Papers › HaluEval: A Large-Scale Hallucination Evaluation Benchmark for Large Language Models

HaluEval: A Large-Scale Hallucination Evaluation Benchmark for Large Language Models

19 May 2023arXiv:2305.11747archive 2025-07-28

Junyi Li, Xiaoxue Cheng, Wayne Xin Zhao, Jian-Yun Nie, Ji-Rong Wen

Large language models (LLMs), such as ChatGPT, are prone to generate hallucinations, i.e., content that conflicts with the source or cannot be verified by the factual knowledge. To understand what types of content and to which extent LLMs are apt to hallucinate, we introduce the Hallucination Evaluation benchmark for Large Language Models (HaluEval), a large collection of generated and human-annotated hallucinated samples for evaluating the performance of LLMs in recognizing hallucination. To generate these samples, we propose a ChatGPT-based two-step framework, i.e., sampling-then-filtering. Besides, we also hire some human labelers to annotate the hallucinations in ChatGPT responses. The empirical results suggest that ChatGPT is likely to generate hallucinated content in specific topics by fabricating unverifiable information (i.e., about 19.5% responses). Moreover, existing LLMs face great challenges in recognizing the hallucinations in texts. However, our experiments also prove that providing external knowledge or adding reasoning steps can help LLMs recognize hallucinations. Our benchmark can be accessed at https://github.com/RUCAIBox/HaluEval.

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 12 code samples harvested from 2 repositories linked to this paper: 8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 12 samples from 2 repositories, 8 ran (5 with no instrument failure; 3 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.

RUCAIBox/HaluEval officialmentioned in papermentioned on GitHubSyntology: 3 samples, 3 ran (3 instrument-failed) · 0 unverified report
rucaibox/helma officialmentioned in papermentioned on GitHubMITSyntology: 9 samples, 5 ran (0 instrument-failed) · 4 unverified report
IAAR-Shanghai/UHGEval Apache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to UHGEval: Benchmarking the Hallucination of Chinese Large Language Models via... (arXiv:2311.15296; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 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

12 samples harvested: 8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 3 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.

3ran · our draft was wrong
5ran
4unverified

Licence: 1 of the 12 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, 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 2 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.

RUCAIBox/HaluEval official repository 3 samples, 3 ran (3 instrument-failed) · 0 unverified
load_dialog analysis/analyze.py ran · our draft was wrong MIT (permissive) · 295b8779d73be38d · report fixture: signature filename:str/0/str · returned tuple · level recorded 2026-09-22
load_qa analysis/analyze.py ran · our draft was wrong MIT (permissive) · 73f3dd95883037cc · report fixture: signature filename:str/0/str · returned tuple · level recorded 2026-09-22
load_summary analysis/analyze.py ran · our draft was wrong MIT (permissive) · 3bd42cb5b14b2cad · report fixture: signature filename:str/0/str · returned tuple · level recorded 2026-09-22
rucaibox/helma official repository 9 samples, 5 ran (0 instrument-failed) · 4 unverified
get_dialogue_res generation/filtering.py ran MIT (permissive) · f698390b537e4d97 · report fixture: signature knowledge:str/0/str, dialog:str/0/str, response1:str/0/str, response2:str/0/str, instruction:str/0/str · returned str · level recorded 2026-09-26
get_dialogue_res generation/generate.py ran MIT (permissive) · 211e2e141467c8dd · report fixture: signature knowledge:str/0/str, dialog:str/0/str, response:str/0/str, instruction:str/0/str · returned str · level recorded 2026-09-26
get_dialogue_response evaluation/evaluate.py ran MIT (permissive) · bf66b0debbe71c7e · report fixture: signature model:str/0/str, dialog:str/0/str, response:str/0/str, instruction:str/0/str · returned str · level recorded 2026-09-26
get_qa_res generation/generate.py ran MIT (permissive) · 409dd3a84718a20b · report fixture: signature knowledge:str/0/str, question:str/0/str, answer:str/0/str, instruction:str/0/str · returned str · level recorded 2026-09-26
get_qa_response evaluation/evaluate.py ran MIT (permissive) · 71b0706abb4deccb · report fixture: signature model:str/0/str, question:str/0/str, answer:str/0/str, instruction:str/0/str · returned str · level recorded 2026-09-26
get_qa_res generation/filtering.py unverified MIT (permissive) · 57cf187fae039bc2 · report
get_summarization_res generation/filtering.py unverified MIT (permissive) · be0c5c938e7e424c · report
get_summarization_res generation/generate.py unverified MIT (permissive) · f92a9ea55882aef2 · report
num_tokens_from_message evaluation/evaluate.py unverified MIT (permissive) here; the stored copy is pointer only · b3a67ee5030c2ffe · report

Tasks

HallucinationHallucination Evaluation

Datasets

Introduced by this paper, per the archive.

HaluEval

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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