{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T11:32:20Z","timestamp":1766057540710,"version":"3.48.0"},"reference-count":42,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,11,3]],"date-time":"2025-11-03T00:00:00Z","timestamp":1762128000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,11,3]],"date-time":"2025-11-03T00:00:00Z","timestamp":1762128000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100007219","name":"Natural Science Foundation of Shanghai","doi-asserted-by":"publisher","award":["25ZR1402137"],"award-info":[{"award-number":["25ZR1402137"]}],"id":[{"id":"10.13039\/100007219","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,11,3]]},"DOI":"10.1109\/ictai66417.2025.00112","type":"proceedings-article","created":{"date-parts":[[2025,12,15]],"date-time":"2025-12-15T18:35:43Z","timestamp":1765823743000},"page":"778-785","source":"Crossref","is-referenced-by-count":0,"title":["Training Generative Judge with Hard Negative Mining: A Metric Learning Perspective"],"prefix":"10.1109","author":[{"given":"Changxin","family":"Chen","sequence":"first","affiliation":[{"name":"Shanghai University of Finance and Economics,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Holistic evaluation of language models","author":"Liang","year":"2022","journal-title":"arXiv preprint"},{"volume-title":"Alpacaeval: An automatic evaluator of instruction-following models","year":"2023","author":"Li","key":"ref2"},{"key":"ref3","first-page":"46595","article-title":"Judging llm-as-a-judge with mt-bench and chatbot arena","volume":"36","author":"Zheng","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref4","article-title":"On the limitations of fine-tuned judge models for llm evaluation","author":"Huang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref5","article-title":"Judgelm: Fine-tuned large language models are scalable judges","author":"Zhu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref6","article-title":"Pandalm: An automatic evaluation benchmark for 11 m instruction tuning optimization","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref7","article-title":"Prometheus: Inducing fine-grained evaluation capability in language models","volume-title":"The Twelfth International Conference on Learning Representations","author":"Kim","year":"2023"},{"key":"ref8","article-title":"Deepseekmath: Pushing the limits of mathematical reasoning in open language models","author":"Shao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref9","article-title":"Deepseek-r1: Incentivizing reasoning capability in via reinforcement learning","author":"Guo","year":"2025","journal-title":"arXiv preprint"},{"key":"ref10","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":"ref11","first-page":"55 006","article-title":"Lima: Less is more for alignment","volume":"36","author":"Zhou","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.283"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00643"},{"key":"ref15","article-title":"Contrastive learning with hard negative samples","author":"Robinson","year":"2020","journal-title":"arXiv preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00742"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.362"},{"key":"ref18","first-page":"1589","article-title":"Trainable hard negative examples in contrastive learning for unsupervised abstractive summarization","author":"Zhuang","year":"2024","journal-title":"Findings of the Association for Computational Linguistics: EACL 2024"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00113"},{"key":"ref20","article-title":"The false promise of imitating proprietary llms","author":"Gudibande","year":"2023","journal-title":"arXiv preprint"},{"key":"ref21","article-title":"Reinforcement learning enhanced : A survey","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref22","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv preprint"},{"key":"ref23","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref24","article-title":"Direct preference optimization: Your language model is secretly a reward model","volume":"36","author":"Rafailov","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29865"},{"key":"ref26","article-title":"The llama 3 herd of models","author":"Grattafiori","year":"2024","journal-title":"arXiv preprint"},{"key":"ref27","article-title":"Qwen2. 5 technical report","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref28","article-title":"Alpacafarm: A simulation framework for methods that learn from human feedback","volume":"36","author":"Dubois","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1162\/coli_a_00561"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.549"},{"key":"ref31","article-title":"Mods: Model-oriented data selection for instruction tuning","author":"Du","year":"2023","journal-title":"arXiv preprint"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.421"},{"key":"ref33","article-title":"Less: Selecting influential data for targeted instruction tuning","author":"Xia","year":"2024","journal-title":"arXiv preprint"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.180"},{"key":"ref35","article-title":"Generative judge for evaluating alignment","author":"Li","year":"2023","journal-title":"arXiv preprint"},{"volume-title":"Ultrafeedback: Boosting language models with high-quality feedback","year":"2023","author":"Cui","key":"ref36"},{"key":"ref37","article-title":"Skywork-reward: Bag of tricks for reward modeling in llms","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.511"},{"volume-title":"Trl: Transformer reinforcement learning","year":"2020","author":"von Werra","key":"ref39"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00024"},{"key":"ref41","article-title":"Training deep nets with sublinear memory cost, 2016","author":"Chen","year":"2016","journal-title":"arXiv preprint"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"}],"event":{"name":"2025 IEEE 37th International Conference on Tools with Artificial Intelligence (ICTAI)","start":{"date-parts":[[2025,11,3]]},"location":"Athens, Greece","end":{"date-parts":[[2025,11,5]]}},"container-title":["2025 IEEE 37th International Conference on Tools with Artificial Intelligence (ICTAI)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11272175\/11272453\/11272767.pdf?arnumber=11272767","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T11:28:29Z","timestamp":1766057309000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11272767\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,3]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/ictai66417.2025.00112","relation":{},"subject":[],"published":{"date-parts":[[2025,11,3]]}}}