{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T11:48:13Z","timestamp":1774352893276,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":37,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,7,10]],"date-time":"2024-07-10T00:00:00Z","timestamp":1720569600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Institute of Health","award":["3U54GM115677-08S1"],"award-info":[{"award-number":["3U54GM115677-08S1"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,7,10]]},"DOI":"10.1145\/3626772.3657841","type":"proceedings-article","created":{"date-parts":[[2024,7,11]],"date-time":"2024-07-11T12:40:05Z","timestamp":1720701605000},"page":"1401-1410","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":13,"title":["Axiomatic Causal Interventions for Reverse Engineering Relevance Computation in Neural Retrieval Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-8734-436X","authenticated-orcid":false,"given":"Catherine","family":"Chen","sequence":"first","affiliation":[{"name":"Brown University, Providence, RI, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-9673-6809","authenticated-orcid":false,"given":"Jack","family":"Merullo","sequence":"additional","affiliation":[{"name":"Brown University, Providence, RI, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9895-4061","authenticated-orcid":false,"given":"Carsten","family":"Eickhoff","sequence":"additional","affiliation":[{"name":"University of T\u00fcbingen, T\u00fcbingen, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,7,11]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1162\/coli_a_00422"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00254"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4471-2099-5_12"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-45439-5_40"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531943"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3409256.3409828"},{"key":"e_1_3_2_1_7_1","volume-title":"Finding Inverse Document Frequency Information in BERT. arXiv preprint arXiv:2202.12191","author":"Choi Jaekeol","year":"2022","unstructured":"Jaekeol Choi, Euna Jung, Sungjun Lim, and Wonjong Rhee. 2022. Finding Inverse Document Frequency Information in BERT. arXiv preprint arXiv:2202.12191 (2022)."},{"key":"e_1_3_2_1_8_1","volume-title":"What does bert look at? an analysis of bert's attention. arXiv preprint arXiv:1906.04341","author":"Clark Kevin","year":"2019","unstructured":"Kevin Clark, Urvashi Khandelwal, Omer Levy, and Christopher D Manning. 2019. What does bert look at? an analysis of bert's attention. arXiv preprint arXiv:1906.04341 (2019)."},{"key":"e_1_3_2_1_9_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_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3450009"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/1008992.1009004"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-72240-1_23"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-99739-7_14"},{"key":"e_1_3_2_1_14_1","first-page":"9574","article-title":"Causal abstractions of neural networks","volume":"34","author":"Geiger Atticus","year":"2021","unstructured":"Atticus Geiger, Hanson Lu, Thomas Icard, and Christopher Potts. 2021. Causal abstractions of neural networks. Advances in Neural Information Processing Systems , Vol. 34 (2021), 9574--9586.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_15_1","volume-title":"Dissecting recall of factual associations in auto-regressive language models. arXiv preprint arXiv:2304.14767","author":"Geva Mor","year":"2023","unstructured":"Mor Geva, Jasmijn Bastings, Katja Filippova, and Amir Globerson. 2023. Dissecting recall of factual associations in auto-regressive language models. arXiv preprint arXiv:2304.14767 (2023)."},{"key":"e_1_3_2_1_16_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_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/2983323.2983704"},{"key":"e_1_3_2_1_18_1","volume-title":"How does GPT-2 compute greater-than?: Interpreting mathematical abilities in a pre-trained language model. arXiv preprint arXiv:2305.00586","author":"Hanna Michael","year":"2023","unstructured":"Michael Hanna, Ollie Liu, and Alexandre Variengien. 2023. How does GPT-2 compute greater-than?: Interpreting mathematical abilities in a pre-trained language model. arXiv preprint arXiv:2305.00586 (2023)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3461702.3462578"},{"key":"e_1_3_2_1_20_1","volume-title":"Proc. of SIGIR.","author":"Sebastian","year":"2021","unstructured":"Sebastian Hofst\"atter, Sheng-Chieh Lin, Jheng-Hong Yang, Jimmy Lin, and Allan Hanbury. 