1_10_1","volume-title":"International conference on machine learning. PMLR, 3929--3938","author":"Guu Kelvin","year":"2020","unstructured":"Kelvin Guu, Kenton Lee, Zora Tung, Panupong Pasupat, and Mingwei Chang. 2020. Retrieval augmented language model pre-training. In International conference on machine learning. PMLR, 3929--3938."},{"key":"e_1_3_2_1_11_1","volume-title":"Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685","author":"Hu Edward J","year":"2021","unstructured":"Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2021. Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)."},{"key":"e_1_3_2_1_12_1","unstructured":"Wenlong Huang Fei Xia Ted Xiao Harris Chan Jacky Liang Pete Florence Andy Zeng Jonathan Tompson Igor Mordatch Yevgen Chebotar et al. 2022. Inner monologue: Embodied reasoning through planning with language models. arXiv preprint arXiv:2207.05608 (2022)."},{"key":"e_1_3_2_1_13_1","volume-title":"Few-shot learning with retrieval augmented language models. arXiv preprint arXiv:2208.03299","author":"Izacard Gautier","year":"2022","unstructured":"Gautier Izacard, Patrick Lewis, Maria Lomeli, Lucas Hosseini, Fabio Petroni, Timo Schick, Jane Dwivedi-Yu, Armand Joulin, Sebastian Riedel, and Edouard Grave. 2022. Few-shot learning with retrieval augmented language models. arXiv preprint arXiv:2208.03299 (2022)."},{"key":"e_1_3_2_1_14_1","volume-title":"International Conference on Machine Learning. PMLR, 1645--1654","author":"Jaques Natasha","year":"2017","unstructured":"Natasha Jaques, Shixiang Gu, Dzmitry Bahdanau, Jos\u00e9 Miguel Hern\u00e1ndez-Lobato, Richard E Turner, and Douglas Eck. 2017. Sequence tutor: Conservative fine-tuning of sequence generation models with kl-control. In International Conference on Machine Learning. PMLR, 1645--1654."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2019.2921572"},{"key":"e_1_3_2_1_16_1","volume-title":"Sewon Min, Patrick Lewis, Ledell Wu, Sergey Edunov, Danqi Chen, and Wen-tau Yih.","author":"Karpukhin Vladimir","year":"2020","unstructured":"Vladimir Karpukhin, Barlas Oug uz, Sewon Min, Patrick Lewis, Ledell Wu, Sergey Edunov, Danqi Chen, and Wen-tau Yih. 2020. Dense passage retrieval for open-domain question answering. arXiv preprint arXiv:2004.04906 (2020)."},{"key":"e_1_3_2_1_17_1","volume-title":"Bridging the Preference Gap between Retrievers and LLMs. arXiv preprint arXiv:2401.06954","author":"Ke Zixuan","year":"2024","unstructured":"Zixuan Ke, Weize Kong, Cheng Li, Mingyang Zhang, Qiaozhu Mei, and Michael Bendersky. 2024. Bridging the Preference Gap between Retrievers and LLMs. arXiv preprint arXiv:2401.06954 (2024)."},{"key":"e_1_3_2_1_18_1","volume-title":"Internet-augmented dialogue generation. arXiv preprint arXiv:2107.07566","author":"Komeili Mojtaba","year":"2021","unstructured":"Mojtaba Komeili, Kurt Shuster, and Jason Weston. 2021. Internet-augmented dialogue generation. arXiv preprint arXiv:2107.07566 (2021)."},{"key":"e_1_3_2_1_19_1","volume-title":"Internet-augmented language models through few-shot prompting for open-domain question answering. arXiv preprint arXiv:2203.05115","author":"Lazaridou Angeliki","year":"2022","unstructured":"Angeliki Lazaridou, Elena Gribovskaya, Wojciech Stokowiec, and Nikolai Grigorev. 2022. Internet-augmented language models through few-shot prompting for open-domain question answering. arXiv preprint arXiv:2203.05115 (2022)."},{"key":"e_1_3_2_1_20_1","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\"aschel, et al. 2020. Retrieval-augmented generation for knowledge-intensive nlp tasks. Advances in Neural Information Processing Systems , Vol. 33 (2020), 9459--9474.