{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T16:40:14Z","timestamp":1786120814855,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":25,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,8,8]],"date-time":"2026-08-08T00:00:00Z","timestamp":1786147200000},"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":[[2026,8,9]]},"DOI":"10.1145\/3770855.3816451","type":"proceedings-article","created":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T17:15:37Z","timestamp":1786036537000},"page":"13395-13398","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Interpretability in the Era of Large Language Models: Mechanistic Methodology, Empirical Practices, and Applications"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-8131-0060","authenticated-orcid":false,"given":"Wei","family":"Zhang","sequence":"first","affiliation":[{"name":"Tongyi Lab, Alibaba Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-6618-8760","authenticated-orcid":false,"given":"Zhengfu","family":"He","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6280-1682","authenticated-orcid":false,"given":"Lulu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tongyi Lab, Alibaba Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9197-9426","authenticated-orcid":false,"given":"Xuanjing","family":"Huang","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8662-5818","authenticated-orcid":false,"given":"Jieping","family":"Ye","sequence":"additional","affiliation":[{"name":"Tongyi Lab, Alibaba Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3501-8510","authenticated-orcid":false,"given":"Xu","family":"Shen","sequence":"additional","affiliation":[{"name":"Tongyi Lab, Alibaba Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,8,8]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Circuit Tracing: Revealing Computational Graphs in Language Models. Transformer Circuits Thread","author":"Ameisen Emmanuel","year":"2025","unstructured":"Emmanuel Ameisen, Jack Lindsey, Adam Pearce, Wes Gurnee, Nicholas L. Turner, Brian Chen, Craig Citro, David Abrahams, Shan Carter, Basil Hosmer, Jonathan Marcus, Michael Sklar, Adly Templeton, Trenton Bricken, Callum McDougall, Hoagy Cunningham, Thomas Henighan, Adam Jermyn, Andy Jones, Andrew Persic, Zhenyi Qi, T. Ben Thompson, Sam Zimmerman, Kelley Rivoire, Thomas Conerly, Chris Olah, and Joshua Batson. 2025. Circuit Tracing: Revealing Computational Graphs in Language Models. Transformer Circuits Thread (2025). https:\/\/transformer-circuits.pub\/2025\/attribution-graphs\/methods.html"},{"key":"e_1_3_2_1_2_1","volume-title":"Forty-first International Conference on Machine Learning","volume":"235","author":"Chen Wei","year":"2024","unstructured":"Wei Chen, Zhen Huang, Liang Xie, Binbin Lin, Houqiang Li, Le Lu, Xinmei Tian, Deng Cai, Yonggang Zhang, Wenxiao Wang, Xu Shen, and Jieping Ye. 2024. From Yes-Men to Truth-Tellers: Addressing Sycophancy in Large Language Models with Pinpoint Tuning. In Forty-first International Conference on Machine Learning, Vol. V235. 6950-6972. https:\/\/proceedings.mlr.press\/v235\/chen24u.html"},{"key":"e_1_3_2_1_3_1","unstructured":"Rui Dai Sile Hu Xu Shen Yonggang Zhang Xinmei Tian and Jieping Ye. 2025. Leveraging Submodule Linearity Enhances Task Arithmetic Performance in LLMs. In The Thirteenth International Conference on Learning Representations. OpenReview.net. https:\/\/openreview.net\/forum?id=irPcM6X5FV"},{"key":"e_1_3_2_1_4_1","volume-title":"A Mathematical Framework for Transformer Circuits. Transformer Circuits Thread","author":"Elhage Nelson","year":"2021","unstructured":"Nelson Elhage, Neel Nanda, Catherine Olsson, Tom Henighan, Nicholas Joseph, Ben Mann, Amanda Askell, Yuntao Bai, Anna Chen, Tom Conerly, Nova DasSarma, Dawn Drain, Deep Ganguli, Zac Hatfield-Dodds, Danny Hernandez, Andy Jones, Jackson Kernion, Liane Lovitt, Kamal Ndousse, Dario Amodei, Tom Brown, Jack Clark, Jared Kaplan, Sam McCandlish, and Chris Olah. 2021. A Mathematical Framework for Transformer Circuits. Transformer Circuits Thread (2021). https:\/\/transformer-circuits.pub\/2021\/framework\/index.html."