2021. Efficiently Teaching an Effective Dense Retriever with Balanced Topic Aware Sampling. In Proc. of SIGIR."},{"key":"e_1_3_2_1_21_1","volume-title":"Badedit: Backdooring large language models by model editing. arXiv preprint arXiv:2403.13355","author":"Li Yanzhou","year":"2024","unstructured":"Yanzhou Li, Tianlin Li, Kangjie Chen, Jian Zhang, Shangqing Liu, Wenhan Wang, Tianwei Zhang, and Yang Liu. 2024. Badedit: Backdooring large language models by model editing. arXiv preprint arXiv:2403.13355 (2024)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00457"},{"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. 2022. 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":"Circuit Component Reuse Across Tasks in Transformer Language Models. arXiv preprint arXiv:2310.08744","author":"Merullo Jack","year":"2023","unstructured":"Jack Merullo, Carsten Eickhoff, and Ellie Pavlick. 2023. Circuit Component Reuse Across Tasks in Transformer Language Models. arXiv preprint arXiv:2310.08744 (2023)."},{"key":"e_1_3_2_1_25_1","unstructured":"Neel Nanda and Joseph Bloom. 2022. TransformerLens. https:\/\/github.com\/neelnanda-io\/TransformerLens."},{"key":"e_1_3_2_1_26_1","volume-title":"MS MARCO: A human generated machine reading comprehension dataset. choice","author":"Nguyen Tri","year":"2016","unstructured":"Tri Nguyen, Mir Rosenberg, Xia Song, Jianfeng Gao, Saurabh Tiwary, Rangan Majumder, and Li Deng. 2016. MS MARCO: A human generated machine reading comprehension dataset. choice , Vol. 2640 (2016), 660."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"crossref","unstructured":"Judea Pearl. 2022. Direct and indirect effects. In Probabilistic and causal inference: the works of Judea Pearl. 373--392.","DOI":"10.1145\/3501714.3501736"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-15712-8_32"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331296"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401286"},{"key":"e_1_3_2_1_31_1","volume-title":"Attention is all you need. Advances in neural information processing systems","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems , Vol. 30 (2017)."},{"key":"e_1_3_2_1_32_1","volume-title":"Investigating gender bias in language models using causal mediation analysis. Advances in neural information processing systems","author":"Vig Jesse","year":"2020","unstructured":"Jesse Vig, Sebastian Gehrmann, Yonatan Belinkov, Sharon Qian, Daniel Nevo, Yaron Singer, and Stuart Shieber. 2020. Investigating gender bias in language models using causal mediation analysis. Advances in neural information processing systems , Vol. 33 (2020), 12388--12401."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3471158.3472256"},{"key":"e_1_3_2_1_34_1","volume-title":"Universal adversarial triggers for attacking and analyzing NLP. arXiv preprint arXiv:1908.07125","author":"Wallace Eric","year":"2019","unstructured":"Eric Wallace, Shi Feng, Nikhil Kandpal, Matt Gardner, and Sameer Singh. 2019. Universal adversarial triggers for attacking and analyzing NLP. arXiv preprint arXiv:1908.07125 (2019)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-28238-6_17"},{"key":"e_1_3_2_1_36_1","volume-title":"Interpretability in the wild: a circuit for indirect object identification in gpt-2 small. arXiv preprint arXiv:2211.00593","author":"Wang Kevin","year":"2022","unstructured":"Kevin Wang, Alexandre Variengien, Arthur Conmy, Buck Shlegeris, and Jacob Steinhardt. 2022. Interpretability in the wild: a circuit for indirect object identification in gpt-2 small. arXiv preprint arXiv:2211.00593 (2022)."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401325"}],"event":{"name":"SIGIR 2024: The 47th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Washington DC USA","acronym":"SIGIR 2024","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3626772.3657841","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3626772.3657841","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T05:41:53Z","timestamp":1755841313000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3626772.3657841"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,10]]},"references-count":37,"alternative-id":["10.1145\/3626772.3657841","10.1145\/3626772"],"URL":"https:\/\/doi.org\/10.1145\/3626772.3657841","relation":{},"subject":[],"published":{"date-parts":[[2024,7,10]]},"assertion":[{"value":"2024-07-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}