{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/attention-meets-post-hoc-interpretability-a","title":"Attention Meets Post-hoc Interpretability: A Mathematical Perspective","arxiv_id":"2402.03485","date":"2024-02-05","proceeding":null,"authors":["Gianluigi Lopardo","Frederic Precioso","Damien Garreau"],"abstract":"Attention-based architectures, in particular transformers, are at the heart of a technological revolution. Interestingly, in addition to helping obtain state-of-the-art results on a wide range of applications, the attention mechanism intrinsically provides meaningful insights on the internal behavior of the model. Can these insights be used as explanations? Debate rages on. In this paper, we mathematically study a simple attention-based architecture and pinpoint the differences between post-hoc and attention-based explanations. We show that they provide quite different results, and that, despite their limitations, post-hoc methods are capable of capturing more useful insights than merely examining the attention weights.","url_abs":"https://arxiv.org/abs/2402.03485v2","url_pdf":"https://arxiv.org/pdf/2402.03485v2.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":"attention-meets-post-hoc-interpretability-a","repo_url":"https://github.com/gianluigilopardo/attention_meets_xai","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2402.03485","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.03485"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/gianluigilopardo/attention_meets_xai","reach":null}],"summary":{"ran_draft_wrong":3},"by_repo_kind":{"official":{"samples":3,"ran":3,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":3,"samples":[{"code_sha256_prefix":"5346471696249003","entry":"eval_step","repo":"gianluigilopardo/attention_meets_xai","repo_kind":"official","path":"multi_head_trainer.py","file_url":"https://github.com/gianluigilopardo/attention_meets_xai/blob/HEAD/multi_head_trainer.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5346471696249003"}},{"code_sha256_prefix":"2d34027948842a82","entry":"train_epoch","repo":"gianluigilopardo/attention_meets_xai","repo_kind":"official","path":"multi_head_trainer.py","file_url":"https://github.com/gianluigilopardo/attention_meets_xai/blob/HEAD/multi_head_trainer.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2d34027948842a82"}},{"code_sha256_prefix":"63b9f52bfaf4e99d","entry":"train_step","repo":"gianluigilopardo/attention_meets_xai","repo_kind":"official","path":"multi_head_trainer.py","file_url":"https://github.com/gianluigilopardo/attention_meets_xai/blob/HEAD/multi_head_trainer.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"63b9f52bfaf4e99d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}