Papers › MuDAF: Long-Context Multi-Document Attention Focusing through Contrastive Learning on...

MuDAF: Long-Context Multi-Document Attention Focusing through Contrastive Learning on Attention Heads

19 Feb 2025arXiv:2502.13963archive 2025-07-28

Weihao Liu, Ning Wu, Shiping Yang, Wenbiao Ding, Shining Liang, Ming Gong, Dongmei Zhang

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.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 14 code samples harvested from 1 repository linked to this paper: 9 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 4 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 14 samples from 1 repository, 9 ran (5 with no instrument failure; 4 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-24 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

NeosKnight233/MuDAF officialmentioned on GitHubjaxApache-2.0Syntology: 14 samples, 9 ran (4 instrument-failed) · 5 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

14 samples harvested: 9 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 4 where Syntology's instrument failed) · 5 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
4ran · our draft was wrong
4ran
5unverified

Licence: 7 of the 14 samples are pointer only, meaning Syntology does not serve that copy's text. For 7 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from NeosKnight233/MuDAF. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives 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” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

NeosKnight233/MuDAF official repository 14 samples, 9 ran (4 instrument-failed) · 5 unverified
get_imports in 16 papers transformers/dynamic_module_utils.py ran Apache-2.0 (permissive) · a263b94a95ef749c · report fixture: signature filename:str/0/str · returned list · level recorded 2026-09-24
get_relative_import_files in 28 papers transformers/dynamic_module_utils.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · 518f6a89865f25d2 · report fixture: signature module_file:str/0/str · returned list · level recorded 2026-09-24
get_relative_imports in 28 papers transformers/dynamic_module_utils.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · 4af5faa701d0f2c9 · report fixture: signature module_file:str/0/str · returned list · level recorded 2026-09-24
infer_metric_tags_from_eval_results in 20 papers transformers/modelcard.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · dd8f7751ef859581 · report fixture: signature eval_results:dict/0/? · returned dict · level recorded 2026-09-24
parse_keras_history in 19 papers transformers/modelcard.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · e6632a5722f0840d · report fixture: signature logs:KerasHistory/0/? · returned tuple · level recorded 2026-09-24
prepare_fa2_from_position_ids in 15 papers transformers/modeling_flash_attention_utils.py ran Apache-2.0 (permissive) · a77b72cc8d5c90f0 · report fixture: signature query:Tensor/4/float, key:Tensor/4/float, value:Tensor/4/float, position_ids:Tensor/2/int · returned tuple · level recorded 2026-09-25
quick_gelu in 43 papers transformers/modeling_flax_utils.py ran · honoured contract fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · a66d2b78670c85e1 · report fixture: signature x:ArrayImpl/2/float · returned ArrayImpl · level recorded 2026-09-24
rename_key_and_reshape_tensor in 22 papers transformers/modeling_flax_pytorch_utils.py ran Apache-2.0 (permissive) here; the stored copy is pointer only · 30d50ff2ced6b7a3 · report fixture: signature pt_tuple_key:tuple/1/str, pt_tensor:ndarray/2/float, random_flax_state_dict:dict/0/?, model_prefix:str/0/str · returned tuple · level recorded 2026-09-24
reverse_permute_weights transformers/modeling_gguf_pytorch_utils.py ran Apache-2.0 (permissive) · bb3c4ecbbdf8a9c1 · report fixture: signature weights:ndarray/2/float, n_head:int/0/int, num_kv_heads:NoneType/0/? · returned ndarray · level recorded 2026-09-25
convert_pytorch_state_dict_to_flax in 21 papers transformers/modeling_flax_pytorch_utils.py unverified Apache-2.0 (permissive) · 8518c46881e53b67 · report
dtype_byte_size in 15 papers transformers/modeling_flax_utils.py unverified Apache-2.0 (permissive) · 5e01aab2a01fb6db · report
flax_shard_checkpoint in 15 papers transformers/modeling_flax_utils.py unverified Apache-2.0 (permissive) · 80d41fe6d81de3dd · report
is_hf_dataset in 20 papers transformers/modelcard.py unverified Apache-2.0 (permissive) here; the stored copy is pointer only · ec7b1528a936234d · report
read_field in 6 papers transformers/modeling_gguf_pytorch_utils.py unverified Apache-2.0 (permissive) · befefbd3afa0731c · report

Tasks

Contrastive LearningQuestion AnsweringRetrieval

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AttentionSoftmax

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections