{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,24]],"date-time":"2026-10-24T11:26:53Z","timestamp":1792841213517,"version":"4.5.0"},"reference-count":72,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2023YFC2705705"],"award-info":[{"award-number":["2023YFC2705705"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62225113"],"award-info":[{"award-number":["62225113"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Innovative Research Group Project of Hubei Province","award":["2024AFA017"],"award-info":[{"award-number":["2024AFA017"]}]},{"name":"Science and Technology Major Project of Hubei Province","award":["2024BAB046"],"award-info":[{"award-number":["2024BAB046"]}]},{"name":"New Cornerstone Science Foundation"},{"name":"Interdisciplinary Innovative Talents Foundation from Renmin Hospital of Wuhan University","award":["JCRCZN-2022-018"],"award-info":[{"award-number":["JCRCZN-2022-018"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"crossref","award":["2042024YXA002"],"award-info":[{"award-number":["2042024YXA002"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"crossref"}]},{"name":"WHU-Kingsoft Joint Lab"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Knowl. Data Eng."],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1109\/tkde.2026.3720785","type":"journal-article","created":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T19:06:13Z","timestamp":1785956773000},"page":"6969-6986","source":"Crossref","is-referenced-by-count":1,"title":["Resolving Knowledge Conflicts in Domain-Specific Data Selection: A Case Study on Medical Instruction-Tuning"],"prefix":"10.1109","volume":"38","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-0118-5217","authenticated-orcid":false,"given":"Qihuang","family":"Zhong","sequence":"first","affiliation":[{"name":"Wuhan University","place":["Wuhan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8976-2084","authenticated-orcid":false,"given":"Liang","family":"Ding","sequence":"additional","affiliation":[{"name":"University of Sydney","place":["Sydney, NSW, Australia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6026-7976","authenticated-orcid":false,"given":"Fei","family":"Liao","sequence":"additional","affiliation":[{"name":"Wuhan University","place":["Wuhan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3907-8820","authenticated-orcid":false,"given":"Juhua","family":"Liu","sequence":"additional","affiliation":[{"name":"Wuhan University","place":["Wuhan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0059-8458","authenticated-orcid":false,"given":"Bo","family":"Du","sequence":"additional","affiliation":[{"name":"Wuhan University","place":["Wuhan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7225-5449","authenticated-orcid":false,"given":"Dacheng","family":"Tao","sequence":"additional","affiliation":[{"name":"Nanyang Technological University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","year":"2023"},{"key":"ref2","article-title":"The Llama 3 herd of models","author":"Dubey","year":"2024"},{"key":"ref3","article-title":"Qwen2. 5 technical report","author":"Yang","year":"2024"},{"key":"ref4","article-title":"Deepseek-v3 technical report","author":"Liu","year":"2024"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-026-60308-3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.348"},{"key":"ref7","article-title":"Finetuned language models are zero-shot learners","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wei","year":"2021"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2400"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.421"},{"key":"ref10","first-page":"22353","article-title":"What makes good data for alignment? a comprehensive study of automatic data selection in instruction tuning","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Liu","year":"2024"},{"key":"ref11","article-title":"AlpaGasus: Training a better alpaca with fewer data","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Chen","year":"2024"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.557"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.486"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.444"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3280"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.330"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2023.3310002"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3469578"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.373"},{"key":"ref20","first-page":"41092","article-title":"Prompting large language model for machine translation: A case study","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhang","year":"2023"},{"key":"ref21","article-title":"DeepSeekMath: Pushing the limits of mathematical reasoning in open language models","author":"Shao","year":"2024"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-025-41102-z"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3230975"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2023.3250499"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3392335"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2025.3540912"},{"key":"ref27","article-title":"MEDITRON-70B: Scaling medical pretraining for large language models","author":"Chen","year":"2023"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29907"},{"key":"ref29","article-title":"AlpaCare: Instruction-tuned large language models for medical application","author":"Zhang","year":"2023"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.7759\/cureus.40895"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3571730"},{"key":"ref32","first-page":"34767","article-title":"ALPAGASUS: Training a better alpaca with fewer data","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen","year":"2024"},{"key":"ref33","article-title":"Resolving knowledge conflicts in large language models","volume-title":"Proc. First Conf. Lang. Model.","author":"Wang","year":"2024"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.390"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.63317\/4fisde58hr4n"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.615"},{"key":"ref37","first-page":"19473","article-title":"3DS: Decomposed difficulty data selection\u2019s case study on LLM medical domain adaptation","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process.","author":"Ding","year":"2025"},{"key":"ref38","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Brown","year":"2020"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.759"},{"key":"ref40","article-title":"Empirical insights on fine-tuning large language models for question-answering","author":"Ye","year":"2024"},{"key":"ref41","article-title":"Self-consistency improves chain of thought reasoning in language models","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Wang","year":"2023"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-024-07421-0"},{"key":"ref43","article-title":"Semantic uncertainty: Linguistic invariances for uncertainty estimation in natural language generation","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Kuhn","year":"2023"},{"issue":"6","key":"ref44","article-title":"A survey on LLM-as-a-judge","volume":"7","author":"Gu","year":"2026","journal-title":"Innovation"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.137"},{"key":"ref46","article-title":"Stanford alpaca: An instruction-following LLAMA model","author":"Taori","year":"2023"},{"key":"ref47","article-title":"MedAlpaca\u2013an open-source collection of medical conversational ai models and training data","author":"Han","year":"2023"},{"key":"ref48","first-page":"248","article-title":"MedMCQA: A large-scale multi-subject multi-choice dataset for medical domain question answering","volume-title":"Proc. Conf. Health, Inference, Learn.","author":"Pal","year":"2022"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.3390\/app11146421"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1259"},{"key":"ref51","article-title":"Measuring massive multitask language understanding","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hendrycks","year":"2020"},{"key":"ref52","article-title":"A benchmark for long-form medical question answering","volume-title":"Proc. Adv. Med. Found. Models: Explainability, Robustness, Secur., Beyond","author":"Hosseini","year":"2024"},{"key":"ref53","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","volume-title":"Proc. Text Summarization Branches Out","author":"Lin","year":"2004"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06291-2"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-024-03423-7"},{"key":"ref56","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hu","year":"2021"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1177\/001316446002000104"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2288-13-61"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.conll-1.21"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-52417-z"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3615285"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0046"},{"key":"ref63","article-title":"DISC-LawLLM: Fine-tuning large language models for intelligent legal services","author":"Yue","year":"2023"},{"key":"ref64","article-title":"GPQA: A graduate-level google-proof q&a benchmark","volume-title":"Proc. First Conf. Lang. Model.","author":"Rein","year":"2024"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.671"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0790"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.452"},{"key":"ref68","article-title":"DeBERTaV3: Improving deberta using electra-style pre-training with gradient-disentangled embedding sharing","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"He","year":"2021"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1101"},{"key":"ref70","article-title":"LoRA learns less and forgets less","author":"Biderman","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671470"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1056\/aira2400380"}],"container-title":["IEEE Transactions on Knowledge and Data Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/69\/11673943\/11641842.pdf?arnumber=11641842","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,2]],"date-time":"2026-09-02T04:54:25Z","timestamp":1788324865000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11641842\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":72,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tkde.2026.3720785","relation":{},"ISSN":["1041-4347","1558-2191","2326-3865"],"issn-type":[{"value":"1041-4347","type":"print"},{"value":"1558-2191","type":"electronic"},{"value":"2326-3865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10]]}}}