{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T05:05:46Z","timestamp":1750309546245,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":57,"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"}],"funder":[{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U24B20180"],"award-info":[{"award-number":["U24B20180"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100018537","name":"National Science and Technology Major Project","doi-asserted-by":"publisher","award":["2023ZD0121102"],"award-info":[{"award-number":["2023ZD0121102"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100018537","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,4,22]]},"DOI":"10.1145\/3696410.3714835","type":"proceedings-article","created":{"date-parts":[[2025,4,22]],"date-time":"2025-04-22T22:52:18Z","timestamp":1745362338000},"page":"1963-1976","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Explainable and Efficient Editing for Large Language Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-4797-682X","authenticated-orcid":false,"given":"Tianyu","family":"Zhang","sequence":"first","affiliation":[{"name":"University of Science and Technology of China, Hefei, Anhui, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3317-2103","authenticated-orcid":false,"given":"Junfeng","family":"Fang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-6599-3572","authenticated-orcid":false,"given":"Houcheng","family":"Jiang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4027-1366","authenticated-orcid":false,"given":"Baolong","family":"Bi","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6148-6329","authenticated-orcid":false,"given":"Xiang","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8472-7992","authenticated-orcid":false,"given":"Xiangnan","family":"He","sequence":"additional","affiliation":[{"name":"MoE Key Lab of BIPC, University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,4,22]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Omer Antverg and Yonatan Belinkov. 2022. On the Pitfalls of Analyzing Individual Neurons in Language Models. In ICLR."},{"key":"e_1_3_2_1_2_1","volume-title":"Glass","author":"Bau Anthony","year":"2019","unstructured":"Anthony Bau, Yonatan Belinkov, Hassan Sajjad, Nadir Durrani, Fahim Dalvi, and James R. Glass. 2019. Identifying and Controlling Important Neurons in Neural Machine Translation. In ICLR."},{"key":"e_1_3_2_1_3_1","volume-title":"Hoa Trang Dang, and Danilo Giampiccolo","author":"Bentivogli Luisa","year":"2009","unstructured":"Luisa Bentivogli, Bernardo Magnini, Ido Dagan, Hoa Trang Dang, and Danilo Giampiccolo. 2009. The Fifth PASCAL Recognizing Textual Entailment Challenge. In TAC."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"crossref","unstructured":"Nicola De Cao Wilker Aziz and Ivan Titov. 2021. Editing Factual Knowledge in Language Models. In EMNLP (1). 6491--6506.","DOI":"10.18653\/v1\/2021.emnlp-main.522"},{"key":"e_1_3_2_1_5_1","volume-title":"Sparse Autoencoders Find Highly Interpretable Features in Language Models. CoRR","author":"Cunningham Hoagy","year":"2023","unstructured":"Hoagy Cunningham, Aidan Ewart, Logan Riggs, Robert Huben, and Lee Sharkey. 2023. Sparse Autoencoders Find Highly Interpretable Features in Language Models. CoRR, Vol. abs\/2309.08600 (2023)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"Damai Dai Li Dong Yaru Hao Zhifang Sui Baobao Chang and Furu Wei. 2022. Knowledge Neurons in Pretrained Transformers. In ACL (1). 