{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,10]],"date-time":"2026-05-10T00:25:12Z","timestamp":1778372712091,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":30,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,21]],"date-time":"2024-10-21T00:00:00Z","timestamp":1729468800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"the National Key R\\&D Program of China","award":["2023YFB3307500"],"award-info":[{"award-number":["2023YFB3307500"]}]},{"name":"the Special Funding Program of Shandong Taishan Scholars Project"},{"name":"the China Scholarship Council"},{"name":"Harbin Institute of Technology Graduate Teaching Reform Project","award":["23Z-DZ039"],"award-info":[{"award-number":["23Z-DZ039"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,21]]},"DOI":"10.1145\/3627673.3679233","type":"proceedings-article","created":{"date-parts":[[2024,10,20]],"date-time":"2024-10-20T19:34:21Z","timestamp":1729452861000},"page":"5309-5313","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["GongBu: Easily Fine-tuning LLMs for Domain-specific Adaptation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6315-1856","authenticated-orcid":false,"given":"Bolin","family":"Zhang","sequence":"first","affiliation":[{"name":"Harbin Institute of Technology & Nanyang Technological University, Harbin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-8645-5981","authenticated-orcid":false,"given":"Yimin","family":"Tian","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Weihai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-6832-6152","authenticated-orcid":false,"given":"Shengwei","family":"Wang","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Weihai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8800-4513","authenticated-orcid":false,"given":"Zhiying","family":"Tu","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Weihai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2973-7252","authenticated-orcid":false,"given":"Dianhui","family":"Chu","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Weihai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7626-7295","authenticated-orcid":false,"given":"Zhiqi","family":"Shen","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10,21]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"XTuner Contributors. 2023. Xtuner: a toolkit for efficiently fine-tuning llm. https:\/\/github.com\/InternLM\/xtuner. (2023)."},{"key":"e_1_3_2_1_2_1","volume-title":"The Twelfth International Conference on Learning Representations.","author":"Dao Tri","year":"2023","unstructured":"Tri Dao. 2023. Flashattention-2: faster attention with better parallelism and work partitioning. In The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-023-00626-4"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"crossref","unstructured":"Neel Guha et al. 2024. Legalbench: a collaboratively built benchmark for measuring legal reasoning in large language models. Advances in Neural Information Processing Systems 36.","DOI":"10.2139\/ssrn.4583531"},{"key":"e_1_3_2_1_5_1","volume-title":"International Conference on Learning Representations.","author":"Hyeon-Woo Nam","year":"2021","unstructured":"Nam Hyeon-Woo, Moon Ye-Bin, and Tae-Hyun Oh. 2021. Fedpara: low-rank hadamard product for communication-efficient federated learning. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_6_1","unstructured":"Albert Q Jiang et al. 2023. Mistral 7b. arXiv preprint arXiv:2310.06825."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.3390\/app11146421"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"e_1_3_2_1_11_1","article-title":"Holistic evaluation of language models","author":"Percy Liang","year":"2023","unstructured":"Percy Liang et al. 2023. Holistic evaluation of language models. Transactions on Machine Learning Research.","journal-title":"Transactions on Machine Learning Research."},{"key":"e_1_3_2_1_12_1","first-page":"1950","article-title":"Few-shot parameter-efficient finetuning is better and cheaper than in-context learning","volume":"35","author":"Liu Haokun","year":"2022","unstructured":"Haokun Liu, Derek Tam, Mohammed Muqeeth, Jay Mohta, Tenghao Huang, Mohit Bansal, and Colin A Raffel. 2022. Few-shot parameter-efficient finetuning is better and cheaper than in-context learning. Advances in Neural Information Processing Systems, 35, 1950--1965.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"crossref","unstructured":"Xiao Liu Yanan Zheng Zhengxiao Du Ming Ding Yujie Qian Zhilin Yang and Jie Tang. 2023. Gpt understands too. AI Open.","DOI":"10.1016\/j.aiopen.2023.08.012"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.5555\/2002472.2002491"},{"key":"e_1_3_2_1_15_1","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. (2022)."