{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T22:33:50Z","timestamp":1777674830802,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":53,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100006374","name":"Center for Intelligent Information Retrieval, University of Massachusetts Amherst","doi-asserted-by":"publisher","award":["-"],"award-info":[{"award-number":["-"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,7,18]]},"DOI":"10.1145\/3731120.3744603","type":"proceedings-article","created":{"date-parts":[[2025,7,18]],"date-time":"2025-07-18T13:34:06Z","timestamp":1752845646000},"page":"336-346","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Probing Ranking LLMs: A Mechanistic Analysis for Information Retrieval"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5975-9017","authenticated-orcid":false,"given":"Tanya","family":"Chowdhury","sequence":"first","affiliation":[{"name":"University of Massachusetts Amherst, Amherst, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-0997-1493","authenticated-orcid":false,"given":"Atharva","family":"Nijasure","sequence":"additional","affiliation":[{"name":"University of Massachusetts Amherst, Amherst, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0132-5694","authenticated-orcid":false,"given":"James","family":"Allan","sequence":"additional","affiliation":[{"name":"University of Massachusetts Amherst, Amherst, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,7,18]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Explainable information retrieval: A survey. arXiv preprint arXiv:2211.02405","author":"Anand Avishek","year":"2022","unstructured":"Avishek Anand, Lijun Lyu, Maximilian Idahl, Yumeng Wang, Jonas Wallat, and Zijian Zhang. 2022. Explainable information retrieval: A survey. arXiv preprint arXiv:2211.02405 (2022)."},{"key":"e_1_3_2_1_2_1","volume-title":"Gradient-based attribution methods. Explainable AI: Interpreting, explaining and visualizing deep learning","author":"Ancona Marco","year":"2019","unstructured":"Marco Ancona, Enea Ceolini, Cengiz \u00d6ztireli, and Markus Gross. 2019. Gradient-based attribution methods. Explainable AI: Interpreting, explaining and visualizing deep learning (2019), 169-191."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1162\/coli_a_00422"},{"key":"e_1_3_2_1_4_1","volume-title":"International Conference on Machine Learning. PMLR, 2397-2430","author":"Biderman Stella","year":"2023","unstructured":"Stella Biderman, Hailey Schoelkopf, Quentin Gregory Anthony, Herbie Bradley, Kyle O'Brien, Eric Hallahan, Mohammad Aflah Khan, Shivanshu Purohit, USVSN Sai Prashanth, Edward Raff, et al., 2023. Pythia: A suite for analyzing large language models across training and scaling. In International Conference on Machine Learning. PMLR, 2397-2430."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657841"},{"key":"e_1_3_2_1_6_1","volume-title":"Beyond Surface: Probing LLaMA Across Scales and Layers. arXiv preprint arXiv:2312.04333","author":"Chen Nuo","year":"2023","unstructured":"Nuo Chen, Ning Wu, Shining Liang, Ming Gong, Linjun Shou, Dongmei Zhang, and Jia Li. 2023. Beyond Surface: Probing LLaMA Across Scales and Layers. arXiv preprint arXiv:2312.04333 (2023)."},{"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","doi-asserted-by":"publisher","DOI":"10.1145\/3578337.3605138"},{"key":"e_1_3_2_1_9_1","volume-title":"RankSHAP: Shapley Value Based Feature Attributions for Learning to Rank. arXiv preprint arXiv:2405.01848","author":"Chowdhury Tanya","year":"2024","unstructured":"Tanya Chowdhury, Yair Zick, and James Allan. 2024. RankSHAP: Shapley Value Based Feature Attributions for Learning to Rank. arXiv preprint arXiv:2405.01848 (2024)."