{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T15:07:13Z","timestamp":1784300833766,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":25,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,7,5]],"date-time":"2026-07-05T00:00:00Z","timestamp":1783209600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,5]]},"DOI":"10.1145\/3803437.3805263","type":"proceedings-article","created":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T14:27:39Z","timestamp":1784298459000},"page":"926-931","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["AutoChecklist: Automated Checklist Refinement for LLM Judges"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-8102-5421","authenticated-orcid":false,"given":"Mansi","family":"Uniyal","sequence":"first","affiliation":[{"name":"Microsoft, Bengaluru, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9510-4512","authenticated-orcid":false,"given":"Mukul","family":"Singh","sequence":"additional","affiliation":[{"name":"Microsoft, Seattle, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9182-597X","authenticated-orcid":false,"given":"Gust","family":"Verbruggen","sequence":"additional","affiliation":[{"name":"Microsoft, Keerbergen, Belgium"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3727-3291","authenticated-orcid":false,"given":"Vu","family":"Le","sequence":"additional","affiliation":[{"name":"Microsoft, Seattle, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9226-9634","authenticated-orcid":false,"given":"Sumit","family":"Gulwani","sequence":"additional","affiliation":[{"name":"Microsoft, Seattle, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,17]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"11th Conference of the European","author":"Callison-Burch Chris","unstructured":"Chris Callison-Burch, Miles Osborne, and Philipp Koehn. 2006. Re-evaluating the Role of Bleu in Machine Translation Research. In 11th Conference of the European Chapter of the Association for Computational Linguistics, Diana McCarthy and Shuly Wintner (Eds.). Association for Computational Linguistics, Trento, Italy, 249\u2013256. https:\/\/aclanthology.org\/E06-1032"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.870"},{"key":"e_1_3_2_1_3_1","unstructured":"DeepSeek-AI Daya Guo Dejian Yang Haowei Zhang Junxiao Song Ruoyu Zhang Runxin Xu Qihao Zhu Shirong Ma Peiyi Wang Xiao Bi Xiaokang Zhang Xingkai Yu Yu Wu Z. F. Wu Zhibin Gou Zhihong Shao Zhuoshu Li Ziyi Gao Aixin Liu Bing Xue Bingxuan Wang Bochao Wu Bei Feng Chengda Lu Chenggang Zhao Chengqi Deng Chenyu Zhang Chong Ruan Damai Dai Deli Chen Dongjie Ji Erhang Li Fangyun Lin Fucong Dai Fuli Luo Guangbo Hao Guanting Chen Guowei Li H. Zhang Han Bao Hanwei Xu Haocheng Wang Honghui Ding Huajian Xin Huazuo Gao Hui Qu Hui Li Jianzhong Guo Jiashi Li Jiawei Wang Jingchang Chen Jingyang Yuan Junjie Qiu Junlong Li J. L. Cai Jiaqi Ni Jian Liang Jin Chen Kai Dong Kai Hu Kaige Gao Kang Guan Kexin Huang Kuai Yu Lean Wang Lecong Zhang Liang Zhao Litong Wang Liyue Zhang Lei Xu Leyi Xia Mingchuan Zhang Minghua Zhang Minghui Tang Meng Li Miaojun Wang Mingming Li Ning Tian Panpan Huang Peng Zhang Qiancheng Wang Qinyu Chen Qiushi Du Ruiqi Ge Ruisong Zhang Ruizhe Pan Runji Wang R. J. Chen R. L. Jin Ruyi Chen Shanghao Lu Shangyan Zhou Shanhuang Chen Shengfeng Ye Shiyu Wang Shuiping Yu Shunfeng Zhou Shuting Pan S. S. Li Shuang Zhou Shaoqing Wu Shengfeng Ye Tao Yun Tian Pei Tianyu Sun T. Wang Wangding Zeng Wanjia Zhao Wen Liu Wenfeng Liang Wenjun Gao Wenqin Yu Wentao Zhang W. L. Xiao Wei An Xiaodong Liu Xiaohan Wang Xiaokang Chen Xiaotao Nie Xin Cheng Xin Liu Xin Xie Xingchao Liu Xinyu Yang Xinyuan Li Xuecheng Su Xuheng Lin X. Q. Li Xiangyue Jin Xiaojin Shen Xiaosha Chen Xiaowen Sun Xiaoxiang Wang Xinnan Song Xinyi Zhou Xianzu Wang Xinxia Shan Y. K. Li Y. Q. Wang Y. X. Wei Yang Zhang Yanhong Xu Yao Li Yao Zhao Yaofeng