Papers › Lookback Lens: Detecting and Mitigating Contextual Hallucinations in Large Language...

Lookback Lens: Detecting and Mitigating Contextual Hallucinations in Large Language Models Using Only Attention Maps

9 Jul 2024arXiv:2407.07071archive 2025-07-28

Yung-Sung Chuang, Linlu Qiu, Cheng-Yu Hsieh, Ranjay Krishna, Yoon Kim, James Glass

When asked to summarize articles or answer questions given a passage, large language models (LLMs) can hallucinate details and respond with unsubstantiated answers that are inaccurate with respect to the input context. This paper describes a simple approach for detecting such contextual hallucinations. We hypothesize that contextual hallucinations are related to the extent to which an LLM attends to information in the provided context versus its own generations. Based on this intuition, we propose a simple hallucination detection model whose input features are given by the ratio of attention weights on the context versus newly generated tokens (for each attention head). We find that a linear classifier based on these lookback ratio features is as effective as a richer detector that utilizes the entire hidden states of an LLM or a text-based entailment model. The lookback ratio-based detector -- Lookback Lens -- is found to transfer across tasks and even models, allowing a detector that is trained on a 7B model to be applied (without retraining) to a larger 13B model. We further apply this detector to mitigate contextual hallucinations, and find that a simple classifier-guided decoding approach is able to reduce the amount of hallucination, for example by 9.6% in the XSum summarization task.

PaperPDFCodeCode Syntology ranMethod as code

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 20 code samples harvested from 1 repository linked to this paper: 11 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 4 honoured, 0 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 9 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; 3 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 20 samples from 1 repository, 11 ran (7 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.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

voidism/lookback-lens officialmentioned in papermentioned on GitHubjaxSyntology: 20 samples, 11 ran (4 instrument-failed) · 9 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

20 samples harvested: 11 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 4 honoured, 0 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 9 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.

4ran · honoured contract
1ran · our draft was wrong
3ran; the contract check could not run
3ran
9unverified

Licence: 20 of the 20 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from voidism/lookback-lens. “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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

voidism/lookback-lens official repository 20 samples, 11 ran (4 instrument-failed) · 9 unverified
best_subspan_em in 6 papers eval_exact_match.py ran · honoured contract no licence file found · pointer only · 10af7cdbc53df7e5 · report fixture: signature prediction:str/0/str, ground_truths:list/1/str · returned float · level recorded 2026-09-24
convert_to_token_level step03_lookback_lens.py ran no licence file found · pointer only · f10a909a93d528cf · report fixture: signature lookback_tensor:list/1/Tensor, labels:list/1/Tensor, sliding_window:int/0/int, sequential:bool/0/bool, min_pool_target:bool/0/bool · returned tuple · level recorded 2026-09-24
extract_time_series_features step03_lookback_lens.py ran; the contract check could not run (RAISES) · metamorphic tier: deterministic no licence file found · pointer only · e6ade772c4fc8437 · report fixture: signature lookback_tensor:list/1/Tensor · returned tuple · level recorded 2026-09-22
gelu_fast in 39 papers transformers-4.32.0/src/transformers/activations_tf.py ran · honoured contract fingerprinted no licence file found · pointer only · 37a5eed2dbd663ca · report fixture: signature x:EagerTensor/2/float · returned EagerTensor · level recorded 2026-09-26
get_config_class_from_processor_class in 29 papers transformers-4.32.0/utils/create_dummy_models.py ran; the contract check could not run (RAISES) no licence file found · pointer only · 3d999b95009c7537 · report fixture: signature processor_class:callable/0/? · returned type · level recorded 2026-09-25
get_processor_types_from_config_class in 29 papers transformers-4.32.0/utils/create_dummy_models.py ran; the contract check could not run (RAISES) no licence file found · pointer only · 0c0b81b081919d8e · report fixture: signature config_class:callable/0/?, allowed_mappings:list/1/str · returned tuple · level recorded 2026-09-25
load_nq_open eval_exact_match.py ran no licence file found · pointer only · 746e55bc216a6a60 · report fixture: signature file_path:str/0/str, parallel:bool/0/bool, total_shard:int/0/int, shard_id:int/0/int, debug:bool/0/bool, data_type:str/0/str, subsample:NoneType/0/? · returned list · level recorded 2026-09-24
load_summarization step02_eval_gpt4o.py ran no licence file found · pointer only · 491bdf9d170e0f42 · report fixture: signature file_path:str/0/str, parallel:bool/0/bool, total_shard:int/0/int, shard_id:int/0/int, debug:bool/0/bool, data_type:str/0/str, subsample:NoneType/0/? · returned dict · level recorded 2026-09-24
mish in 95 papers
census: 5 implementations from 8 papers, 1 distinct output on one shared input
transformers-4.32.0/src/transformers/activations_tf.py ran · honoured contract no licence file found · pointer only · cc8c8c3ebf0c343f · report fixture: signature x:ndarray/2/float · returned EagerTensor · level recorded 2026-09-26
normalize_answer in 304 papers eval_exact_match.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 9706a9a0b961096b · report fixture: signature s:str/0/str · returned str · level recorded 2026-09-26
quick_gelu in 43 papers transformers-4.32.0/src/transformers/activations_tf.py ran · honoured contract fingerprinted no licence file found · pointer only · e2d56cb91f999bef · report fixture: signature x:EagerTensor/2/float · returned EagerTensor · level recorded 2026-09-26
get_architectures_from_config_class in 29 papers transformers-4.32.0/utils/create_dummy_models.py unverified no licence file found · pointer only · b176efb26f72e507 · report
load_jsonl in 179 papers step02_eval_gpt4o.py unverified no licence file found · pointer only · 93fb30bbe389d023 · report
load_nq_open step01_extract_attns.py unverified no licence file found · pointer only · 124e3218c2d64455 · report
load_nq_open step02_eval_gpt4o.py unverified no licence file found · pointer only · 3abd09dee278805a · report
load_nq_open step04_run_decoding.py unverified no licence file found · pointer only · d10fb7dd76f75e3b · report
num_tokens_from_message step01_extract_attns.py unverified no licence file found · pointer only · b3a67ee5030c2ffe · report
num_tokens_from_message step04_run_decoding.py unverified no licence file found · pointer only · aba17adf1edf4960 · report
truncate_message step01_extract_attns.py unverified no licence file found · pointer only · 00d2f6a6c8b0f564 · report
truncate_message step04_run_decoding.py unverified no licence file found · pointer only · 0eaabf1df4cdff46 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for Lookback Lens (graph method: Lookback Lens). 1 brick; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

  1. extract_time_series_features entry · level 1 · ran; the contract check could not run (RAISES) · e6ade772c4fc8437

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2407.07071") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

ArticlesHallucination

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