{"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/mudaf-long-context-multi-document-attention","title":"MuDAF: Long-Context Multi-Document Attention Focusing through Contrastive Learning on Attention Heads","arxiv_id":"2502.13963","date":"2025-02-19","proceeding":null,"authors":["Weihao Liu","Ning Wu","Shiping Yang","Wenbiao Ding","Shining Liang","Ming Gong","Dongmei Zhang"],"abstract":"Large Language Models (LLMs) frequently show distracted attention due to irrelevant information in the input, which severely impairs their long-context capabilities. Inspired by recent studies on the effectiveness of retrieval heads in long-context factutality, we aim at addressing this distraction issue through improving such retrieval heads directly. We propose Multi-Document Attention Focusing (MuDAF), a novel method that explicitly optimizes the attention distribution at the head level through contrastive learning. According to the experimental results, MuDAF can significantly improve the long-context question answering performance of LLMs, especially in multi-document question answering. Extensive evaluations on retrieval scores and attention visualizations show that MuDAF possesses great potential in making attention heads more focused on relevant information and reducing attention distractions.","url_abs":"https://arxiv.org/abs/2502.13963v1","url_pdf":"https://arxiv.org/pdf/2502.13963v1.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":"mudaf-long-context-multi-document-attention","repo_url":"https://github.com/NeosKnight233/MuDAF","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2502.13963","atlas_url":"https://app.syntology.ai/?focus=2502.13963","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.13963"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2502.13963"},"returns":"the samples harvested from this paper, each with its run record; it does not verify the paper"},{"tool":"get_code","arguments_in":"samples[].code_sha256","returns":"one stored sample by its code_sha256; not shown on this site"}]},"developers":"https://syntology.ai/developers","held":true,"reason":"in_graph_layer","checked_against":null,"agent_calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2502.13963"},"call":"get_harvested_code_for_paper(arxiv_id=\"2502.13963\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"2502.13963"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2502.13963\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2502.13963"},"call":"get_concepts_for_paper(arxiv_id=\"2502.13963\")"}],"by_repo":[{"repo":"NeosKnight233/MuDAF","kind":"official","samples":14,"ran":9,"instrument":4,"unverified":5}],"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","read_at":"2026-10-05T00:36:11+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","ran_record":{"url":"https://syntology.ai/api/ran/2502.13963.json","schema":"syntology.ran_record/1","counts_crosswalk":{"n_samples":"syntology.counts.lifted","n_ran":"syntology.counts.executed","n_ran_checked":"syntology.counts.checked","n_instrument":"syntology.counts.instrument_failures","n_unverified":"syntology.counts.no_recorded_run"},"note":"live record, measured at request time; may be newer than this page's graph read","badge":"https://syntology.ai/api/ran/2502.13963.svg"},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/NeosKnight233/MuDAF","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":4,"ran_draft_wrong":4,"ran_honours":1,"unverified":5},"n_samples":14,"n_ran":9,"n_constructed":0,"n_ran_checked":5,"n_instrument":4,"n_unverified":5,"n_instrument_is":"failures of Syntology's instrument, not of the code","every_run_is_an_instrument_failure":false,"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"by_repo_kind":{"official":{"samples":14,"ran":9,"n_ran_checked":5,"n_instrument":4,"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":7,"inline_ok_is":"inline_ok is true only when both licence gates allow Syntology to serve this code's text: this paper's link (inline_ok_link, from the licence of this paper's copy) and the stored copy of the same code that Syntology serves, which may have been first harvested from another repository. withheld_clause is Syntology's own wording of which gate keeps the text a pointer and why, and is null when inline_ok is true. This site shows no code text either way; n_pointer_only_for_licence counts samples with inline_ok false (both gates), n_pointer_only_link_allows those of them whose inline_ok_link is true","n_pointer_only_link_allows":7,"fixture_fields_is":{"signature_and_fixture_out_type":"the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right","level_recorded_at":"when Syntology's graph wrote the sample's verification level, not when the code executed; absent