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_21_1","volume-title":"Let's Verify Step by Step. arXiv preprint arXiv:2305.20050","author":"Lightman Hunter","year":"2023","unstructured":"Hunter Lightman, Vineet Kosaraju, Yura Burda, Harri Edwards, Bowen Baker, Teddy Lee, Jan Leike, John Schulman, Ilya Sutskever, and Karl Cobbe. 2023. Let's Verify Step by Step. arXiv preprint arXiv:2305.20050 (2023)."},{"key":"e_1_3_2_1_22_1","volume-title":"Ra-dit: Retrieval-augmented dual instruction tuning. arXiv preprint arXiv:2310.01352","author":"Lin Xi Victoria","year":"2023","unstructured":"Xi Victoria Lin, Xilun Chen, Mingda Chen, Weijia Shi, Maria Lomeli, Rich James, Pedro Rodriguez, Jacob Kahn, Gergely Szilvasy, Mike Lewis, et al. 2023. Ra-dit: Retrieval-augmented dual instruction tuning. arXiv preprint arXiv:2310.01352 (2023)."},{"key":"e_1_3_2_1_23_1","volume-title":"Llava-plus: Learning to use tools for creating multimodal agents. arXiv preprint arXiv:2311.05437","author":"Liu Shilong","year":"2023","unstructured":"Shilong Liu, Hao Cheng, Haotian Liu, Hao Zhang, Feng Li, Tianhe Ren, Xueyan Zou, Jianwei Yang, Hang Su, Jun Zhu, et al. 2023. Llava-plus: Learning to use tools for creating multimodal agents. arXiv preprint arXiv:2311.05437 (2023)."},{"key":"e_1_3_2_1_24_1","volume-title":"Song-Chun Zhu, and Jianfeng Gao.","author":"Lu Pan","year":"2023","unstructured":"Pan Lu, Baolin Peng, Hao Cheng, Michel Galley, Kai-Wei Chang, Ying Nian Wu, Song-Chun Zhu, and Jianfeng Gao. 2023. Chameleon: Plug-and-play compositional reasoning with large language models. arXiv preprint arXiv:2304.09842 (2023)."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.89"},{"key":"e_1_3_2_1_26_1","volume-title":"PEFT: State-of-the-art Parameter-Efficient Fine-Tuning methods. https:\/\/github.com\/huggingface\/peft.","author":"Mangrulkar Sourab","year":"2022","unstructured":"Sourab Mangrulkar, Sylvain Gugger, Lysandre Debut, Younes Belkada, Sayak Paul, and Benjamin Bossan. 2022. PEFT: State-of-the-art Parameter-Efficient Fine-Tuning methods. https:\/\/github.com\/huggingface\/peft."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/bf02295996"},{"key":"e_1_3_2_1_28_1","volume-title":"Christoforos Nalmpantis, Ram Pasunuru, Roberta Raileanu, Baptiste Rozi\u00e8re, Timo Schick, Jane Dwivedi-Yu, Asli Celikyilmaz, et al.","author":"Mialon Gr\u00e9goire","year":"2023","unstructured":"Gr\u00e9goire Mialon, Roberto Dess`i, Maria Lomeli, Christoforos Nalmpantis, Ram Pasunuru, Roberta Raileanu, Baptiste Rozi\u00e8re, Timo Schick, Jane Dwivedi-Yu, Asli Celikyilmaz, et al. 2023. Augmented language models: a survey. arXiv preprint arXiv:2302.07842 (2023)."},{"key":"e_1_3_2_1_29_1","volume-title":"Webgpt: Browser-assisted question-answering with human feedback. arXiv preprint arXiv:2112.09332","author":"Nakano Reiichiro","year":"2021","unstructured":"Reiichiro Nakano, Jacob Hilton, Suchir Balaji, Jeff Wu, Long Ouyang, Christina Kim, Christopher Hesse, Shantanu Jain, Vineet Kosaraju, William Saunders, et al. 2021. Webgpt: Browser-assisted question-answering with human feedback. arXiv preprint arXiv:2112.09332 (2021)."},{"key":"e_1_3_2_1_30_1","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume":"35","author":"Ouyang Long","year":"2022","unstructured":"Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, et al. 2022. Training language models to follow instructions with human feedback. Advances in Neural Information Processing Systems , Vol. 35 (2022), 27730--27744.