},{"key":"e_1_3_2_1_5_1","volume-title":"Evolution of Concepts in Language Model Pre-Training. In The Fourteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=qKmXz1UR0Z","author":"Ge Xuyang","year":"2026","unstructured":"Xuyang Ge, Wentao Shu, Jiaxing Wu, Yunhua Zhou, Zhengfu He, and Xipeng Qiu. 2026. Evolution of Concepts in Language Model Pre-Training. In The Fourteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=qKmXz1UR0Z"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2405.13868"},{"key":"e_1_3_2_1_7_1","volume-title":"Localizing model behavior with path patching. arXiv preprint arXiv:2304.05969","author":"Goldowsky-Dill Nicholas","year":"2023","unstructured":"Nicholas Goldowsky-Dill, Chris MacLeod, Lucas Sato, and Aryaman Arora. 2023. Localizing model behavior with path patching. arXiv preprint arXiv:2304.05969 (2023)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.471"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2410.20526"},{"key":"e_1_3_2_1_10_1","volume-title":"Towards Understanding the Nature of Attention with Low-Rank Sparse Decomposition. In The Fourteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=9A2etpDFIB","author":"He Zhengfu","year":"2026","unstructured":"Zhengfu He, Junxuan Wang, Rui Lin, Xuyang Ge, Wentao Shu, Qiong Tang, Junping Zhang, and Xipeng Qiu. 2026. Towards Understanding the Nature of Attention with Low-Rank Sparse Decomposition. In The Fourteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=9A2etpDFIB"},{"key":"e_1_3_2_1_11_1","volume-title":"Emergent Introspective Awareness in Large Language Models. Transformer Circuits Thread","author":"Lindsey Jack","year":"2025","unstructured":"Jack Lindsey. 2025. Emergent Introspective Awareness in Large Language Models. Transformer Circuits Thread (2025). https:\/\/transformer-circuits.pub\/2025\/introspection\/index.html"},{"key":"e_1_3_2_1_12_1","volume-title":"On the Biology of a Large Language Model. Transformer Circuits Thread","author":"Lindsey Jack","year":"2025","unstructured":"Jack Lindsey, Wes Gurnee, Emmanuel Ameisen, Brian Chen, Adam Pearce, Nicholas L. Turner, Craig Citro, David Abrahams, Shan Carter, Basil Hosmer, Jonathan Marcus, Michael Sklar, Adly Templeton, Trenton Bricken, Callum McDougall, Hoagy Cunningham, Thomas Henighan, Adam Jermyn, Andy Jones, Andrew Persic, Zhenyi Qi, T. Ben Thompson, Sam Zimmerman, Kelley Rivoire, Thomas Conerly, Chris Olah, and Joshua Batson. 2025. On the Biology of a Large Language Model. Transformer Circuits Thread (2025). https:\/\/transformer-circuits.pub\/2025\/attribution-graphs\/biology.html."},{"key":"e_1_3_2_1_13_1","volume-title":"Task-Specific Data Selection for Instruction Tuning via Monosemantic Neuronal Activations. arXiv preprint arXiv:2503.15573","author":"Ma Da","year":"2025","unstructured":"Da Ma, Gonghu Shang, Zhi Chen, Libo Qin, Yijie Luo, Lei Pan, Shuai Fan, Lu Chen, and Kai Yu. 2025. Task-Specific Data Selection for Instruction Tuning via Monosemantic Neuronal Activations. arXiv preprint arXiv:2503.15573 (2025)."},{"key":"e_1_3_2_1_14_1","unstructured":"nostalgebraist. 2020. Interpreting GPT: the logit lens. https:\/\/www.lesswrong.com\/posts\/AcKRB8wDpdaN6v6ru\/interpreting-gpt-the-logit-lens. LessWrong."