},{"key":"e_1_3_2_1_16_1","volume-title":"Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 15991--16111","author":"Niklas","unstructured":"Niklas Muennighoff et al. 2023. Crosslingual generalization through multitask finetuning. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 15991--16111."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00024"},{"key":"e_1_3_2_1_18_1","volume-title":"International Conference on Learning Representations.","author":"Sener Ozan","year":"2018","unstructured":"Ozan Sener and Silvio Savarese. 2018. Active learning for convolutional neural networks: a core-set approach. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_19_1","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. (2023)."},{"key":"e_1_3_2_1_20_1","unstructured":"Gemma Team et al. 2024. Gemma: open models based on gemini research and technology. arXiv preprint arXiv:2403.08295."},{"key":"e_1_3_2_1_21_1","unstructured":"Hugo Touvron et al. 2023. Llama 2: open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288."},{"key":"e_1_3_2_1_22_1","unstructured":"Jiahao Wang Bolin Zhang Qianlong Du Jiajun Zhang and Dianhui Chu. 2024. A survey on data selection for llm instruction tuning. arXiv preprint arXiv:2402.05123."},{"key":"e_1_3_2_1_23_1","volume-title":"NeurIPS 2023 Workshop on Instruction Tuning and Instruction Following.","author":"Wang Neng","year":"2023","unstructured":"Neng Wang, Hongyang Yang, and Christina Wang. 2023. Fingpt: instruction tuning benchmark for open-source large language models in financial datasets. In NeurIPS 2023 Workshop on Instruction Tuning and Instruction Following."},{"key":"e_1_3_2_1_24_1","volume-title":"M3E: Moka Massive Mixed Embedding Model","author":"Wang Yuxin Sun Qingxuan He","year":"2023","unstructured":"[SW] He sicheng Wang Yuxin Sun Qingxuan, M3E: Moka Massive Mixed Embedding Model 2023."},{"key":"e_1_3_2_1_25_1","volume-title":"The Twelfth International Conference on Learning Representations.","author":"Yu-Guan Hsieh SHIH-YING YEH","year":"2023","unstructured":"SHIH-YING YEH, Yu-Guan Hsieh, Zhidong Gao, Bernard BW Yang, Giyeong Oh, and Yanmin Gong. 2023. Navigating text-to-image customization: from lycoris fine-tuning to model evaluation. In The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_2_1_26_1","volume-title":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU). IEEE, 1--8.","author":"Yu","unstructured":"Yu Yu et al. 2023. Low-rank adaptation of large language model rescoring for parameter-efficient speech recognition. In 2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU). IEEE, 1--8."},{"key":"e_1_3_2_1_27_1","volume-title":"The Eleventh International Conference on Learning Representations.","author":"Zhang Qingru","year":"2023","unstructured":"Qingru Zhang, Minshuo Chen, Alexander Bukharin, Pengcheng He, Yu Cheng, Weizhu Chen, and Tuo Zhao. 2023. Adaptive budget allocation for parameterefficient fine-tuning. In The Eleventh International Conference on Learning Representations."},{"key":"e_1_3_2_1_28_1","unstructured":"Renrui Zhang et al. 2023. Llama-adapter: efficient fine-tuning of language models with zero-init attention. arXiv preprint arXiv:2303.16199."},{"key":"e_1_3_2_1_29_1","unstructured":"Xujiang Zhao et al. 2023. Domain specialization as the key to make large language models disruptive: a comprehensive survey. arXiv preprint arXiv:2305.18703."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"crossref","unstructured":"Yaowei Zheng Richong Zhang Junhao Zhang Yanhan Ye Zheyan Luo and Yongqiang Ma. 2024. Llamafactory: unified efficient fine-tuning of 100 language models. arXiv preprint arXiv:2403.13372. http:\/\/arxiv.org\/abs\/2403.13372.","DOI":"10.18653\/v1\/2024.acl-demos.38"}],"event":{"name":"CIKM '24: The 33rd ACM International Conference on Information and Knowledge Management","location":"Boise ID USA","acronym":"CIKM '24","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 33rd ACM International Conference on Information and Knowledge Management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3627673.3679233","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3627673.3679233","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:03:28Z","timestamp":1750291408000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3627673.3679233"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,21]]},"references-count":30,"alternative-id":["10.1145\/3627673.3679233","10.1145\/3627673"],"URL":"https:\/\/doi.org\/10.1145\/3627673.3679233","relation":{},"subject":[],"published":{"date-parts":[[2024,10,21]]},"assertion":[{"value":"2024-10-21","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}