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_31_1","volume-title":"2023 a. RankVicuna: Zero-Shot Listwise Document Reranking with Open-Source Large Language Models. arXiv preprint arXiv:2309.15088","author":"Pradeep Ronak","year":"2023","unstructured":"Ronak Pradeep, Sahel Sharifymoghaddam, and Jimmy Lin. 2023 a. RankVicuna: Zero-Shot Listwise Document Reranking with Open-Source Large Language Models. arXiv preprint arXiv:2309.15088 (2023)."},{"key":"e_1_3_2_1_32_1","volume-title":"2023 b. RankZephyr: Effective and Robust Zero-Shot Listwise Reranking is a Breeze! arXiv:2312.02724","author":"Pradeep Ronak","year":"2023","unstructured":"Ronak Pradeep, Sahel Sharifymoghaddam, and Jimmy Lin. 2023 b. RankZephyr: Effective and Robust Zero-Shot Listwise Reranking is a Breeze! arXiv:2312.02724 (2023)."},{"key":"e_1_3_2_1_33_1","volume-title":"In-context retrieval-augmented language models. arXiv preprint arXiv:2302.00083","author":"Ram Ori","year":"2023","unstructured":"Ori Ram, Yoav Levine, Itay Dalmedigos, Dor Muhlgay, Amnon Shashua, Kevin Leyton-Brown, and Yoav Shoham. 2023. In-context retrieval-augmented language models. arXiv preprint arXiv:2302.00083 (2023)."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"e_1_3_2_1_35_1","volume-title":"Maria Lomeli, Luke Zettlemoyer, Nicola Cancedda, and Thomas Scialom.","author":"Schick Timo","year":"2023","unstructured":"Timo Schick, Jane Dwivedi-Yu, Roberto Dess`i, Roberta Raileanu, Maria Lomeli, Luke Zettlemoyer, Nicola Cancedda, and Thomas Scialom. 2023. Toolformer: Language models can teach themselves to use tools. arXiv preprint arXiv:2302.04761 (2023)."},{"key":"e_1_3_2_1_36_1","volume-title":"Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347","author":"Schulman John","year":"2017","unstructured":"John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, and Oleg Klimov. 2017. Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.25080\/Majora-92bf1922-011"},{"key":"e_1_3_2_1_38_1","unstructured":"ShareGPT. 2023. https:\/\/sharegpt.com\/."},{"key":"e_1_3_2_1_39_1","volume-title":"Hugginggpt: Solving ai tasks with chatgpt and its friends in huggingface. arXiv preprint arXiv:2303.17580","author":"Shen Yongliang","year":"2023","unstructured":"Yongliang Shen, Kaitao Song, Xu Tan, Dongsheng Li, Weiming Lu, and Yueting Zhuang. 2023. Hugginggpt: Solving ai tasks with chatgpt and its friends in huggingface. arXiv preprint arXiv:2303.17580 (2023)."},{"key":"e_1_3_2_1_40_1","volume-title":"Retrieval augmentation reduces hallucination in conversation. arXiv preprint arXiv:2104.07567","author":"Shuster Kurt","year":"2021","unstructured":"Kurt Shuster, Spencer Poff, Moya Chen, Douwe Kiela, and Jason Weston. 2021. Retrieval augmentation reduces hallucination in conversation. arXiv preprint arXiv:2104.07567 (2021)."},{"key":"e_1_3_2_1_41_1","first-page":"3008","article-title":"Learning to summarize with human feedback","volume":"33","author":"Stiennon Nisan","year":"2020","unstructured":"Nisan Stiennon, Long Ouyang, Jeffrey Wu, Daniel Ziegler, Ryan Lowe, Chelsea Voss, Alec Radford, Dario Amodei, and Paul F Christiano. 2020. Learning to summarize with human feedback. Advances in Neural Information Processing Systems , Vol. 33 (2020), 3008--3021.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_42_1","volume-title":"Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agent. arXiv preprint arXiv:2304.09542","author":"Sun Weiwei","year":"2023","unstructured":"Weiwei Sun, Lingyong Yan, Xinyu Ma, Pengjie Ren, Dawei Yin, and Zhaochun Ren. 2023. Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agent. arXiv preprint arXiv:2304.09542 (2023)."},{"key":"e_1_3_2_1_43_1","volume-title":"Hashimoto","author":"Taori Rohan","year":"2023","unstructured":"Rohan Taori, Ishaan Gulrajani, Tianyi Zhang, Yann Dubois, Xuechen Li, Carlos Guestrin, Percy Liang, and Tatsunori B. Hashimoto. 