Papers › HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination and...

HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language Models

23 Oct 2023CVPR 2024 1arXiv:2310.14566archive 2025-07-28

Tianrui Guan, Fuxiao Liu, Xiyang Wu, Ruiqi Xian, Zongxia Li, Xiaoyu Liu, Xijun Wang, Lichang Chen, Furong Huang, Yaser Yacoob, Dinesh Manocha, Tianyi Zhou

We introduce HallusionBench, a comprehensive benchmark designed for the evaluation of image-context reasoning. This benchmark presents significant challenges to advanced large visual-language models (LVLMs), such as GPT-4V(Vision), Gemini Pro Vision, Claude 3, and LLaVA-1.5, by emphasizing nuanced understanding and interpretation of visual data. The benchmark comprises 346 images paired with 1129 questions, all meticulously crafted by human experts. We introduce a novel structure for these visual questions designed to establish control groups. This structure enables us to conduct a quantitative analysis of the models' response tendencies, logical consistency, and various failure modes. In our evaluation on HallusionBench, we benchmarked 15 different models, highlighting a 31.42% question-pair accuracy achieved by the state-of-the-art GPT-4V. Notably, all other evaluated models achieve accuracy below 16%. Moreover, our analysis not only highlights the observed failure modes, including language hallucination and visual illusion, but also deepens an understanding of these pitfalls. Our comprehensive case studies within HallusionBench shed light on the challenges of hallucination and illusion in LVLMs. Based on these insights, we suggest potential pathways for their future improvement. The benchmark and codebase can be accessed at https://github.com/tianyi-lab/HallusionBench.

PaperPDFConference PDFCodeCode 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 8 code samples harvested from 3 repositories linked to this paper: 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 1 sample from 1 repository, 1 ran (1 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 7 samples from 2 repositories, 3 ran (2 with no instrument failure; 1 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 4 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

tianyi-lab/hallusionbench officialmentioned in papermentioned on GitHubBSD-3-ClauseSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
FuxiaoLiu/LRV-Instruction mentioned on GitHubpytorchBSD-3-ClauseSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to MMC: Advancing Multimodal Chart Understanding with Large-scale Instruction Tuning (arXiv:2311.10774; that paper's own run record: 14 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 2 violated, 6 with no contract checked; 5 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
FuxiaoLiu/VisualNews-Repository mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to MMC: Advancing Multimodal Chart Understanding with Large-scale Instruction Tuning (arXiv:2311.10774; that paper's own run record: 14 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 2 violated, 6 with no contract checked; 5 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
dongping-chen/mllm-as-a-judge mentioned on GitHubpytorchSyntology: not harvested report
fuxiaoliu/mmc mentioned on GitHubpytorchGPL-3.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to MMC: Advancing Multimodal Chart Understanding with Large-scale Instruction Tuning (arXiv:2311.10774; that paper's own run record: 14 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 2 violated, 6 with no contract checked; 5 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
wuxiyang1996/AutoHallusion mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
zli12321/qa_metrics mentioned on GitHubMITSyntology: 6 samples, 2 ran (0 instrument-failed) · 4 unverified report
zli12321/videohallu mentioned on GitHubpytorchSyntology: not harvested report
codelion/adaptive-classifier pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Overcoming catastrophic forgetting in neural networks (arXiv:1612.00796; that paper's own run record: 16 ran (of which 8 constructed an object rather than computing a result; 12 with no instrument failure: 2 honoured, 0 violated, 10 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified) and Transformer-Squared: Self-adaptive LLMs (arXiv:2501.06252; that paper's own run record: 6 ran (of which 1 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. 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

8 samples harvested: 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · violated contract
1ran · our draft was wrong
2ran
4unverified

Licence: 1 of the 8 samples is 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 3 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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.

tianyi-lab/hallusionbench official repository 1 sample, 1 ran (0 instrument-failed) · 0 unverified
generate_answer in 12 papers evaluation.py ran · violated contract BSD-3-Clause (permissive) · c5e2fa32f54d0bba · report fixture: signature data:dict/0/?, model_output_entry:dict/0/? · returned dict · level recorded 2026-09-22
wuxiyang1996/AutoHallusion community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
path_header_replace main_abnormal_obj_insertion.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 1c0fbbfc151cff32 · report fixture: signature path:str/0/str, new_header:str/0/str, case_id:str/0/str · returned str · level recorded 2026-09-22
zli12321/qa_metrics community (archive-listed) 6 samples, 2 ran (0 instrument-failed) · 4 unverified
f1_score_with_precision_recall_normalized qa_metrics/f1.py ran fingerprinted MIT (permissive) · 8e34f912950b0c10 · report fixture: signature reference:str/0/str, candidate:str/0/str · returned dict · level recorded 2026-09-24
get_score in 56 papers qa_metrics/RewardBert.py ran MIT (permissive) · bb06d405aa0fd21d · report fixture: signature model:callable/0/?, tokenizer:callable/0/?, reference:str/0/str, generated_response:str/0/str, device:device/0/?, max_length:int/0/int · returned tuple · level recorded 2026-09-24
em_match qa_metrics/em.py unverified MIT (permissive) · 630c8505ee831159 · report
f1_score in 121 papers qa_metrics/f1.py unverified MIT (permissive) · 032dc5fee649f52c · report
f1_score_with_precision_recall qa_metrics/f1.py unverified MIT (permissive) · 71a1ffe945841c01 · report
load_model_and_tokenizer_from_hub qa_metrics/RewardBert.py unverified MIT (permissive) · 4aa1be5727c48a7d · report

Tasks

DiagnosticHallucinationHallucination EvaluationVisual Question Answering (VQA)

Datasets

Introduced by this paper, per the archive.

HallusionBench

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Visual Question Answering (VQA) HallusionBench GPT-4V Question Pair Acc 12.2047 #1 of 4 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

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