Sun Yaohui Wang Yi Yu Yichao Zhang Yifan Shi Yiliang Xiong Ying He Yishi Piao Yisong Wang Yixuan Tan Yiyang Ma Yiyuan Liu Yongqiang Guo Yuan Ou Yuduan Wang Yue Gong Yuheng Zou Yujia He Yunfan Xiong Yuxiang Luo Yuxiang You Yuxuan Liu Yuyang Zhou Y. X. Zhu Yanhong Xu Yanping Huang Yaohui Li Yi Zheng Yuchen Zhu Yunxian Ma Ying Tang Yukun Zha Yuting Yan Z. Z. Ren Zehui Ren Zhangli Sha Zhe Fu Zhean Xu Zhenda Xie Zhengyan Zhang Zhewen Hao Zhicheng Ma Zhigang Yan Zhiyu Wu Zihui Gu Zijia Zhu Zijun Liu Zilin Li Ziwei Xie Ziyang Song Zizheng Pan Zhen Huang Zhipeng Xu Zhongyu Zhang and Zhen Zhang. 2025. DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning. arXiv:2501.12948 [cs.CL] https:\/\/arxiv.org\/abs\/2501.12948"},{"key":"e_1_3_2_1_4_1","volume-title":"Sshubam Verma, and Mitesh M Khapra.","author":"Doddapaneni Sumanth","year":"2024","unstructured":"Sumanth Doddapaneni, Mohammed Safi Ur Rahman Khan, Sshubam Verma, and Mitesh M Khapra. 2024. Finding blind spots in evaluator llms with interpretable checklists. arXiv preprint arXiv:2406.13439 (2024)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00373"},{"key":"e_1_3_2_1_6_1","volume-title":"Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 6556\u20136576","author":"Ng Kiong","year":"2024","unstructured":"Jinlan Fu, See Kiong Ng, Zhengbao Jiang, and Pengfei Liu. 2024. Gptscore: Evaluate as you desire. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 6556\u20136576."},{"key":"e_1_3_2_1_7_1","unstructured":"Mingqi Gao Xinyu Hu Jie Ruan Xiao Pu and Xiaojun Wan. 2024. LLM-based NLG Evaluation: Current Status and Challenges. arXiv:2402.01383 [cs.CL] https:\/\/arxiv.org\/abs\/2402.01383"},{"key":"e_1_3_2_1_8_1","volume-title":"Proceedings of the 7th Linguistic Annotation Workshop and Interoperability with Discourse. 33\u201341","author":"Graham Yvette","year":"2013","unstructured":"Yvette Graham, Timothy Baldwin, Alistair Moffat, and Justin Zobel. 2013. Continuous measurement scales in human evaluation of machine translation. In Proceedings of the 7th Linguistic Annotation Workshop and Interoperability with Discourse. 33\u201341."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510203"},{"key":"e_1_3_2_1_10_1","volume-title":"Jamin Shin, Sean Welleck, Graham Neubig, Moontae Lee, Kyungjae Lee, and Minjoon Seo.","author":"Kim Seungone","year":"2024","unstructured":"Seungone Kim, Juyoung Suk, Shayne Longpre, Bill Yuchen Lin, Jamin Shin, Sean Welleck, Graham Neubig, Moontae Lee, Kyungjae Lee, and Minjoon Seo. 2024. Prometheus 2: An open source language model specialized in evaluating other language models. arXiv preprint arXiv:2405.01535 (2024)."},{"key":"e_1_3_2_1_11_1","volume-title":"Findings of the 2022 conference on machine translation (WMT22). In Proceedings of the Seventh Conference on Machine Translation (WMT). 1\u201345","author":"Kocmi Tom","year":"2022","unstructured":"Tom Kocmi, Rachel Bawden, Ond\u0159ej Bojar, Anton Dvorkovich, Christian Federmann, Mark Fishel, Thamme Gowda, Yvette Graham, Roman Grundkiewicz, Barry Haddow, et al. 2022. Findings of the 2022 conference on machine translation (WMT22). In Proceedings of the Seventh Conference on Machine Translation (WMT). 1\u201345."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1549"},{"key":"e_1_3_2_1_13_1","volume-title":"CheckEval: Robust Evaluation Framework using Large Language Model via Checklist. arXiv preprint arXiv:2403.18771","author":"Lee Yukyung","year":"2024","unstructured":"Yukyung Lee, Joonghoon Kim, Jaehee Kim, Hyowon Cho, and Pilsung Kang. 2024. CheckEval: Robust Evaluation Framework using Large Language Model via Checklist. arXiv preprint arXiv:2403.18771 (2024)."