where the level was written before the date was kept, and never filled in with the build date","present_on":"samples that ran only; a key is absent, never empty, where the graph records nothing"},"n_ran_with_level_date":9,"n_ran_without_level_date":0,"n_ran_signature_not_shown":0,"levels_written_between":{"first":"2026-09-24","last":"2026-09-25","is":"the first and last UTC dates on which Syntology's graph wrote a verification level for a sample on this page that ran, not when the code executed"},"code_page_min_papers":5,"code_page_is":"a page for the entry name across every paper's harvested code; the name is a string, not an identity","samples":[{"code_sha256":"a263b94a95ef749c","code_sha256_prefix":"a263b94a95ef749c","entry":"get_imports","repo":"NeosKnight233/MuDAF","repo_kind":"official","path":"transformers/dynamic_module_utils.py","file_url":"https://github.com/NeosKnight233/MuDAF/blob/HEAD/transformers/dynamic_module_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"filename:str/0/str","fixture_out_type":"list","level_recorded_at":"2026-09-24T23:25:36.931776+00:00","code_page":"/code/get-imports","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"a263b94a95ef749c"}},{"code_sha256":"518f6a89865f25d2","code_sha256_prefix":"518f6a89865f25d2","entry":"get_relative_import_files","repo":"NeosKnight233/MuDAF","repo_kind":"official","path":"transformers/dynamic_module_utils.py","file_url":"https://github.com/NeosKnight233/MuDAF/blob/HEAD/transformers/dynamic_module_utils.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"module_file:str/0/str","fixture_out_type":"list","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":"/code/get-relative-import-files","census":null,"licence":"Apache-2.0","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from JD-GenX/Uni-AdGen, and GitHub detected no licence in that repository when it was checked","mcp_get_code":{"code_sha256":"518f6a89865f25d2"}},{"code_sha256":"4af5faa701d0f2c9","code_sha256_prefix":"4af5faa701d0f2c9","entry":"get_relative_imports","repo":"NeosKnight233/MuDAF","repo_kind":"official","path":"transformers/dynamic_module_utils.py","file_url":"https://github.com/NeosKnight233/MuDAF/blob/HEAD/transformers/dynamic_module_utils.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"module_file:str/0/str","fixture_out_type":"list","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":"/code/get-relative-imports","census":null,"licence":"Apache-2.0","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from JD-GenX/Uni-AdGen, and GitHub detected no licence in that repository when it was checked","mcp_get_code":{"code_sha256":"4af5faa701d0f2c9"}},{"code_sha256":"dd8f7751ef859581","code_sha256_prefix":"dd8f7751ef859581","entry":"infer_metric_tags_from_eval_results","repo":"NeosKnight233/MuDAF","repo_kind":"official","path":"transformers/modelcard.py","file_url":"https://github.com/NeosKnight233/MuDAF/blob/HEAD/transformers/modelcard.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"eval_results:dict/0/?","fixture_out_type":"dict","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":"/code/infer-metric-tags-from-eval-results","census":null,"licence":"Apache-2.0","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from shen8424/CORE, and GitHub detected no licence in that repository when it was checked","mcp_get_code":{"code_sha256":"dd8f7751ef859581"}},{"code_sha256":"e6632a5722f0840d","code_sha256_prefix":"e6632a5722f0840d","entry":"parse_keras_history","repo":"NeosKnight233/MuDAF","repo_kind":"official","path":"transformers/modelcard.py","file_url":"https://github.com/NeosKnight233/MuDAF/blob/HEAD/transformers/modelcard.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"logs:KerasHistory/0/?","fixture_out_type":"tuple","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":"/code/parse-keras-history","census":null,"licence":"Apache-2.0","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from shen8424/CORE, and GitHub detected no licence in that repository when it was checked","mcp_get_code":{"code_sha256":"e6632a5722f0840d"}},{"code_sha256":"a77b72cc8d5c90f0","code_sha256_prefix":"a77b72cc8d5c90f0","entry":"prepare_fa2_from_position_ids","repo":"NeosKnight233/MuDAF","repo_kind":"official","path":"transformers/modeling_flash_attention_utils.py","file_url":"https://github.com/NeosKnight233/MuDAF/blob/HEAD/transformers/modeling_flash_attention_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"query:Tensor/4/float, key:Tensor/4/float, value:Tensor/4/float, position_ids:Tensor/2/int","fixture_out_type":"tuple","level_recorded_at":"2026-09-25T23:53:12.863503+00:00","code_page":"/code/prepare-fa2-from-position-ids","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"a77b72cc8d5c90f0"}},{"code_sha256":"a66d2b78670c85e1","code_sha256_prefix":"a66d2b78670c85e1","entry":"quick_gelu","repo":"NeosKnight233/MuDAF","repo_kind":"official","path":"transformers/modeling_flax_utils.py","file_url":"https://github.com/NeosKnight233/MuDAF/blob/HEAD/transformers/modeling_flax_utils.