{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T00:05:08Z","timestamp":1755907508875,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":42,"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:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Shanghai Municipal Natural Science Foundation","award":["23ZR1425400"],"award-info":[{"award-number":["23ZR1425400"]}]},{"DOI":"10.13039\/501100006374","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62102241"],"award-info":[{"award-number":["62102241"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,7,10]]},"DOI":"10.1145\/3626772.3657920","type":"proceedings-article","created":{"date-parts":[[2024,7,11]],"date-time":"2024-07-11T12:40:05Z","timestamp":1720701605000},"page":"2384-2389","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Enhancing Task Performance in Continual Instruction Fine-tuning Through Format Uniformity"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3555-7143","authenticated-orcid":false,"given":"Xiaoyu","family":"Tan","sequence":"first","affiliation":[{"name":"INF Technology (Shanghai) Co., Ltd., Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-6625-1961","authenticated-orcid":false,"given":"Leijun","family":"Cheng","sequence":"additional","affiliation":[{"name":"School of Electronic and Electrical Engineering, Shanghai University of Engineering Science, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4024-925X","authenticated-orcid":false,"given":"Xihe","family":"Qiu","sequence":"additional","affiliation":[{"name":"School of Electronic and Electrical Engineering, Shanghai University of Engineering Science, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-5781-0941","authenticated-orcid":false,"given":"Shaojie","family":"Shi","sequence":"additional","affiliation":[{"name":"School of Electronic and Electrical Engineering, Shanghai University of Engineering Science, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2502-9101","authenticated-orcid":false,"given":"Yuan","family":"Cheng","sequence":"additional","affiliation":[{"name":"AI3 Institute, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6401-6111","authenticated-orcid":false,"given":"Wei","family":"Chu","sequence":"additional","affiliation":[{"name":"INF Technology (Shanghai) Co., Ltd., Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7346-2794","authenticated-orcid":false,"given":"Yinghui","family":"Xu","sequence":"additional","affiliation":[{"name":"AI3 Institute, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-9377-5755","authenticated-orcid":false,"given":"Yuan","family":"Qi","sequence":"additional","affiliation":[{"name":"AI3 Institute, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,7,11]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al.","author":"Achiam Josh","year":"2023","unstructured":"Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al. 2023. Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)."},{"key":"e_1_3_2_1_2_1","volume-title":"Matti Lassas, Luca Ratti, and Matteo Santacesaria.","author":"Alberti Giovanni S","year":"2021","unstructured":"Giovanni S Alberti, Ernesto De Vito, Matti Lassas, Luca Ratti, and Matteo Santacesaria. 2021. Learning the optimal Tikhonov regularizer for inverse problems. In Advances in Neural Information Processing Systems, M. Ranzato, A. Beygelzimer, Y. Dauphin, P.S. Liang, and J.Wortman Vaughan (Eds.), Vol. 34. Curran Associates, Inc., 25205--25216. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2021\/file\/ d3e6cd9f66f2c1d3840ade4161cf7406-Paper.pdf"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"crossref","unstructured":"Teodoro Baldazzi Luigi Bellomarini Stefano Ceri Andrea Colombo Andrea Gentili and Emanuel Sallinger. 2023. Fine-Tuning Large Enterprise Language Models via Ontological Reasoning. In Rules and Reasoning Anna Fensel Ana Ozaki Dumitru Roman and Ahmet Soylu (Eds.). Springer Nature Switzerland Cham 86--94.","DOI":"10.1007\/978-3-031-45072-3_6"},{"key":"e_1_3_2_1_4_1","volume-title":"Training with noise is equivalent to Tikhonov regularization. Neural computation 7, 1","author":"Bishop Chris M","year":"1995","unstructured":"Chris M Bishop. 1995. Training with noise is equivalent to Tikhonov regularization. Neural computation 7, 1 (1995), 108--116."},{"key":"e_1_3_2_1_5_1","unstructured":"Tom Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared D Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell et al. 2020. Language models are few-shot learners. Advances in neural information processing systems 33 (2020) 1877--1901."