2023. Stanford Alpaca: An Instruction-following LLaMA model. https:\/\/github.com\/tatsu-lab\/stanford_alpaca."},{"key":"e_1_3_2_1_44_1","volume-title":"Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971","author":"Touvron Hugo","year":"2023","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 al. 2023. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)."},{"key":"e_1_3_2_1_45_1","volume-title":"Solving math word problems with process-and outcome-based feedback. arXiv preprint arXiv:2211.14275","author":"Uesato Jonathan","year":"2022","unstructured":"Jonathan Uesato, Nate Kushman, Ramana Kumar, Francis Song, Noah Siegel, Lisa Wang, Antonia Creswell, Geoffrey Irving, and Irina Higgins. 2022. Solving math word problems with process-and outcome-based feedback. arXiv preprint arXiv:2211.14275 (2022)."},{"key":"e_1_3_2_1_46_1","volume-title":"TRL: Transformer Reinforcement Learning. https:\/\/github.com\/lvwerra\/trl.","author":"von Werra Leandro","year":"2020","unstructured":"Leandro von Werra, Younes Belkada, Lewis Tunstall, Edward Beeching, Tristan Thrush, and Nathan Lambert. 2020. TRL: Transformer Reinforcement Learning. https:\/\/github.com\/lvwerra\/trl."},{"key":"e_1_3_2_1_47_1","volume-title":"Thinking and speech. The collected works of LS Vygotsky","author":"Vygotsky Lev S","year":"1987","unstructured":"Lev S Vygotsky. 1987. Thinking and speech. The collected works of LS Vygotsky , Vol. 1 (1987), 39--285."},{"key":"e_1_3_2_1_48_1","volume-title":"Adapting LLM Agents Through Communication. arXiv preprint arXiv:2310.01444","author":"Wang Kuan","year":"2023","unstructured":"Kuan Wang, Yadong Lu, Michael Santacroce, Yeyun Gong, Chao Zhang, and Yelong Shen. 2023. Adapting LLM Agents Through Communication. arXiv preprint arXiv:2310.01444 (2023)."},{"key":"e_1_3_2_1_49_1","unstructured":"Jason Wei Yi Tay Rishi Bommasani Colin Raffel Barret Zoph Sebastian Borgeaud Dani Yogatama Maarten Bosma Denny Zhou Donald Metzler et al. 2022. Emergent abilities of large language models. arXiv preprint arXiv:2206.07682 (2022)."},{"key":"e_1_3_2_1_50_1","volume-title":"Neural text generation with unlikelihood training. arXiv preprint arXiv:1908.04319","author":"Welleck Sean","year":"2019","unstructured":"Sean Welleck, Ilia Kulikov, Stephen Roller, Emily Dinan, Kyunghyun Cho, and Jason Weston. 2019. Neural text generation with unlikelihood training. arXiv preprint arXiv:1908.04319 (2019)."},{"key":"e_1_3_2_1_51_1","volume-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations. Association for Computational Linguistics, Online, 38--45","author":"Wolf Thomas","year":"2020","unstructured":"Thomas Wolf, Lysandre Debut, Victor Sanh, Julien Chaumond, Clement Delangue, Anthony Moi, Pierric Cistac, Tim Rault, R\u00e9mi Louf, Morgan Funtowicz, Joe Davison, Sam Shleifer, Patrick von Platen, Clara Ma, Yacine Jernite, Julien Plu, Canwen Xu, Teven Le Scao, Sylvain Gugger, Mariama Drame, Quentin Lhoest, and Alexander M. Rush. 2020. Transformers: State-of-the-Art Natural Language Processing. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations. Association for Computational Linguistics, Online, 38--45. https:\/\/www.aclweb.org\/anthology\/2020.emnlp-demos.6"},{"key":"e_1_3_2_1_52_1","volume-title":"2023 a. Tackling Vision Language Tasks Through Learning Inner Monologues. arXiv preprint arXiv:2308.09970","author":"Yang Diji","year":"2023","unstructured":"Diji Yang, Kezhen Chen, Jinmeng Rao, Xiaoyuan Guo, Yawen Zhang, Jie Yang, and Yi Zhang. 2023 a. Tackling Vision Language Tasks Through Learning Inner Monologues. arXiv preprint arXiv:2308.09970 (2023)."