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"x:ArrayImpl/2/float","fixture_out_type":"ArrayImpl","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","retrieve_with":{"tool":"get_code","code_sha256":"a66d2b78670c85e1"},"code_page":"/code/quick-gelu","census":null,"licence":"Apache-2.0","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from shen8424/CORE, and GitHub detected no licence in that repository when it was checked","mcp_get_code":{"code_sha256":"a66d2b78670c85e1"}},{"code_sha256":"30d50ff2ced6b7a3","code_sha256_prefix":"30d50ff2ced6b7a3","entry":"rename_key_and_reshape_tensor","repo":"NeosKnight233/MuDAF","repo_kind":"official","path":"transformers/modeling_flax_pytorch_utils.py","file_url":"https://github.com/NeosKnight233/MuDAF/blob/HEAD/transformers/modeling_flax_pytorch_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"pt_tuple_key:tuple/1/str, pt_tensor:ndarray/2/float, random_flax_state_dict:dict/0/?, model_prefix:str/0/str","fixture_out_type":"tuple","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":"/code/rename-key-and-reshape-tensor","census":null,"licence":"Apache-2.0","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from shen8424/CORE, and GitHub detected no licence in that repository when it was checked","mcp_get_code":{"code_sha256":"30d50ff2ced6b7a3"}},{"code_sha256":"bb3c4ecbbdf8a9c1","code_sha256_prefix":"bb3c4ecbbdf8a9c1","entry":"reverse_permute_weights","repo":"NeosKnight233/MuDAF","repo_kind":"official","path":"transformers/modeling_gguf_pytorch_utils.py","file_url":"https://github.com/NeosKnight233/MuDAF/blob/HEAD/transformers/modeling_gguf_pytorch_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"weights:ndarray/2/float, n_head:int/0/int, num_kv_heads:NoneType/0/?","fixture_out_type":"ndarray","level_recorded_at":"2026-09-25T16:13:10.526492+00:00","code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"bb3c4ecbbdf8a9c1"}},{"code_sha256":"8518c46881e53b67","code_sha256_prefix":"8518c46881e53b67","entry":"convert_pytorch_state_dict_to_flax","repo":"NeosKnight233/MuDAF","repo_kind":"official","path":"transformers/modeling_flax_pytorch_utils.py","file_url":"https://github.com/NeosKnight233/MuDAF/blob/HEAD/transformers/modeling_flax_pytorch_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/convert-pytorch-state-dict-to-flax","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"8518c46881e53b67"}},{"code_sha256":"5e01aab2a01fb6db","code_sha256_prefix":"5e01aab2a01fb6db","entry":"dtype_byte_size","repo":"NeosKnight233/MuDAF","repo_kind":"official","path":"transformers/modeling_flax_utils.py","file_url":"https://github.com/NeosKnight233/MuDAF/blob/HEAD/transformers/modeling_flax_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/dtype-byte-size","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"5e01aab2a01fb6db"}},{"code_sha256":"80d41fe6d81de3dd","code_sha256_prefix":"80d41fe6d81de3dd","entry":"flax_shard_checkpoint","repo":"NeosKnight233/MuDAF","repo_kind":"official","path":"transformers/modeling_flax_utils.py","file_url":"https://github.com/NeosKnight233/MuDAF/blob/HEAD/transformers/modeling_flax_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/flax-shard-checkpoint","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"80d41fe6d81de3dd"}},{"code_sha256":"ec7b1528a936234d","code_sha256_prefix":"ec7b1528a936234d","entry":"is_hf_dataset","repo":"NeosKnight233/MuDAF","repo_kind":"official","path":"transformers/modelcard.py","file_url":"https://github.com/NeosKnight233/MuDAF/blob/HEAD/transformers/modelcard.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/is-hf-dataset","census":null,"licence":"Apache-2.0","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from shen8424/CORE, and GitHub detected no licence in that repository when it was checked","mcp_get_code":{"code_sha256":"ec7b1528a936234d"}},{"code_sha256":"befefbd3afa0731c","code_sha256_prefix":"befefbd3afa0731c","entry":"read_field","repo":"NeosKnight233/MuDAF","repo_kind":"official","path":"transformers/modeling_gguf_pytorch_utils.py","file_url":"https://github.com/NeosKnight233/MuDAF/blob/HEAD/transformers/modeling_gguf_pytorch_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/read-field","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"befefbd3afa0731c"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"3df498a222069ac37e2bc73dbd43b948dcaf5bc33775a0c7d43d5662c81f6e84","record_changed_at":"2026-10-04","record_changed_at_basis":"changed"}