},{"key":"e_1_3_2_1_10_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_11_1","volume-title":"Are neural nets modular? inspecting functional modularity through differentiable weight masks. arXiv preprint arXiv:2010.02066","author":"Csord\u00e1s R\u00f3bert","year":"2020","unstructured":"R\u00f3bert Csord\u00e1s, Sjoerd van Steenkiste, and J\u00fcrgen Schmidhuber. 2020. Are neural nets modular? inspecting functional modularity through differentiable weight masks. arXiv preprint arXiv:2010.02066 (2020)."},{"key":"e_1_3_2_1_12_1","volume-title":"Sparse autoencoders find highly interpretable features in language models. arXiv preprint arXiv:2309.08600","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. arXiv preprint arXiv:2309.08600 (2023)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2016.42"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3287560.3287572"},{"key":"e_1_3_2_1_15_1","unstructured":"Abhimanyu Dubey Abhinav Jauhri Abhinav Pandey Abhishek Kadian Ahmad Al-Dahle Aiesha Letman Akhil Mathur Alan Schelten Amy Yang Angela Fan et al. 2024. The llama 3 herd of models. arXiv preprint arXiv:2407.21783 (2024)."},{"key":"e_1_3_2_1_16_1","first-page":"1","article-title":"A mathematical framework for transformer circuits","volume":"1","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, et al., 2021. A mathematical framework for transformer circuits. Transformer Circuits Thread, Vol. 1 (2021), 1.","journal-title":"Transformer Circuits Thread"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3450009"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331312"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1575"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-72240-1_23"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-99739-7_14"},{"key":"e_1_3_2_1_22_1","volume-title":"Kevin Ro Wang, and Yoav Goldberg","author":"Geva Mor","year":"2022","unstructured":"Mor Geva, Avi Caciularu, Kevin Ro Wang, and Yoav Goldberg. 2022. Transformer feed-forward layers build predictions by promoting concepts in the vocabulary space. arXiv preprint arXiv:2203.14680 (2022)."},{"key":"e_1_3_2_1_23_1","volume-title":"Transformer feed-forward layers are key-value memories. arXiv preprint arXiv:2012.14913","author":"Geva Mor","year":"2020","unstructured":"Mor Geva, Roei Schuster, Jonathan Berant, and Omer Levy. 2020. Transformer feed-forward layers are key-value memories. arXiv preprint arXiv:2012.14913 (2020)."},{"key":"e_1_3_2_1_24_1","volume-title":"Finding neurons in a haystack: Case studies with sparse probing. arXiv preprint arXiv:2305.01610","author":"Gurnee Wes","year":"2023","unstructured":"Wes Gurnee, Neel Nanda, Matthew Pauly, Katherine Harvey, Dmitrii Troitskii, and Dimitris Bertsimas. 2023. Finding neurons in a haystack: Case studies with sparse probing. arXiv preprint arXiv:2305.01610 (2023)."},{"key":"e_1_3_2_1_25_1","volume-title":"Language models represent space and time. arXiv preprint arXiv:2310.02207","author":"Gurnee Wes","year":"2023","unstructured":"Wes Gurnee and Max Tegmark. 2023. Language models represent space and time. arXiv preprint arXiv:2310.02207 (2023)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.431"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401075"},{"key":"e_1_3_2_1_28_1","unstructured":"Connor Kissane Robert Krzyzanowski Arthur Conmy and Neel Nanda. 2024. Saes (usually) transfer between base and chat models. In AI Alignment Forum."},{"key":"e_1_3_2_1_29_1","unstructured":"Nathan Lambert Lewis Tunstall Nazneen Rajani and Tristan Thrush. 