{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T17:09:51Z","timestamp":1774026591586,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":45,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,4,22]],"date-time":"2025-04-22T00:00:00Z","timestamp":1745280000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,4,22]]},"DOI":"10.1145\/3696410.3714732","type":"proceedings-article","created":{"date-parts":[[2025,5,5]],"date-time":"2025-05-05T16:42:02Z","timestamp":1746463322000},"page":"1716-1732","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Assessing and Post-Processing Black Box Large Language Models for Knowledge Editing"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-8870-1759","authenticated-orcid":false,"given":"Xiaoshuai","family":"Song","sequence":"first","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-4995-2041","authenticated-orcid":false,"given":"Zhengyang","family":"Wang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8831-560X","authenticated-orcid":false,"given":"Keqing","family":"He","sequence":"additional","affiliation":[{"name":"Meituan Group, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2318-0281","authenticated-orcid":false,"given":"Guanting","family":"Dong","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4109-1984","authenticated-orcid":false,"given":"Yutao","family":"Mou","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-2454-927X","authenticated-orcid":false,"given":"Jinxu","family":"Zhao","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9416-7666","authenticated-orcid":false,"given":"Weiran","family":"Xu","sequence":"additional","affiliation":[{"name":"Beijing University of Post and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,4,22]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Chatgpt is a knowledgeable but inexperienced solver: An investigation of commonsense problem in large language models. arXiv preprint arXiv:2303.16421","author":"Bian Ning","year":"2023","unstructured":"Ning Bian, Xianpei Han, Le Sun, Hongyu Lin, Yaojie Lu, and Ben He. 2023. Chatgpt is a knowledgeable but inexperienced solver: An investigation of commonsense problem in large language models. arXiv preprint arXiv:2303.16421 (2023)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29728"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.12"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_7_1","volume-title":"A survey for in-context learning. arXiv preprint arXiv:2301.00234","author":"Dong Qingxiu","year":"2022","unstructured":"Qingxiu Dong, Lei Li, Damai Dai, Ce Zheng, Zhiyong Wu, Baobao Chang, Xu Sun, Jingjing Xu, and Zhifang Sui. 2022. A survey for in-context learning. arXiv preprint arXiv:2301.00234 (2022)."},{"key":"e_1_3_2_1_8_1","volume-title":"Ragas: Automated evaluation of retrieval augmented generation. arXiv preprint arXiv:2309.15217","author":"Es Shahul","year":"2023","unstructured":"Shahul Es, Jithin James, Luis Espinosa-Anke, and Steven Schockaert. 2023. Ragas: Automated evaluation of retrieval augmented generation. arXiv preprint arXiv:2309.15217 (2023)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_10_1","unstructured":"Yunfan Gao Yun Xiong Xinyu Gao Kangxiang Jia Jinliu Pan Yuxi Bi Yi Dai Jiawei Sun Meng Wang and Haofen Wang. 2024. Retrieval-Augmented Generation for Large Language Models: A Survey. arxiv: 2312.10997 [cs.CL]"},{"key":"e_1_3_2_1_11_1","unstructured":"Google. 2023. Google AI PaLM 2 -- Google AI. https:\/\/ai.google\/discover\/palm2"},{"key":"e_1_3_2_1_12_1","unstructured":"Edward J. Hu Yelong Shen Phillip Wallis Zeyuan Allen-Zhu Yuanzhi Li Shean Wang Lu Wang and Weizhu Chen. 2021. LoRA: Low-Rank Adaptation of Large Language Models. arxiv: 2106.09685 [cs.CL]"},{"key":"e_1_3_2_1_13_1","volume-title":"Transformer-Patcher: One Mistake worth One Neuron. arXiv preprint arXiv:2301.09785","author":"Huang Zeyu","year":"2023","unstructured":"Zeyu Huang, Yikang Shen, Xiaofeng Zhang, Jie Zhou, Wenge Rong, and Zhang Xiong. 2023. Transformer-Patcher: One Mistake worth One Neuron. arXiv preprint arXiv:2301.09785 (2023)."