{"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/attnlrp-attention-aware-layer-wise-relevance","title":"AttnLRP: Attention-Aware Layer-Wise Relevance Propagation for Transformers","arxiv_id":"2402.05602","date":"2024-02-08","proceeding":null,"authors":["Reduan Achtibat","Sayed Mohammad Vakilzadeh Hatefi","Maximilian Dreyer","Aakriti Jain","Thomas Wiegand","Sebastian Lapuschkin","Wojciech Samek"],"abstract":"Large Language Models are prone to biased predictions and hallucinations, underlining the paramount importance of understanding their model-internal reasoning process. However, achieving faithful attributions for the entirety of a black-box transformer model and maintaining computational efficiency is an unsolved challenge. By extending the Layer-wise Relevance Propagation attribution method to handle attention layers, we address these challenges effectively. While partial solutions exist, our method is the first to faithfully and holistically attribute not only input but also latent representations of transformer models with the computational efficiency similar to a single backward pass. Through extensive evaluations against existing methods on LLaMa 2, Mixtral 8x7b, Flan-T5 and vision transformer architectures, we demonstrate that our proposed approach surpasses alternative methods in terms of faithfulness and enables the understanding of latent representations, opening up the door for concept-based explanations. We provide an LRP library at https://github.com/rachtibat/LRP-eXplains-Transformers.","url_abs":"https://arxiv.org/abs/2402.05602v2","url_pdf":"https://arxiv.org/pdf/2402.05602v2.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":"attnlrp-attention-aware-layer-wise-relevance","repo_url":"https://github.com/rachtibat/lrp-explains-transformers","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"attnlrp-attention-aware-layer-wise-relevance","repo_url":"https://github.com/rachtibat/lrp-for-transformers","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"attribute","task_name":"Attribute"},{"task_slug":"computational-efficiency","task_name":"Computational Efficiency"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"flan-t5","method_name":"Flan-T5"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":null,"method_name":"Library"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"},{"method_slug":"vision-transformer","method_name":"Vision Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2402.05602","atlas_url":"https://app.syntology.ai/?focus=2402.05602","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":"2402.05602"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2402.05602\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2402.05602"},"call":"get_concepts_for_paper(arxiv_id=\"2402.05602\")"}],"by_repo":[{"repo":"rachtibat/lrp-explains-transformers","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2310.01188"],"harvested_for_calls":[{"arxiv_id":"2310.01188","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2310.01188"},"call":"get_harvested_code_for_paper(arxiv_id=\"2310.01188\")"}]},{"repo":"rachtibat/lrp-for-transformers","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","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":"18c746f4f61db24bb808f8a37b6088419688ad0ef708c99bb72702d9b1865ac1","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}