Definition
Factuality evaluation scores the factual precision of a model or of a set of its outputs: the share of claims a trusted knowledge source supports. One recipe is decompose-then-verify (FActScore, Min et al., EMNLP 2023). Another is consistency with a given source, measured by question answering (QAGS, QuestEval) or entailment (SummaC). Fixed benchmarks include FEVER and TruthfulQA.
Hallucination detection flags one output at inference time, often with no reference. Factuality evaluation is the offline measurement. It takes many outputs and labelled evidence, and returns a number to compare models, decoding settings or training runs. It can be slow and use retrieval, because nobody waits on it.
The task: input a prompt , the model's response , and a knowledge source (Wikipedia, a document, search results). Output a score in . It is hard because long text mixes true and false claims, often within one sentence. Overlap metrics such as ROUGE and BLEU also barely see a one-word error like "Kraków" for "Warsaw". Maynez et al. (ACL 2020) found that entailment-based measures agreed with human faithfulness judgments better than ROUGE.
Decompose, then verify
FActScore splits each response into atomic facts: short statements that carry one piece of information. In the original work an LLM proposed the facts and human annotators corrected them. Each fact is then labelled supported or not against , and the score is the supported share, averaged over prompts:
- atomic facts of response y
- knowledge source; FActScore uses the Wikipedia page of the person in the prompt
- prompts the model actually answers; abstentions are reported separately
Human annotation of people biographies (“Tell me a bio of …”) put ChatGPT at only 58%. The paper then built an automatic estimator: retrieve passages from the page and ask an LM whether each fact is true. Its error against the human FActScore was under 2%, and it was used to score 6,500 generations from 13 recent LMs.
Consistency with a source: QA and NLI
When the reference is a given document, as in summarisation or RAG answers, the question becomes faithfulness to that document. QAGS (Wang, Cho and Lewis, ACL 2020) generates questions from the summary and answers each one twice, from the source and from the summary. The score is the mean similarity of the answer pairs. QuestEval (Scialom et al., EMNLP 2021) also asks questions in the other direction, from the source, which adds a recall component.
SummaC (Laban, Schnabel, Bennett and Hearst, TACL 2022) fixes a granularity mismatch. NLI models are trained on sentence pairs, so it scores every (source sentence, summary sentence) pair and aggregates:
- i-th source sentence, j-th summary sentence
- entailment score of the pair from an MNLI-style model
- each summary sentence needs support from only one source sentence; SummaC-Conv instead learns from the histogram of the column
FactCC (Kryściński et al., EMNLP 2020) takes another route: a classifier trained on synthetic corruptions such as swapped entities, numbers and negations. FRANK (Pagnoni et al., NAACL 2021) annotates a typology of error types, so you can see which errors each metric misses.
Benchmarks and reference results
- FEVER
- Thorne et al., NAACL 2018. 185,445 claims made by altering Wikipedia sentences, labelled Supported, Refuted or NotEnoughInfo, with evidence sentences
- TruthfulQA
- Lin, Hilton and Evans, ACL 2022. 817 questions in 38 categories that target common misconceptions. The best model then was truthful on 58%, humans on 94%. See LLM evaluation and benchmarking
- FActScore
- Min et al., EMNLP 2023. People biographies scored against Wikipedia. Human FActScore of ChatGPT: 58%. Automatic estimator error: under 2%
- SAFE / LongFact
- Wei et al., 2024. An LLM agent checks each fact with Google Search. It agreed with crowd annotators on 72% of facts and won 76% of 100 disagreements, at over 20× lower cost
Is the metric itself right?
An automatic factuality metric is a model, so it must be validated against people. There are three levels. At the fact level, measure the agreement or Cohen's of the verdicts with human labels. At the output level, use correlation or balanced accuracy on consistent-vs-inconsistent summaries; SummaC's benchmark uses balanced accuracy. At the system level, ask whether the estimated scores rank models in the human order and how far each score is off.
Worked example
| Sentence | Atomic facts | Supported | Sentence fully supported? |
|---|---|---|---|
| S1 Polish-born physicist and chemist | Polish-born · physicist · chemist | 3 / 3 | yes |
| S2 Nobel Physics 1903, Chemistry 1911 | Physics prize · in 1903 · Chemistry prize · in 1911 | 4 / 4 | yes |
| S3 born in Kraków in 1867 | born in Kraków · born in 1867 | 1 / 2 | no |
| S4 discovered polonium and radium with Pierre | polonium · radium · with Pierre Curie | 3 / 3 | yes |
| S5 died in 1938 | died in 1938 | 0 / 1 | no |
| Total | 13 facts | 11 / 13 = 0.846 | 3 / 5 = 0.600 |
SummaC-ZS on a 2 × 2 matrix
- 1Source sentences ; summary sentences . NLI entailment scores (rows: source, columns: summary).
- 2Column maxima: , .
- 3Mean over summary sentences: . Sentence is weakly supported, so this summary is suspect.
1from transformers import pipeline2from sklearn.metrics import cohen_kappa_score34nli = pipeline("text-classification", model="microsoft/deberta-large-mnli", top_k=None)56passage = ("Maria Salomea Skłodowska-Curie (7 November 1867 – 4 July 1934) was a Polish "7 "and naturalised-French physicist and chemist ... She was born in Warsaw ...")8facts = ["Marie Curie was Polish-born.", "Marie Curie was a physicist.",9 "Marie Curie was born in Kraków.", "Marie Curie was born in 1867.",10 "Marie Curie died in 1938."]11human = [1, 1, 0, 1, 0]1213def p_entail(premise, hypothesis):14 out = nli([{"text": premise, "text_pair": hypothesis}])[0]15 return next(d["score"] for d in out if d["label"] == "ENTAILMENT")1617auto = [int(p_entail(passage, f) >= 0.5) for f in facts]18print("FActScore (auto) :", sum(auto) / len(auto))19print("FActScore (human):", sum(human) / len(human)) # 0.620print("Cohen's kappa :", cohen_kappa_score(human, auto))Where it's used
Model comparison
Rank LLMs, decoding settings or RAG pipelines on long-form factual precision (biographies, LongFact prompts).
Summarisation
Gate abstractive summaries by SummaC or QA-based consistency with the source document.
Training signal
Use automatic factuality scores as rewards or preference labels for fine-tuning toward fewer unsupported claims.
Check yourself
A response has 4 sentences with 3 atomic facts each. Exactly one fact in each sentence is false. What are FActScore and the sentence-level score?
Check yourself
On 50 facts, an automatic verifier's FActScore is within 0.02 of the human FActScore. What can you conclude?
Remember
- ✓Factuality evaluation measures precision offline over many outputs. Hallucination detection flags single outputs at inference.
- ✓FActScore mean share of atomic facts supported by the knowledge source. Human-annotated ChatGPT bios: 58%. The automatic estimator's error was under 2%.
- ✓Source consistency: QAGS and QuestEval compare answers to generated questions. SummaC takes, for each summary sentence, the max NLI entailment over source sentences, then averages.
- ✓Benchmarks: FEVER (185,445 claims, Supported / Refuted / NotEnoughInfo) and TruthfulQA (817 misconception questions).
- ✓Validate metrics against humans at the fact level (agreement, κ), the output level (correlation, balanced accuracy) and the system level (ranking).
- ✓Precision alone rewards short or abstaining answers. Report coverage, or use F1@K.