8493--8502.","DOI":"10.18653\/v1\/2022.acl-long.581"},{"key":"e_1_3_2_1_7_1","volume-title":"Larimar: Large Language Models with Episodic Memory Control. CoRR","author":"Das Payel","year":"2024","unstructured":"Payel Das, Subhajit Chaudhury, Elliot Nelson, Igor Melnyk, Sarath Swaminathan, Sihui Dai, Aur\u00e9lie C. Lozano, Georgios Kollias, Vijil Chenthamarakshan, Jir\u00ed Navr\u00e1til, Soham Dan, and Pin-Yu Chen. 2024. Larimar: Large Language Models with Episodic Memory Control. CoRR, Vol. abs\/2403.11901 (2024)."},{"key":"e_1_3_2_1_8_1","volume-title":"Dolan and Chris Brockett","author":"William","year":"2005","unstructured":"William B. Dolan and Chris Brockett. 2005. Automatically Constructing a Corpus of Sentential Paraphrases. In IWP@IJCNLP."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"crossref","unstructured":"Qingxiu Dong Damai Dai Yifan Song Jingjing Xu Zhifang Sui and Lei Li. 2022. Calibrating Factual Knowledge in Pretrained Language Models. In EMNLP. 5937--5947.","DOI":"10.18653\/v1\/2022.findings-emnlp.438"},{"key":"e_1_3_2_1_10_1","unstructured":"Angeliki Lazaridou er al. 2021. Mind the Gap: Assessing Temporal Generalization in Neural Language Models. In NeurIPS. 29348--29363."},{"key":"e_1_3_2_1_11_1","unstructured":"Abhimanyu Dubey et al. 2024a. The Llama 3 Herd of Models. CoRR Vol. abs\/2407.21783 (2024)."},{"key":"e_1_3_2_1_12_1","unstructured":"Ningyu Zhang et al. 2024b. A Comprehensive Study of Knowledge Editing for Large Language Models. CoRR Vol. abs\/2401.01286 (2024)."},{"key":"e_1_3_2_1_13_1","volume-title":"Brown et al","author":"Tom","year":"2020","unstructured":"Tom B. Brown et al. 2020. Language Models are Few-Shot Learners. In NeurIPS."},{"key":"e_1_3_2_1_14_1","volume-title":"AlphaEdit: Null-Space Constrained Knowledge Editing for Language Models. ICLR","author":"Fang Junfeng","year":"2025","unstructured":"Junfeng Fang, Houcheng Jiang, Kun Wang, Yunshan Ma, Xiang Wang, Xiangnan He, and Tat seng Chua. 2025. AlphaEdit: Null-Space Constrained Knowledge Editing for Language Models. ICLR (2025)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"crossref","unstructured":"Mor Geva Roei Schuster Jonathan Berant and Omer Levy. 2021. Transformer Feed-Forward Layers Are Key-Value Memories. In EMNLP (1). 5484--5495.","DOI":"10.18653\/v1\/2021.emnlp-main.446"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"crossref","unstructured":"Jia-Chen Gu Hao-Xiang Xu Jun-Yu Ma Pan Lu Zhen-Hua Ling Kai-Wei Chang and Nanyun Peng. 2024. Model Editing Harms General Abilities of Large Language Models: Regularization to the Rescue. In EMNLP. 16801--16819.","DOI":"10.18653\/v1\/2024.emnlp-main.934"},{"key":"e_1_3_2_1_17_1","volume-title":"Resolving Model Collapse during Sequential Model Editing. CoRR","author":"Gupta Akshat","year":"2024","unstructured":"Akshat Gupta and Gopala Anumanchipalli. 2024. Rebuilding ROME : Resolving Model Collapse during Sequential Model Editing. CoRR, Vol. abs\/2403.07175 (2024)."},{"key":"e_1_3_2_1_18_1","volume-title":"Model Editing at Scale leads to Gradual and Catastrophic Forgetting. CoRR","author":"Gupta Akshat","year":"2024","unstructured":"Akshat Gupta, Anurag Rao, and Gopala Anumanchipalli. 2024. Model Editing at Scale leads to Gradual and Catastrophic Forgetting. CoRR, Vol. abs\/2401.07453 (2024)."