},{"key":"e_1_3_2_1_53_1","volume-title":"2023 b. GPT4Tools: Teaching Large Language Model to Use Tools via Self-instruction. arXiv preprint arXiv:2305.18752","author":"Yang Rui","year":"2023","unstructured":"Rui Yang, Lin Song, Yanwei Li, Sijie Zhao, Yixiao Ge, Xiu Li, and Ying Shan. 2023 b. GPT4Tools: Teaching Large Language Model to Use Tools via Self-instruction. arXiv preprint arXiv:2305.18752 (2023)."},{"key":"e_1_3_2_1_54_1","volume-title":"Explainable Multi-hop Question Answering. In Conference on Empirical Methods in Natural Language Processing (EMNLP).","author":"Yang Zhilin","unstructured":"Zhilin Yang, Peng Qi, Saizheng Zhang, Yoshua Bengio, William W. Cohen, Ruslan Salakhutdinov, and Christopher D. Manning. 2018. HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering. In Conference on Empirical Methods in Natural Language Processing (EMNLP)."},{"key":"e_1_3_2_1_55_1","volume-title":"React: Synergizing reasoning and acting in language models. arXiv preprint arXiv:2210.03629","author":"Yao Shunyu","year":"2022","unstructured":"Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik Narasimhan, and Yuan Cao. 2022. React: Synergizing reasoning and acting in language models. arXiv preprint arXiv:2210.03629 (2022)."},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/1835449.1835511"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462942"},{"key":"e_1_3_2_1_58_1","volume-title":"Why Does ChatGPT Fall Short in Answering Questions Faithfully? arXiv preprint arXiv:2304.10513","author":"Zheng Shen","year":"2023","unstructured":"Shen Zheng, Jie Huang, and Kevin Chen-Chuan Chang. 2023. Why Does ChatGPT Fall Short in Answering Questions Faithfully? arXiv preprint arXiv:2304.10513 (2023)."},{"key":"e_1_3_2_1_59_1","volume-title":"Think Before You Speak: Cultivating Communication Skills of Large Language Models via Inner Monologue. arXiv preprint arXiv:2311.07445","author":"Zhou Junkai","year":"2023","unstructured":"Junkai Zhou, Liang Pang, Huawei Shen, and Xueqi Cheng. 2023. Think Before You Speak: Cultivating Communication Skills of Large Language Models via Inner Monologue. arXiv preprint arXiv:2311.07445 (2023)."},{"key":"e_1_3_2_1_60_1","volume-title":"Adaptive information seeking for open-domain question answering. arXiv preprint arXiv:2109.06747","author":"Zhu Yunchang","year":"2021","unstructured":"Yunchang Zhu, Liang Pang, Yanyan Lan, Huawei Shen, and Xueqi Cheng. 2021. Adaptive information seeking for open-domain question answering. arXiv preprint arXiv:2109.06747 (2021)."},{"key":"e_1_3_2_1_61_1","volume-title":"Fine-tuning language models from human preferences. arXiv preprint arXiv:1909.08593","author":"Ziegler Daniel M","year":"2019","unstructured":"Daniel M Ziegler, Nisan Stiennon, Jeffrey Wu, Tom B Brown, Alec Radford, Dario Amodei, Paul Christiano, and Geoffrey Irving. 2019. Fine-tuning language models from human preferences. arXiv preprint arXiv:1909.08593 (2019)."}],"event":{"name":"SIGIR 2024: The 47th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Washington DC USA","acronym":"SIGIR 2024","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3626772.3657760","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3626772.3657760","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T05:34:06Z","timestamp":1755840846000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3626772.3657760"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,10]]},"references-count":61,"alternative-id":["10.1145\/3626772.3657760","10.1145\/3626772"],"URL":"https:\/\/doi.org\/10.1145\/3626772.3657760","relation":{},"subject":[],"published":{"date-parts":[[2024,7,10]]},"assertion":[{"value":"2024-07-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}