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.570"},{"key":"e_1_3_2_1_7_1","volume-title":"Deep reinforcement learning from human preferences. Advances in neural information processing systems 30","author":"Christiano Paul F","year":"2017","unstructured":"Paul F Christiano, Jan Leike, Tom Brown, Miljan Martic, Shane Legg, and Dario Amodei. 2017. Deep reinforcement learning from human preferences. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_1_8_1","volume-title":"Free Dolly: Introducing the World's First Truly Open Instruction-Tuned LLM. https:\/\/www.databricks.com\/blog\/2023\/04\/12\/dolly-first-opencommercially-viable-instruction-tuned-llm","author":"Conover Mike","year":"2023","unstructured":"Mike Conover, Matt Hayes, Ankit Mathur, Jianwei Xie, Jun Wan, Sam Shah, Ali Ghodsi, Patrick Wendell, Matei Zaharia, and Reynold Xin. 2023. Free Dolly: Introducing the World's First Truly Open Instruction-Tuned LLM. https:\/\/www.databricks.com\/blog\/2023\/04\/12\/dolly-first-opencommercially-viable-instruction-tuned-llm"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.357"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.626"},{"key":"e_1_3_2_1_11_1","volume-title":"Yuhan Liu, and Yulia Tsvetkov.","author":"Feng Shangbin","year":"2023","unstructured":"Shangbin Feng, Chan Young Park, Yuhan Liu, and Yulia Tsvetkov. 2023. From Pretraining Data to Language Models to Downstream Tasks: Tracking the Trails of Political Biases Leading to Unfair NLP Models. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Anna Rogers, Jordan Boyd-Graber, and Naoaki Okazaki (Eds.). Association for Computational Linguistics, Toronto, Canada, 11737--11762. https:\/\/doi.org\/10. 18653\/v1\/2023.acl-long.656"},{"key":"e_1_3_2_1_12_1","volume-title":"Debertav3: Improving deberta using electra-style pre-training with gradient-disentangled embedding sharing. arXiv preprint arXiv:2111.09543","author":"He Pengcheng","year":"2021","unstructured":"Pengcheng He, Jianfeng Gao, and Weizhu Chen. 2021. Debertav3: Improving deberta using electra-style pre-training with gradient-disentangled embedding sharing. arXiv preprint arXiv:2111.09543 (2021)."},{"key":"e_1_3_2_1_13_1","unstructured":"Felix Hill Antoine Bordes Sumit Chopra and JasonWeston. 2016. The Goldilocks Principle: Reading Children's Books with Explicit Memory Representations. arXiv:1511.02301 [cs.CL]"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.61"},{"key":"e_1_3_2_1_15_1","volume-title":"Fine-tuning and Utilization Methods of Domain-specific LLMs. arXiv preprint arXiv:2401.02981","author":"Jeong Cheonsu","year":"2024","unstructured":"Cheonsu Jeong. 2024. Fine-tuning and Utilization Methods of Domain-specific LLMs. arXiv preprint arXiv:2401.02981 (2024)."},{"key":"e_1_3_2_1_16_1","volume-title":"Nataraj Jammalamadaka, Jianyu Huang, Hector Yuen, et al.","author":"Kalamkar Dhiraj","year":"2019","unstructured":"Dhiraj Kalamkar, Dheevatsa Mudigere, Naveen Mellempudi, Dipankar Das, Kunal Banerjee, Sasikanth Avancha, Dharma Teja Vooturi, Nataraj Jammalamadaka, Jianyu Huang, Hector Yuen, et al. 2019. A study of BFLOAT16 for deep learning training. arXiv preprint arXiv:1905.12322 (2019)."},{"key":"e_1_3_2_1_17_1","volume-title":"Proceedings of naacL-HLT","volume":"1","author":"Ming-Wei Chang Jacob Devlin","year":"2019","unstructured":"Jacob Devlin Ming-Wei Chang Kenton and Lee Kristina Toutanova. 2019. Bert: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of naacL-HLT, Vol. 1. 2."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611835114"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1082"},{"key":"e_1_3_2_1_20_1","unstructured":"Yong Lin Lu Tan Hangyu Lin Zeming Zheng Renjie Pi Jipeng Zhang Shizhe Diao Haoxiang Wang Han Zhao Yuan Yao et al. 2023. Speciality vs generality: An empirical study on catastrophic forgetting in fine-tuning foundation models. arXiv preprint arXiv:2309.06256 (2023)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3560815"},{"key":"e_1_3_2_1_22_1","first-page":"181","article-title":"Second thoughts are best: Learning to re-align with human values from text edits","volume":"35","author":"Liu Ruibo","year":"2022","unstructured":"Ruibo Liu, Chenyan Jia, Ge Zhang, Ziyu Zhuang, Tony Liu, and Soroush Vosoughi. 2022. Second thoughts are best: Learning to re-align with human values from text edits. Advances in Neural Information Processing Systems 35 (2022), 181--196.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_23_1","volume-title":"An empirical study of catastrophic forgetting in large language models during continual fine-tuning. arXiv preprint arXiv:2308.08747","author":"Luo Yun","year":"2023","unstructured":"Yun Luo, Zhen Yang, Fandong Meng, Yafu Li, Jie Zhou, and Yue Zhang. 