{"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/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":{"atlas_url":"https://app.syntology.ai/?focus=2502.13963","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.13963"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/NeosKnight233/MuDAF","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":6,"unverified":8},"by_repo_kind":{"official":{"samples":14,"ran":6,"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":0,"samples":[{"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","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"518f6a89865f25d2"}},{"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","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4af5faa701d0f2c9"}},{"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","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"dd8f7751ef859581"}},{"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","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e6632a5722f0840d"}},{"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","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a66d2b78670c85e1"}},{"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,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"30d50ff2ced6b7a3"}},{"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,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8518c46881e53b67"}},{"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,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5e01aab2a01fb6db"}},{"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,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"80d41fe6d81de3dd"}},{"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":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a263b94a95ef749c"}},{"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,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ec7b1528a936234d"}},{"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":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a77b72cc8d5c90f0"}},{"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,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"befefbd3afa0731c"}},{"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":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bb3c4ecbbdf8a9c1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}