{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,8]],"date-time":"2026-02-08T04:21:01Z","timestamp":1770524461325,"version":"3.49.0"},"reference-count":45,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,5,13]]},"DOI":"10.1109\/icde60146.2024.00390","type":"proceedings-article","created":{"date-parts":[[2024,7,23]],"date-time":"2024-07-23T17:38:03Z","timestamp":1721756283000},"page":"5184-5197","source":"Crossref","is-referenced-by-count":8,"title":["CoachLM: Automatic Instruction Revisions Improve the Data Quality in LLM Instruction Tuning"],"prefix":"10.1109","author":[{"given":"Yilun","family":"Liu","sequence":"first","affiliation":[{"name":"Huawei,China"}]},{"given":"Shimin","family":"Tao","sequence":"additional","affiliation":[{"name":"Huawei,China"}]},{"given":"Xiaofeng","family":"Zhao","sequence":"additional","affiliation":[{"name":"Huawei,China"}]},{"given":"Ming","family":"Zhu","sequence":"additional","affiliation":[{"name":"Huawei,China"}]},{"given":"Wenbing","family":"Ma","sequence":"additional","affiliation":[{"name":"Huawei,China"}]},{"given":"Junhao","family":"Zhu","sequence":"additional","affiliation":[{"name":"Huawei,China"}]},{"given":"Chang","family":"Su","sequence":"additional","affiliation":[{"name":"Huawei,China"}]},{"given":"Yutai","family":"Hou","sequence":"additional","affiliation":[{"name":"Huawei,China"}]},{"given":"Miao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Huawei,China"}]},{"given":"Min","family":"Zhang","sequence":"additional","affiliation":[{"name":"Huawei,China"}]},{"given":"Hongxia","family":"Ma","sequence":"additional","affiliation":[{"name":"Huawei,China"}]},{"given":"Li","family":"Zhang","sequence":"additional","affiliation":[{"name":"Huawei,China"}]},{"given":"Hao","family":"Yang","sequence":"additional","affiliation":[{"name":"Huawei,China"}]},{"given":"Yanfei","family":"Jiang","sequence":"additional","affiliation":[{"name":"Huawei,China"}]}],"member":"263","reference":[{"key":"ref1","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume":"35","author":"Ouyang","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref2","volume-title":"Gpt-4 technical report","year":"2023"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.nlp.2023.100048"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pdig.0000198"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3615111"},{"key":"ref6","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref7","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"issue":"1","key":"ref8","first-page":"5485","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"The Journal of Machine Learning Research"},{"key":"ref9","article-title":"Finetuned language models are zero-shot learners","volume-title":"International Conference on Learning Representations","author":"Wei","year":"2021"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.244"},{"key":"ref11","article-title":"Deep reinforcement learning from human preferences","volume":"30","author":"Christiano","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.530"},{"key":"ref13","article-title":"Instruction tuning for large language models: A survey","author":"Zhang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref14","first-page":"13484","article-title":"Self-instruct: Aligning language models with self-generated instructions","volume-title":"Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Wang"},{"key":"ref15","volume-title":"Stanford alpaca: An instruction-following llama model","author":"Taori","year":"2023"},{"key":"ref16","volume-title":"Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality","author":"Chiang","year":"2023"},{"key":"ref17","article-title":"Koala: A dialogue model for academic research","volume-title":"Blog post","author":"Geng","year":"2023"},{"key":"ref18","article-title":"Lima: Less is more for alignment","volume":"36","author":"Zhou","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref19","article-title":"From quantity to quality: Boosting llm performance with self-guided data selection for instruction tuning","author":"Li","year":"2023","journal-title":"arXiv preprint"},{"key":"ref20","article-title":"Alpagasus: Training a better alpaca model with fewer data","volume-title":"International Conference on Learning Representations","author":"Chen","year":"2024"},{"key":"ref21","article-title":"Instruction mining: High-quality instruction data selection for large language models","author":"Cao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref22","article-title":"WizardLM: Empowering large pre-trained language models to follow complex instructions","volume-title":"International Conference on Learning Representations","author":"Xu","year":"2024"},{"key":"ref23","article-title":"Can foundation models label data like humans?","volume-title":"Hugging Face Blog","author":"Rajani","year":"2023"},{"key":"ref24","article-title":"PandaLM: An automatic evaluation benchmark for LLM instruction tuning optimization","volume-title":"International Conference on Learning Representations","author":"Wang","year":"2024"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3571730"},{"key":"ref26","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume":"35","author":"Wei","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref27","first-page":"2507","article-title":"Learn to explain: Multimodal reasoning via thought chains for science question answering","volume":"35","author":"Lu","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1155\/2021\/9368128"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.3390\/fi14020037"},{"key":"ref30","article-title":"Instructiongpt-4: A 200-instruction paradigm for fine-tuning minigpt-4","author":"Wei","year":"2023","journal-title":"arXiv preprint"},{"key":"ref31","first-page":"707","article-title":"Binary codes capable of correcting deletions, insertions, and reversals","volume-title":"Soviet physics doklady","volume":"10","author":"Levenshtein","year":"1966"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.26"},{"key":"ref33","article-title":"Lora: Low-rank adaptation of large language models","volume-title":"International Conference on Learning Representations","author":"Hu","year":"2021"},{"key":"ref34","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref35","volume-title":"Free dolly: Introducing the worlds first truly open instruction-tuned llm","author":"Conover","year":"2023"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/2882903.2912574"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20074-8_21"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-3091-3_90"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE48619.2023.00149"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3544216.3544244"},{"key":"ref41","volume-title":"Github copilot - your ai pair programmer","year":"2023"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3520312.3534862"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1126\/science.abq1158"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3558489.3559072"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-industry.59"}],"event":{"name":"2024 IEEE 40th International Conference on Data Engineering (ICDE)","location":"Utrecht, Netherlands","start":{"date-parts":[[2024,5,13]]},"end":{"date-parts":[[2024,5,16]]}},"container-title":["2024 IEEE 40th International Conference on Data Engineering (ICDE)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10597630\/10597390\/10597991.pdf?arnumber=10597991","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,24]],"date-time":"2024-07-24T07:32:10Z","timestamp":1721806330000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10597991\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/icde60146.2024.00390","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]}}}