2023. HuggingFace H4 Stack Exchange Preference Dataset. https:\/\/huggingface.co\/datasets\/HuggingFaceH4\/stack-exchange-preferences"},{"key":"e_1_3_2_1_30_1","volume-title":"Implicit representations of meaning in neural language models. arXiv preprint arXiv:2106.00737","author":"Li Belinda Z","year":"2021","unstructured":"Belinda Z Li, Maxwell Nye, and Jacob Andreas. 2021. Implicit representations of meaning in neural language models. arXiv preprint arXiv:2106.00737 (2021)."},{"key":"e_1_3_2_1_31_1","volume-title":"How do Large Language Models Understand Relevance? A Mechanistic Interpretability Perspective. arXiv preprint arXiv:2504.07898","author":"Liu Qi","year":"2025","unstructured":"Qi Liu, Jiaxin Mao, and Ji-Rong Wen. 2025. How do Large Language Models Understand Relevance? A Mechanistic Interpretability Perspective. arXiv preprint arXiv:2504.07898 (2025)."},{"key":"e_1_3_2_1_32_1","volume-title":"A unified approach to interpreting model predictions. Advances in neural information processing systems","author":"Lundberg Scott M","year":"2017","unstructured":"Scott M Lundberg and Su-In Lee. 2017. A unified approach to interpreting model predictions. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_33_1","volume-title":"Fine-tuning llama for multi-stage text retrieval. arXiv preprint arXiv:2310.08319","author":"Ma Xueguang","year":"2023","unstructured":"Xueguang Ma, Liang Wang, Nan Yang, Furu Wei, and Jimmy Lin. 2023. Fine-tuning llama for multi-stage text retrieval. arXiv preprint arXiv:2310.08319 (2023)."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00457"},{"key":"e_1_3_2_1_35_1","volume-title":"Is this the subspace you are looking for? an interpretability illusion for subspace activation patching. arXiv preprint arXiv:2311.17030","author":"Makelov Aleksandar","year":"2023","unstructured":"Aleksandar Makelov, Georg Lange, and Neel Nanda. 2023. Is this the subspace you are looking for? an interpretability illusion for subspace activation patching. arXiv preprint arXiv:2311.17030 (2023)."},{"key":"e_1_3_2_1_36_1","volume-title":"Towards principled evaluations of sparse autoencoders for interpretability and control. arXiv preprint arXiv:2405.08366","author":"Makelov Aleksandar","year":"2024","unstructured":"Aleksandar Makelov, George Lange, and Neel Nanda. 2024. Towards principled evaluations of sparse autoencoders for interpretability and control. arXiv preprint arXiv:2405.08366 (2024)."},{"key":"e_1_3_2_1_37_1","volume-title":"Is sparse attention more interpretable? arXiv preprint arXiv:2106.01087","author":"Meister Clara","year":"2021","unstructured":"Clara Meister, Stefan Lazov, Isabelle Augenstein, and Ryan Cotterell. 2021. Is sparse attention more interpretable? arXiv preprint arXiv:2106.01087 (2021)."},{"key":"e_1_3_2_1_38_1","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. (2016)."},{"key":"e_1_3_2_1_39_1","volume-title":"How Relevance Emerges: Interpreting LoRA Fine-Tuning in Reranking LLMs. arXiv preprint arXiv:2504.08780","author":"Nijasure Atharva","year":"2025","unstructured":"Atharva Nijasure, Tanya Chowdhury, and James Allan. 2025. How Relevance Emerges: Interpreting LoRA Fine-Tuning in Reranking LLMs. arXiv preprint arXiv:2504.08780 (2025)."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"crossref","unstructured":"Andrew Parry Catherine Chen Carsten Eickhoff and Sean MacAvaney. 2024. MechIR: A Mechanistic Interpretability Framework for Information Retrieval. (2024).","DOI":"10.1007\/978-3-031-88720-8_16"},{"key":"e_1_3_2_1_41_1","volume-title":"abs\/1306.2597","author":"Qin Tao","year":"2013","unstructured":"Tao Qin and Tie-Yan Liu. 2013. Introducing LETOR 4.0 Datasets. CoRR, Vol. abs\/1306.2597 (2013). http:\/\/arxiv.org\/abs\/1306.2597"},{"key":"e_1_3_2_1_42_1","volume-title":"Explaining documents' relevance to search queries. arXiv preprint arXiv:2111.01314","author":"Rahimi Razieh","year":"2021","unstructured":"Razieh Rahimi, Youngwoo Kim, Hamed Zamani, and James Allan. 