},{"key":"e_1_3_2_1_14_1","unstructured":"Hakan Inan Kartikeya Upasani Jianfeng Chi Rashi Rungta Krithika Iyer Yuning Mao Michael Tontchev Qing Hu Brian Fuller Davide Testuggine et al. 2023. Llama guard: Llm-based input-output safeguard for human-ai conversations. arXiv preprint arXiv:2312.06674 (2023)."},{"key":"e_1_3_2_1_15_1","volume-title":"Scaling laws for neural language models. arXiv preprint arXiv:2001.08361","author":"Kaplan Jared","year":"2020","unstructured":"Jared Kaplan, Sam McCandlish, Tom Henighan, Tom B Brown, Benjamin Chess, Rewon Child, Scott Gray, Alec Radford, Jeffrey Wu, and Dario Amodei. 2020. Scaling laws for neural language models. arXiv preprint arXiv:2001.08361 (2020)."},{"key":"e_1_3_2_1_16_1","volume-title":"Kingma and Jimmy Ba","author":"Diederik","year":"2017","unstructured":"Diederik P. Kingma and Jimmy Ba. 2017. Adam: A Method for Stochastic Optimization. arxiv: 1412.6980 [cs.LG]"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/K17-1034"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29818"},{"key":"e_1_3_2_1_19_1","volume-title":"Rouge: A package for automatic evaluation of summaries. In Text summarization branches out. 74--81.","author":"Lin Chin-Yew","year":"2004","unstructured":"Chin-Yew Lin. 2004. Rouge: A package for automatic evaluation of summaries. In Text summarization branches out. 74--81."},{"key":"e_1_3_2_1_20_1","volume-title":"Vera: A General-Purpose Plausibility Estimation Model for Commonsense Statements. arXiv preprint arXiv:2305.03695","author":"Liu Jiacheng","year":"2023","unstructured":"Jiacheng Liu, Wenya Wang, Dianzhuo Wang, Noah A Smith, Yejin Choi, and Hannaneh Hajishirzi. 2023a. Vera: A General-Purpose Plausibility Estimation Model for Commonsense Statements. arXiv preprint arXiv:2305.03695 (2023)."},{"key":"e_1_3_2_1_21_1","volume-title":"What Makes Good Data for Alignment? A Comprehensive Study of Automatic Data Selection in Instruction Tuning. arXiv preprint arXiv:2312.15685","author":"Liu Wei","year":"2023","unstructured":"Wei Liu, Weihao Zeng, Keqing He, Yong Jiang, and Junxian He. 2023b. What Makes Good Data for Alignment? A Comprehensive Study of Automatic Data Selection in Instruction Tuning. arXiv preprint arXiv:2312.15685 (2023)."},{"key":"e_1_3_2_1_22_1","volume-title":"Instruction Tagging for Analyzing Supervised Fine-tuning of Large Language Models. arXiv e-prints","author":"Lu Keming","year":"2023","unstructured":"Keming Lu, Hongyi Yuan, Zheng Yuan, Runji Lin, Junyang Lin, Chuanqi Tan, Chang Zhou, and Jingren Zhou. 2023. # InsTag: Instruction Tagging for Analyzing Supervised Fine-tuning of Large Language Models. arXiv e-prints (2023), arXiv--2308."},{"key":"e_1_3_2_1_23_1","first-page":"17359","article-title":"Locating and editing factual associations in GPT","volume":"35","author":"Meng Kevin","year":"2022","unstructured":"Kevin Meng, David Bau, Alex Andonian, and Yonatan Belinkov. 2022a. Locating and editing factual associations in GPT. Advances in Neural Information Processing Systems, Vol. 35 (2022), 17359--17372.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_24_1","volume-title":"Alex Andonian, Yonatan Belinkov, and David Bau.","author":"Meng Kevin","year":"2022","unstructured":"Kevin Meng, Arnab Sen Sharma, Alex Andonian, Yonatan Belinkov, and David Bau. 2022b. Mass-editing memory in a transformer. arXiv preprint arXiv:2210.07229 (2022)."},{"key":"e_1_3_2_1_25_1","unstructured":"meta. 2023. meta-llama\/Llama-2--70b-chat-hf \u00b7 Hugging Face. https:\/\/huggingface.co\/meta-llama\/Llama-2--70b-chat-hf"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.741"},{"key":"e_1_3_2_1_27_1","volume-title":"Fast model editing at scale. arXiv preprint arXiv:2110.11309","author":"Mitchell Eric","year":"2021","unstructured":"Eric Mitchell, Charles Lin, Antoine Bosselut, Chelsea Finn, and Christopher D Manning. 2021. Fast model editing at scale. arXiv preprint arXiv:2110.11309 (2021)."},{"key":"e_1_3_2_1_28_1","volume-title":"International Conference on Machine Learning. PMLR, 15817--15831","author":"Mitchell Eric","year":"2022","unstructured":"Eric Mitchell, Charles Lin, Antoine Bosselut, Christopher D Manning, and Chelsea Finn. 2022. Memory-based model editing at scale. In International Conference on Machine Learning. PMLR, 15817--15831."