},{"key":"e_1_3_2_1_19_1","unstructured":"Tom Hartvigsen Swami Sankaranarayanan Hamid Palangi Yoon Kim and Marzyeh Ghassemi. 2023. Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptors. In NeurIPS."},{"key":"e_1_3_2_1_20_1","unstructured":"Peter Hase Mohit Bansal Been Kim and Asma Ghandeharioun. 2023. Does Localization Inform Editing? Surprising Differences in Causality-Based Localization vs. Knowledge Editing in Language Models. In NeurIPS."},{"key":"e_1_3_2_1_21_1","unstructured":"Dan Hendrycks Collin Burns Steven Basart Andy Zou Mantas Mazeika Dawn Song and Jacob Steinhardt. 2021. Measuring Massive Multitask Language Understanding. In ICLR."},{"key":"e_1_3_2_1_22_1","unstructured":"Zeyu Huang Yikang Shen Xiaofeng Zhang Jie Zhou Wenge Rong and Zhang Xiong. 2023. Transformer-Patcher: One Mistake Worth One Neuron. In ICLR."},{"key":"e_1_3_2_1_23_1","unstructured":"Houcheng Jiang Junfeng Fang Tianyu Zhang An Zhang Ruipeng Wang Tao Liang and Xiang Wang. 2024. Neuron-Level Sequential Editing for Large Language Models. arxiv: 2410.04045 [cs.CL] https:\/\/arxiv.org\/abs\/2410.04045"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00324"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TC.1972.5008975"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"crossref","unstructured":"Omer Levy Minjoon Seo Eunsol Choi and Luke Zettlemoyer. 2017. Zero-Shot Relation Extraction via Reading Comprehension. In CoNLL. 333--342.","DOI":"10.18653\/v1\/K17-1034"},{"key":"e_1_3_2_1_27_1","volume-title":"Consecutive Model Editing with Batch alongside HooK Layers. CoRR","author":"Li Shuaiyi","year":"2024","unstructured":"Shuaiyi Li, Yang Deng, Deng Cai, Hongyuan Lu, Liang Chen, and Wai Lam. 2024a. Consecutive Model Editing with Batch alongside HooK Layers. CoRR, Vol. abs\/2403.05330 (2024)."},{"key":"e_1_3_2_1_28_1","volume-title":"PMET: Precise Model Editing in a Transformer. In AAAI. 18564--18572.","author":"Li Xiaopeng","year":"2024","unstructured":"Xiaopeng Li, Shasha Li, Shezheng Song, Jing Yang, Jun Ma, and Jie Yu. 2024b. PMET: Precise Model Editing in a Transformer. In AAAI. 18564--18572."},{"key":"e_1_3_2_1_29_1","volume-title":"Perturbation-Restrained Sequential Model Editing. CoRR","author":"Ma Jun-Yu","year":"2024","unstructured":"Jun-Yu Ma, Hong Wang, Hao-Xiang Xu, Zhen-Hua Ling, and Jia-Chen Gu. 2024. Perturbation-Restrained Sequential Model Editing. CoRR, Vol. abs\/2405.16821 (2024)."},{"key":"e_1_3_2_1_30_1","unstructured":"Kevin Meng David Bau Alex Andonian and Yonatan Belinkov. 2022. Locating and Editing Factual Associations in GPT. In NeurIPS."},{"key":"e_1_3_2_1_31_1","volume-title":"Alex J. Andonian, Yonatan Belinkov, and David Bau.","author":"Meng Kevin","year":"2023","unstructured":"Kevin Meng, Arnab Sen Sharma, Alex J. Andonian, Yonatan Belinkov, and David Bau. 2023. Mass-Editing Memory in a Transformer. In ICLR."},{"key":"e_1_3_2_1_32_1","volume-title":"Manning","author":"Mitchell Eric","year":"2022","unstructured":"Eric Mitchell, Charles Lin, Antoine Bosselut, Chelsea Finn, and Christopher D. Manning. 2022a. Fast Model Editing at Scale. In ICLR."},{"key":"e_1_3_2_1_33_1","unstructured":"Eric Mitchell Charles Lin Antoine Bosselut Christopher D. Manning and Chelsea Finn. 2022b. Memory-Based Model Editing at Scale. In ICML. 15817--15831."},{"key":"e_1_3_2_1_35_1","volume-title":"Finding and Editing Multi-Modal Neurons in Pre-Trained Transformer. CoRR","author":"Pan Haowen","year":"2023","unstructured":"Haowen Pan, Yixin Cao, Xiaozhi Wang, and Xun Yang. 2023. Finding and Editing Multi-Modal Neurons in Pre-Trained Transformer. CoRR, Vol. abs\/2311.07470 (2023)."