2021. Explaining documents' relevance to search queries. arXiv preprint arXiv:2111.01314 (2021)."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/SaTML54575.2023.00039"},{"key":"e_1_3_2_1_44_1","volume-title":"Probing the probing paradigm: Does probing accuracy entail task relevance? arXiv preprint arXiv:2005.00719","author":"Ravichander Abhilasha","year":"2020","unstructured":"Abhilasha Ravichander, Yonatan Belinkov, and Eduard Hovy. 2020. Probing the probing paradigm: Does probing accuracy entail task relevance? arXiv preprint arXiv:2005.00719 (2020)."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00519"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3289600.3290620"},{"key":"e_1_3_2_1_47_1","volume-title":"International conference on machine learning. PMLR, 3319-3328","author":"Sundararajan Mukund","year":"2017","unstructured":"Mukund Sundararajan, Ankur Taly, and Qiqi Yan. 2017. Axiomatic attribution for deep networks. In International conference on machine learning. PMLR, 3319-3328."},{"key":"e_1_3_2_1_48_1","volume-title":"Beir: A heterogenous benchmark for zero-shot evaluation of information retrieval models. arXiv preprint arXiv:2104.08663","author":"Thakur Nandan","year":"2021","unstructured":"Nandan Thakur, Nils Reimers, Andreas R\u00fcckl\u00e9, Abhishek Srivastava, and Iryna Gurevych. 2021. Beir: A heterogenous benchmark for zero-shot evaluation of information retrieval models. arXiv preprint arXiv:2104.08663 (2021)."},{"key":"e_1_3_2_1_49_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_50_1","first-page":"15173","article-title":"Supermasks in superposition","volume":"33","author":"Wortsman Mitchell","year":"2020","unstructured":"Mitchell Wortsman, Vivek Ramanujan, Rosanne Liu, Aniruddha Kembhavi, Mohammad Rastegari, Jason Yosinski, and Ali Farhadi. 2020. Supermasks in superposition. Advances in Neural Information Processing Systems, Vol. 33 (2020), 15173-15184.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401325"},{"key":"e_1_3_2_1_52_1","volume-title":"Object detectors emerge in deep scene cnns. arXiv preprint arXiv:1412.6856","author":"Zhou Bolei","year":"2014","unstructured":"Bolei Zhou, Aditya Khosla, Agata Lapedriza, Aude Oliva, and Antonio Torralba. 2014. Object detectors emerge in deep scene cnns. arXiv preprint arXiv:1412.6856 (2014)."},{"key":"e_1_3_2_1_53_1","volume-title":"Revisiting the importance of individual units in cnns via ablation. arXiv preprint arXiv:1806.02891","author":"Zhou Bolei","year":"2018","unstructured":"Bolei Zhou, Yiyou Sun, David Bau, and Antonio Torralba. 2018. Revisiting the importance of individual units in cnns via ablation. arXiv preprint arXiv:1806.02891 (2018)."}],"event":{"name":"ICTIR '25: International ACM SIGIR Conference on Innovative Concepts and Theories in Information Retrieval","location":"Padua Italy","acronym":"ICTIR '25","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 2025 International ACM SIGIR Conference on Innovative Concepts and Theories in Information Retrieval (ICTIR)"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3731120.3744603","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T13:18:41Z","timestamp":1755868721000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3731120.3744603"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,18]]},"references-count":53,"alternative-id":["10.1145\/3731120.3744603","10.1145\/3731120"],"URL":"https:\/\/doi.org\/10.1145\/3731120.3744603","relation":{},"subject":[],"published":{"date-parts":[[2025,7,18]]},"assertion":[{"value":"2025-07-18","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}