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_30_1","volume-title":"Editable neural networks. arXiv preprint arXiv:2004.00345","author":"Sinitsin Anton","year":"2020","unstructured":"Anton Sinitsin, Vsevolod Plokhotnyuk, Dmitriy Pyrkin, Sergei Popov, and Artem Babenko. 2020. Editable neural networks. arXiv preprint arXiv:2004.00345 (2020)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_32_1","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale et al. 2023. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)."},{"key":"e_1_3_2_1_33_1","volume-title":"Evaluating open question answering evaluation. arXiv preprint arXiv:2305.12421","author":"Wang Cunxiang","year":"2023","unstructured":"Cunxiang Wang, Sirui Cheng, Zhikun Xu, Bowen Ding, Yidong Wang, and Yue Zhang. 2023a. Evaluating open question answering evaluation. arXiv preprint arXiv:2305.12421 (2023)."},{"key":"e_1_3_2_1_34_1","unstructured":"Song Wang Yaochen Zhu Haochen Liu Zaiyi Zheng Chen Chen et al. 2023b. Knowledge editing for large language models: A survey. arXiv preprint arXiv:2310.16218 (2023)."},{"key":"e_1_3_2_1_35_1","volume-title":"Deepedit: Knowledge editing as decoding with constraints. arXiv preprint arXiv:2401.10471","author":"Wang Yiwei","year":"2024","unstructured":"Yiwei Wang, Muhao Chen, Nanyun Peng, and Kai-Wei Chang. 2024. Deepedit: Knowledge editing as decoding with constraints. arXiv preprint arXiv:2401.10471 (2024)."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.174"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.632"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_39_1","unstructured":"Ningyu Zhang Yunzhi Yao Bozhong Tian Peng Wang Shumin Deng Mengru Wang Zekun Xi Shengyu Mao Jintian Zhang Yuansheng Ni Siyuan Cheng Ziwen Xu Xin Xu Jia-Chen Gu Yong Jiang Pengjun Xie Fei Huang Lei Liang Zhiqiang Zhang Xiaowei Zhu Jun Zhou and Huajun Chen. 2024. A Comprehensive Study of Knowledge Editing for Large Language Models. arxiv: 2401.01286 [cs.CL]"},{"key":"e_1_3_2_1_40_1","volume-title":"Wei Bi, Freda Shi, and Shuming Shi.","author":"Zhang Yue","year":"2023","unstructured":"Yue Zhang, Yafu Li, Leyang Cui, Deng Cai, Lemao Liu, Tingchen Fu, Xinting Huang, Enbo Zhao, Yu Zhang, Yulong Chen, Longyue Wang, Anh Tuan Luu, Wei Bi, Freda Shi, and Shuming Shi. 2023. Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models. arxiv: 2309.01219 [cs.CL]"},{"key":"e_1_3_2_1_41_1","unstructured":"Wayne Xin Zhao Kun Zhou Junyi Li Tianyi Tang Xiaolei Wang Yupeng Hou Yingqian Min Beichen Zhang Junjie Zhang Zican Dong et al. 2023. A survey of large language models. arXiv preprint arXiv:2303.18223 (2023)."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.296"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.971"},{"key":"e_1_3_2_1_44_1","volume-title":"Lima: Less is more for alignment. arXiv preprint arXiv:2305.11206","author":"Zhou Chunting","year":"2023","unstructured":"Chunting Zhou, Pengfei Liu, Puxin Xu, Srini Iyer, Jiao Sun, Yuning Mao, Xuezhe Ma, Avia Efrat, Ping Yu, Lili Yu, et al. 2023. Lima: Less is more for alignment. arXiv preprint arXiv:2305.11206 (2023)."},{"key":"e_1_3_2_1_45_1","volume-title":"Manzil Zaheer, Srinadh Bhojanapalli, Daliang Li, Felix Yu, and Sanjiv Kumar.","author":"Zhu Chen","year":"2020","unstructured":"Chen Zhu, Ankit Singh Rawat, Manzil Zaheer, Srinadh Bhojanapalli, Daliang Li, Felix Yu, and Sanjiv Kumar. 2020. Modifying memories in transformer models. arXiv preprint arXiv:2012.00363 (2020). n"}],"event":{"name":"WWW '25: The ACM Web Conference 2025","location":"Sydney NSW Australia","acronym":"WWW '25","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the ACM on Web Conference 2025"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3696410.3714732","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3696410.3714732","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:18:41Z","timestamp":1750295921000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3696410.3714732"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,22]]},"references-count":45,"alternative-id":["10.1145\/3696410.3714732","10.1145\/3696410"],"URL":"https:\/\/doi.org\/10.1145\/3696410.3714732","relation":{},"subject":[],"published":{"date-parts":[[2025,4,22]]},"assertion":[{"value":"2025-04-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}