2023. An empirical study of catastrophic forgetting in large language models during continual fine-tuning. arXiv preprint arXiv:2308.08747 (2023)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591992"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.bigpicture-1.10"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.94"},{"key":"e_1_3_2_1_27_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 35 (2022), 27730--27744.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-industry.45"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2024.3377590"},{"key":"e_1_3_2_1_30_1","article-title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","volume":"21","author":"Raffel Colin","year":"2019","unstructured":"Colin Raffel, Noam M. Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J. Liu. 2019. Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer. J. Mach. Learn. Res. 21 (2019), 140:1--140:67. https:\/\/api.semanticscholar.org\/CorpusID:204838007","journal-title":"J. Mach. Learn. Res."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3406703"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"volume-title":"Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing","author":"Richardson Matthew","key":"e_1_3_2_1_33_1","unstructured":"Matthew Richardson, Christopher J.C. Burges, and Erin Renshaw. 2013. MCTest: A Challenge Dataset for the Open-Domain Machine Comprehension of Text. In Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, David Yarowsky, Timothy Baldwin, Anna Korhonen, Karen Livescu, and Steven Bethard (Eds.). Association for Computational Linguistics, Seattle, Washington, USA, 193--203. https:\/\/aclanthology.org\/D13-1020"},{"key":"e_1_3_2_1_34_1","unstructured":"Yu Sun Shuohuan Wang Shikun Feng Siyu Ding Chao Pang Junyuan Shang Jiaxiang Liu Xuyi Chen Yanbin Zhao Yuxiang Lu et al. 2021. Ernie 3.0: Large-scale knowledge enhanced pre-training for language understanding and generation. arXiv preprint arXiv:2107.02137 (2021)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-industry.62"},{"key":"e_1_3_2_1_36_1","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale et al. 2023. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)."},{"key":"e_1_3_2_1_37_1","volume-title":"Mini-GPTs: Efficient Large Language Models through Contextual Pruning. arXiv preprint arXiv:2312.12682","author":"Valicenti Tim","year":"2023","unstructured":"Tim Valicenti, Justice Vidal, and Ritik Patnaik. 2023. Mini-GPTs: Efficient Large Language Models through Contextual Pruning. arXiv preprint arXiv:2312.12682 (2023)."},{"key":"e_1_3_2_1_38_1","volume-title":"Bowman","author":"Wang Alex","year":"2019","unstructured":"Alex Wang, Amanpreet Singh, Julian Michael, Felix Hill, Omer Levy, and Samuel R. Bowman. 2019. GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding. In the Proceedings of ICLR.."},{"key":"e_1_3_2_1_39_1","volume-title":"Armand Joulin, and Tomas Mikolov.","author":"Weston Jason","year":"2015","unstructured":"Jason Weston, Antoine Bordes, Sumit Chopra, Alexander M Rush, Bart Van Merri\u00ebnboer, Armand Joulin, and Tomas Mikolov. 2015. Towards ai-complete question answering: A set of prerequisite toy tasks. arXiv preprint arXiv:1502.05698 (2015)."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-industry.29"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.633"},{"key":"e_1_3_2_1_42_1","volume-title":"Lima: Less is more for alignment. arXiv preprint arXiv:2305.11206","author":"Zhou Chunting","year":"2023","unstructured":"Chunting Zhou, Pengfei Liu, Puxin Xu, Srini Iyer, Jiao Sun, Yuning Mao, Xuezhe Ma, Avia Efrat, Ping Yu, Lili Yu, et al. 2023. Lima: Less is more for alignment. arXiv preprint arXiv:2305.11206 (2023)."}],"event":{"name":"SIGIR 2024: The 47th International ACM SIGIR Conference on Research and Development in Information Retrieval","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"],"location":"Washington DC USA","acronym":"SIGIR 2024"},"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\/3626772.3657920","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3626772.3657920","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T05:23:15Z","timestamp":1755840195000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3626772.3657920"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,10]]},"references-count":42,"alternative-id":["10.1145\/3626772.3657920","10.1145\/3626772"],"URL":"https:\/\/doi.org\/10.1145\/3626772.3657920","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"}}]}}