},{"key":"e_1_3_2_1_36_1","volume-title":"Miller","author":"Petroni Fabio","year":"2019","unstructured":"Fabio Petroni, Tim Rockt\u00e4schel, Sebastian Riedel, Patrick S. H. Lewis, Anton Bakhtin, Yuxiang Wu, and Alexander H. Miller. 2019. Language Models as Knowledge Bases?. In EMNLP\/IJCNLP (1). 2463--2473."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.23915\/distill.00024.009"},{"key":"e_1_3_2_1_38_1","unstructured":"Alec Radford Jeffrey Wu Rewon Child David Luan Dario Amodei Ilya Sutskever et al. 2019. Language models are unsupervised multitask learners. OpenAI blog Vol. 1 8 (2019) 9."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"crossref","unstructured":"Adam Roberts Colin Raffel and Noam Shazeer. 2020. How Much Knowledge Can You Pack Into the Parameters of a Language Model?. In EMNLP (1). 5418--5426.","DOI":"10.18653\/v1\/2020.emnlp-main.437"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00519"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"crossref","unstructured":"Sarah Schwettmann Neil Chowdhury Samuel Klein David Bau and Antonio Torralba. 2023. Multimodal Neurons in Pretrained Text-Only Transformers. In ICCV (Workshops). 2854--2859.","DOI":"10.1109\/ICCVW60793.2023.00308"},{"key":"e_1_3_2_1_42_1","volume-title":"Explaining black box text modules in natural language with language models. CoRR","author":"Singh Chandan","year":"2023","unstructured":"Chandan Singh, Aliyah R. Hsu, Richard Antonello, Shailee Jain, Alexander G. Huth, Bin Yu, and Jianfeng Gao. 2023. Explaining black box text modules in natural language with language models. CoRR, Vol. abs\/2305.09863 (2023)."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"crossref","unstructured":"Richard Socher Alex Perelygin Jean Wu Jason Chuang Christopher D. Manning Andrew Y. Ng and Christopher Potts. 2013. Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank. In EMNLP. 1631--1642.","DOI":"10.18653\/v1\/D13-1170"},{"key":"e_1_3_2_1_44_1","unstructured":"Katherine Tian Eric Mitchell Huaxiu Yao Christopher D. Manning and Chelsea Finn. 2024. Fine-Tuning Language Models for Factuality. In ICLR."},{"key":"e_1_3_2_1_45_1","volume-title":"Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971","author":"Touvron Hugo","year":"2023","unstructured":"Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timoth\u00e9e Lacroix, Baptiste Rozi\u00e8re, Naman Goyal, Eric Hambro, Faisal Azhar, et al. 2023. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)."},{"key":"e_1_3_2_1_46_1","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N. Gomez Lukasz Kaiser and Illia Polosukhin. 2017. Attention is All you Need. In NIPS. 5998--6008."},{"volume-title":"N-gram, Positional. In ACL, Lun-Wei Ku","author":"Voita Elena","key":"e_1_3_2_1_47_1","unstructured":"Elena Voita, Javier Ferrando, and Christoforos Nalmpantis. 2024. Neurons in Large Language Models: Dead, N-gram, Positional. In ACL, Lun-Wei Ku, Andre Martins, and Vivek Srikumar (Eds.). Association for Computational Linguistics, 1288--1301."},{"key":"e_1_3_2_1_48_1","volume-title":"Bowman","author":"Wang Alex","year":"2019","unstructured":"Alex Wang, Amanpreet Singh, Julian Michael, Felix Hill, Omer Levy, and Samuel R. Bowman. 2019. GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding. In ICLR."