},{"key":"e_1_3_2_1_14_1","volume-title":"ROUGE: A Package for Automatic Evaluation of Summaries. In Text Summarization Branches Out","author":"Lin Chin-Yew","year":"2004","unstructured":"Chin-Yew Lin. 2004. ROUGE: A Package for Automatic Evaluation of Summaries. In Text Summarization Branches Out. Association for Computational Linguistics, Barcelona, Spain, 74\u201381. https:\/\/aclanthology.org\/W04-1013"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.228"},{"key":"e_1_3_2_1_16_1","volume-title":"https:\/\/openai.com\/blog\/chatgpt last-accesed","author":"AI.","year":"2023","unstructured":"OpenAI. 2023. Chat-GPT. https:\/\/openai.com\/blog\/chatgpt last-accesed: Oct 2023."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"e_1_3_2_1_18_1","volume-title":"Benjamin Van Durme, and Elnaz Nouri","author":"Payan Justin","year":"2023","unstructured":"Justin Payan, Swaroop Mishra, Mukul Singh, Carina Negreanu, Christian Poelitz, Chitta Baral, Subhro Roy, Rasika Chakravarthy, Benjamin Van Durme, and Elnaz Nouri. 2023. InstructExcel: A Benchmark for Natural Language Instruction in Excel. In Findings of the Association for Computational Linguistics: EMNLP 2023. 4026\u20134043."},{"key":"e_1_3_2_1_19_1","volume-title":"Beyond accuracy: Behavioral testing of NLP models with CheckList. arXiv preprint arXiv:2005.04118","author":"Ribeiro Marco Tulio","year":"2020","unstructured":"Marco Tulio Ribeiro, Tongshuang Wu, Carlos Guestrin, and Sameer Singh. 2020. Beyond accuracy: Behavioral testing of NLP models with CheckList. arXiv preprint arXiv:2005.04118 (2020)."},{"key":"e_1_3_2_1_20_1","volume-title":"Yossi Adi, Jingyu Liu, Romain Sauvestre, Tal Remez, et al.","author":"Roziere Baptiste","year":"2023","unstructured":"Baptiste Roziere, Jonas Gehring, Fabian Gloeckle, Sten Sootla, Itai Gat, Xiaoqing Ellen Tan, Yossi Adi, Jingyu Liu, Romain Sauvestre, Tal Remez, et al. 2023. Code llama: Open foundation models for code."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3501385.3543957"},{"key":"e_1_3_2_1_22_1","volume-title":"Junyi Jessy Li, and Greg Durrett","author":"Wadhwa Manya","year":"2023","unstructured":"Manya Wadhwa, Jifan Chen, Junyi Jessy Li, and Greg Durrett. 2023. Using natural language explanations to rescale human judgments. arXiv preprint arXiv:2305.14770 (2023)."},{"key":"e_1_3_2_1_23_1","volume-title":"International Conference on Machine Learning. PMLR, 41092\u201341110","author":"Zhang Biao","year":"2023","unstructured":"Biao Zhang, Barry Haddow, and Alexandra Birch. 2023. Prompting large language model for machine translation: A case study. In International Conference on Machine Learning. PMLR, 41092\u201341110."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00632"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"crossref","unstructured":"Lianmin Zheng Wei-Lin Chiang Ying Sheng Siyuan Zhuang Zhanghao Wu Yonghao Zhuang Zi Lin Zhuohan Li Dacheng Li Eric Xing et al. 2023. Judging llm-as-a-judge with mt-bench and chatbot arena. Advances in neural information processing systems 36 (2023) 46595\u201346623.","DOI":"10.52202\/075280-2020"}],"event":{"name":"FSE Companion '26: 34th ACM International Conference on the Foundations of Software Engineering","location":"Concordia University Montreal QC Canada","acronym":"FSE Companion '26","sponsor":["SIGSOFT ACM Special Interest Group on Software Engineering"]},"container-title":["Proceedings of the 34th ACM International Conference on the Foundations of Software Engineering"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3803437.3805263","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T14:38:06Z","timestamp":1784299086000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3803437.3805263"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,5]]},"references-count":25,"alternative-id":["10.1145\/3803437.3805263","10.1145\/3803437"],"URL":"https:\/\/doi.org\/10.1145\/3803437.3805263","relation":{},"subject":[],"published":{"date-parts":[[2026,7,5]]},"assertion":[{"value":"2026-07-17","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}