},{"key":"e_1_3_2_1_15_1","volume-title":"Bridging the Attention Gap: Complete Replacement Models for Complete Circuit Tracing. OpenMOSS Interpretability Research","author":"Shu Wentao","year":"2026","unstructured":"Wentao Shu, Xuyang Ge, Guancheng Zhou, Junxuan Wang, Rui Lin, Zhaoxuan Song, Jiaxing Wu, Zhengfu He, and Xipeng Qiu. 2026. Bridging the Attention Gap: Complete Replacement Models for Complete Circuit Tracing. OpenMOSS Interpretability Research (2026). https:\/\/interp.open-moss.com\/posts\/complete-replacement"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.196"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v40i39.40592"},{"key":"e_1_3_2_1_18_1","volume-title":"Neuron Descriptions: Understanding Neurons in Language Models. https:\/\/transluce.org\/neuron-descriptions","year":"2024","unstructured":"Transluce. 2024. Neuron Descriptions: Understanding Neurons in Language Models. https:\/\/transluce.org\/neuron-descriptions"},{"key":"e_1_3_2_1_19_1","volume-title":"International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=NpsVSN6o4ul","author":"Wang Kevin Ro","year":"2023","unstructured":"Kevin Ro Wang, Alexandre Variengien, Arthur Conmy, Buck Shlegeris, and Jacob Steinhardt. 2023. Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 Small. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=NpsVSN6o4ul"},{"key":"e_1_3_2_1_20_1","volume-title":"Olivia Watkins, Alex Makelov, Ryan A Chi, Samuel Miserendino, Jeffrey Wang, Achyuta Rajaram, Johannes Heidecke, Tejal Patwardhan, et al.","author":"Wang Miles","year":"2025","unstructured":"Miles Wang, Tom Dupr\u00e9 la Tour, Olivia Watkins, Alex Makelov, Ryan A Chi, Samuel Miserendino, Jeffrey Wang, Achyuta Rajaram, Johannes Heidecke, Tejal Patwardhan, et al., 2025a. Persona features control emergent misalignment. arXiv preprint arXiv:2506.19823 (2025)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.1133"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0502"},{"key":"e_1_3_2_1_23_1","volume-title":"SAEMark: Steering Personalized Multilingual LLM Watermarks with Sparse Autoencoders. In The Thirty-ninth Annual Conference on Neural Information Processing Systems.","author":"Yu Zhuohao","unstructured":"Zhuohao Yu, Xingru Jiang, Weizheng Gu, Yidong Wang, Qingsong Wen, Shikun Zhang, and Wei Ye. [n.d.]. SAEMark: Steering Personalized Multilingual LLM Watermarks with Sparse Autoencoders. In The Thirty-ninth Annual Conference on Neural Information Processing Systems."},{"key":"e_1_3_2_1_24_1","volume-title":"Interpreting and Improving Large Language Models in Arithmetic Calculation. In Forty-first International Conference on Machine Learning","volume":"235","author":"Zhang Wei","year":"2024","unstructured":"Wei Zhang, Chaoqun Wan, Yonggang Zhang, Yiu-ming Cheung, Xinmei Tian, Xu Shen, and Jieping Ye. 2024. Interpreting and Improving Large Language Models in Arithmetic Calculation. In Forty-first International Conference on Machine Learning, Vol. V235. 59932-59950. https:\/\/proceedings.mlr.press\/v235\/zhang24bk.html"},{"key":"e_1_3_2_1_25_1","volume-title":"Verifying Chain-of-Thought Reasoning via Its Computational Graph. arXiv preprint arXiv:2510.09312","author":"Zhao Zheng","year":"2025","unstructured":"Zheng Zhao, Yeskendir Koishekenov, Xianjun Yang, Naila Murray, and Nicola Cancedda. 2025. Verifying Chain-of-Thought Reasoning via Its Computational Graph. arXiv preprint arXiv:2510.09312 (2025)."}],"event":{"name":"KDD '26: The 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Jeju Island Republic of Korea","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2"],"original-title":[],"deposited":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T01:32:20Z","timestamp":1786066340000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3770855.3816451"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,8]]},"references-count":25,"alternative-id":["10.1145\/3770855.3816451","10.1145\/3770855"],"URL":"https:\/\/doi.org\/10.1145\/3770855.3816451","relation":{},"subject":[],"published":{"date-parts":[[2026,8,8]]},"assertion":[{"value":"2026-08-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}