},{"key":"e_1_3_2_1_49_1","unstructured":"Ben Wang and Aran Komatsuzaki. 2021. GPT-J-6B: A 6 billion parameter autoregressive language model."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"crossref","unstructured":"Xiaozhi Wang Kaiyue Wen Zhengyan Zhang Lei Hou Zhiyuan Liu and Juanzi Li. 2022. Finding Skill Neurons in Pre-trained Transformer-based Language Models. In EMNLP. 11132--11152.","DOI":"10.18653\/v1\/2022.emnlp-main.765"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00290"},{"key":"e_1_3_2_1_52_1","volume-title":"Bowman","author":"Williams Adina","year":"2018","unstructured":"Adina Williams, Nikita Nangia, and Samuel R. Bowman. 2018. A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference. In NAACL-HLT. 1112--1122."},{"key":"e_1_3_2_1_53_1","volume-title":"HuggingFace's Transformers: State-of-the-art Natural Language Processing. CoRR","author":"Wolf Thomas","year":"2019","unstructured":"Thomas Wolf, Lysandre Debut, Victor Sanh, Julien Chaumond, Clement Delangue, Anthony Moi, Pierric Cistac, Tim Rault, R\u00e9mi Louf, Morgan Funtowicz, and Jamie Brew. 2019. HuggingFace's Transformers: State-of-the-art Natural Language Processing. CoRR, Vol. abs\/1910.03771 (2019)."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"crossref","unstructured":"Yunzhi Yao Peng Wang Bozhong Tian Siyuan Cheng Zhoubo Li Shumin Deng Huajun Chen and Ningyu Zhang. 2023. Editing Large Language Models: Problems Methods and Opportunities. In EMNLP. 10222--10240.","DOI":"10.18653\/v1\/2023.emnlp-main.632"},{"key":"e_1_3_2_1_55_1","volume-title":"MELO: Enhancing Model Editing with Neuron-Indexed Dynamic LoRA. In AAAI. 19449--19457.","author":"Yu Lang","year":"2024","unstructured":"Lang Yu, Qin Chen, Jie Zhou, and Liang He. 2024. MELO: Enhancing Model Editing with Neuron-Indexed Dynamic LoRA. In AAAI. 19449--19457."},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/3639372"},{"key":"e_1_3_2_1_57_1","volume-title":"Can We Edit Factual Knowledge by In-Context Learning? CoRR","author":"Zheng Ce","year":"2023","unstructured":"Ce Zheng, Lei Li, Qingxiu Dong, Yuxuan Fan, Zhiyong Wu, Jingjing Xu, and Baobao Chang. 2023. Can We Edit Factual Knowledge by In-Context Learning? CoRR, Vol. abs\/2305.12740 (2023)."},{"key":"e_1_3_2_1_58_1","volume-title":"Manzil Zaheer, Srinadh Bhojanapalli, Daliang Li, Felix X. Yu, and Sanjiv Kumar.","author":"Zhu Chen","year":"2020","unstructured":"Chen Zhu, Ankit Singh Rawat, Manzil Zaheer, Srinadh Bhojanapalli, Daliang Li, Felix X. Yu, and Sanjiv Kumar. 2020. Modifying Memories in Transformer Models. CoRR, Vol. abs\/2012.00363 (2020)."}],"event":{"name":"WWW '25: The ACM Web Conference 2025","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"],"location":"Sydney NSW Australia","acronym":"WWW '25"},"container-title":["Proceedings of the ACM on Web Conference 2025"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3696410.3714835","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3696410.3714835","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:18:42Z","timestamp":1750295922000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3696410.3714835"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,22]]},"references-count":57,"alternative-id":["10.1145\/3696410.3714835","10.1145\/3696410"],"URL":"https:\/\/doi.org\/10.1145\/3696410.3714835","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"}}]}}