{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/axiomatic-causal-interventions-for-reverse","title":"Axiomatic Causal Interventions for Reverse Engineering Relevance Computation in Neural Retrieval Models","arxiv_id":"2405.02503","date":"2024-05-03","proceeding":null,"authors":["Catherine Chen","Jack Merullo","Carsten Eickhoff"],"abstract":"Neural models have demonstrated remarkable performance across diverse ranking tasks. However, the processes and internal mechanisms along which they determine relevance are still largely unknown. Existing approaches for analyzing neural ranker behavior with respect to IR properties rely either on assessing overall model behavior or employing probing methods that may offer an incomplete understanding of causal mechanisms. To provide a more granular understanding of internal model decision-making processes, we propose the use of causal interventions to reverse engineer neural rankers, and demonstrate how mechanistic interpretability methods can be used to isolate components satisfying term-frequency axioms within a ranking model. We identify a group of attention heads that detect duplicate tokens in earlier layers of the model, then communicate with downstream heads to compute overall document relevance. More generally, we propose that this style of mechanistic analysis opens up avenues for reverse engineering the processes neural retrieval models use to compute relevance. This work aims to initiate granular interpretability efforts that will not only benefit retrieval model development and training, but ultimately ensure safer deployment of these models.","url_abs":"https://arxiv.org/abs/2405.02503v2","url_pdf":"https://arxiv.org/pdf/2405.02503v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"axiomatic-causal-interventions-for-reverse","repo_url":"https://github.com/catherineschen/axiomatic-ir-interventions","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":null},{"paper_slug":"axiomatic-causal-interventions-for-reverse","repo_url":"https://github.com/oliversavolainen/axiomatic-ir-reproduce","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":null}],"tasks":[{"task_slug":"decision-making","task_name":"Decision Making"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2405.02503","atlas_url":"https://app.syntology.ai/?focus=2405.02503","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2405.02503"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2405.02503\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2405.02503"},"call":"get_concepts_for_paper(arxiv_id=\"2405.02503\")"}],"by_repo":[{"repo":"catherineschen/axiomatic-ir-interventions","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"oliversavolainen/axiomatic-ir-reproduce","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"721684ee00888df7375f23766d8f7231a94ef20075d928092b4ae7b20fee1248","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}