Papers › FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation

FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation

23 May 2023arXiv:2305.14251archive 2025-07-28

Sewon Min, Kalpesh Krishna, Xinxi Lyu, Mike Lewis, Wen-tau Yih, Pang Wei Koh, Mohit Iyyer, Luke Zettlemoyer, Hannaneh Hajishirzi

Evaluating the factuality of long-form text generated by large language models (LMs) is non-trivial because (1) generations often contain a mixture of supported and unsupported pieces of information, making binary judgments of quality inadequate, and (2) human evaluation is time-consuming and costly. In this paper, we introduce FACTSCORE, a new evaluation that breaks a generation into a series of atomic facts and computes the percentage of atomic facts supported by a reliable knowledge source. We conduct an extensive human evaluation to obtain FACTSCOREs of people biographies generated by several state-of-the-art commercial LMs -- InstructGPT, ChatGPT, and the retrieval-augmented PerplexityAI -- and report new analysis demonstrating the need for such a fine-grained score (e.g., ChatGPT only achieves 58%). Since human evaluation is costly, we also introduce an automated model that estimates FACTSCORE using retrieval and a strong language model, with less than a 2% error rate. Finally, we use this automated metric to evaluate 6,500 generations from a new set of 13 recent LMs that would have cost $26K if evaluated by humans, with various findings: GPT-4 and ChatGPT are more factual than public models, and Vicuna and Alpaca are some of the best public models. FACTSCORE is available for public use via `pip install factscore`.

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 15 code samples harvested from 2 repositories linked to this paper: 11 ran (of which 1 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 3 violated, 4 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 1 repository, 10 ran (7 with no instrument failure; 3 where Syntology's instrument failed); community (archive-listed): 3 samples from 1 repository, 1 ran (1 with no instrument failure; 0 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 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

shmsw25/factscore officialmentioned in papermentioned on GitHubpytorchMITSyntology: 12 samples, 10 ran (3 instrument-failed) · 2 unverified report
d223302/merging-facts-crafting-fallacies mentioned on GitHubSyntology: not harvested report
freshllms/freshqa mentioned on GitHubApache-2.0Syntology: not harvested report
tatsu-lab/linguistic_calibration mentioned on GitHubpytorchSyntology: 3 samples, 1 ran (0 instrument-failed) · 2 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

15 samples harvested: 11 ran (of which 1 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 3 violated, 4 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 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
3ran · violated contract
3ran · our draft was wrong
4ran
4unverified

Licence: 6 of the 15 samples are pointer only, meaning Syntology does not serve that copy's text. For 6 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 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.

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.

shmsw25/factscore official repository 12 samples, 10 ran (3 instrument-failed) · 2 unverified
best_demos in 6 papers factscore/atomic_facts.py ran MIT (permissive) here; the stored copy is pointer only · 510528f4db1006bc · report fixture: signature query:str/0/str, bm25:BM25Okapi/0/?, demons_sents:list/1/str, k:int/0/int · returned list · level recorded 2026-09-24
call_ChatGPT factscore/openai_lm.py ran MIT (permissive) · 6c0eab0d68ea3036 · report fixture: signature message:list/1/dict, model_name:str/0/str, max_len:int/0/int, temp:float/0/float, verbose:bool/0/bool · returned dict · level recorded 2026-09-24
call_GPT3 factscore/openai_lm.py ran MIT (permissive) · e5bb87d92ea99a8b · report fixture: signature prompt:str/0/str, model_name:str/0/str, max_len:int/0/int, temp:float/0/float, num_log_probs:int/0/int, echo:bool/0/bool, verbose:bool/0/bool · returned dict · level recorded 2026-09-24
get_memory_footprint in 5 papers factscore/utils.py ran · honoured contract MIT (permissive) · f06c53e363e1ebaa · report fixture: signature model:callable/0/?, return_buffers:bool/0/bool · returned int · level recorded 2026-09-24
is_invalid_paragraph_ppl in 7 papers factscore/abstain_detection.py ran · violated contract MIT (permissive) here; the stored copy is pointer only · 8eb846a8e76a79b8 · report fixture: signature text:str/0/str · returned bool · level recorded 2026-09-24
is_invalid_ppl in 7 papers factscore/abstain_detection.py ran · violated contract MIT (permissive) here; the stored copy is pointer only · 672bd38d830be48d · report fixture: signature text:str/0/str · returned bool · level recorded 2026-09-24
normalize_answer in 304 papers factscore/atomic_facts.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · 6a96435eba311b08 · report fixture: signature s:str/0/str · returned str · level recorded 2026-09-22
remove_citation in 7 papers factscore/abstain_detection.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · 3635046105ae0fce · report fixture: signature text:str/0/str · returned str · level recorded 2026-09-24
softmax in 240 papers
census: 53 implementations from 63 papers, 16 distinct outputs across 8 buckets, one shared input per bucket
factscore/npm.py ran · violated contract fingerprinted MIT (permissive) · 925c59b7e44138ab · report fixture: signature x:ndarray/1/float · returned ndarray · level recorded 2026-09-25
text_to_sentences in 7 papers factscore/atomic_facts.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · 13867f872a481bd3 · report fixture: signature text:str/0/str · returned list · level recorded 2026-09-24
convert_model_to_int8_on_gpu factscore/utils.py unverified MIT (permissive) · 7e4c366c4dbf9568 · report
recover_instruct_llama in 5 papers factscore/download_data.py unverified MIT (permissive) · 02c83d89394be1c7 · report
tatsu-lab/linguistic_calibration community (archive-listed) 3 samples, 1 ran (0 instrument-failed) · 2 unverified
Retrieval src/linguistic_calibration/auto_annotations/factscore_retrieval_utils.py ran Apache-2.0 (permissive) · 7ad7a356ddeef1cb · report fixture: returned Retrieval · level recorded 2026-09-22
DocDB src/linguistic_calibration/auto_annotations/factscore_retrieval_utils.py unverified Apache-2.0 (permissive) · c4456232ee580c04 · report
FactScorer src/linguistic_calibration/auto_annotations/factscore_retrieval_utils.py unverified Apache-2.0 (permissive) · d14a268e400630cf · 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 FACTSCORE (graph method: FACTSCORE). 3 bricks; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

  1. FactScorer entry · level 0 · unverified · d14a268e400630cf
  2. DocDB helper · level 0 · unverified · c4456232ee580c04
  3. Retrieval helper · level 1 · ran · 7ad7a356ddeef1cb

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="2305.14251") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

FormLanguage ModellingRetrievalText Generation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutGPT-4Label SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

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