# Long-form factuality in large language models

arXiv: https://arxiv.org/abs/2403.18802 · HTML: https://mlsanity.com/paper/2403.18802/

## Key facts

- Cited by 155 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Mar 2024.

## Built on by (most cited first, 30 of 155)

- [Measuring short-form factuality in large language models](https://mlsanity.com/paper/2411.04368/) (2024)
- [On LLMs-Driven Synthetic Data Generation, Curation, and Evaluation: A Survey](https://mlsanity.com/paper/2406.15126/) (2024)
- [AI Agents Under Threat: A Survey of Key Security Challenges and Future Pathways](https://mlsanity.com/paper/2406.02630/) (2024)
- [Best Practices and Lessons Learned on Synthetic Data](https://mlsanity.com/paper/2404.07503/) (2024)
- [OverThink: Slowdown Attacks on Reasoning LLMs](https://mlsanity.com/paper/2502.02542/) (2025)
- [HalluLens: LLM Hallucination Benchmark](https://mlsanity.com/paper/2504.17550/) (2025)
- [FaithEval: Can Your Language Model Stay Faithful to Context, Even If "The Moon is Made of Marshmallows"](https://mlsanity.com/paper/2410.03727/) (2024)
- [One Thousand and One Pairs: A "novel" challenge for long-context language models](https://mlsanity.com/paper/2406.16264/) (2024)
- [Foundational Autoraters: Taming Large Language Models for Better Automatic Evaluation](https://mlsanity.com/paper/2407.10817/) (2024)
- [Self-play with Execution Feedback: Improving Instruction-following Capabilities of Large Language Models](https://mlsanity.com/paper/2406.13542/) (2024)
- [UltraMedical: Building Specialized Generalists in Biomedicine](https://mlsanity.com/paper/2406.03949/) (2024)
- [SimpleQA Verified: A Reliable Factuality Benchmark to Measure Parametric Knowledge](https://mlsanity.com/paper/2509.07968/) (2025)
- [The FACTS Grounding Leaderboard: Benchmarking LLMs' Ability to Ground Responses to Long-Form Input](https://mlsanity.com/paper/2501.03200/) (2025)
- [DeepSearchQA: Bridging the Comprehensiveness Gap for Deep Research Agents](https://mlsanity.com/paper/2601.20975/) (2026)
- [FIRE: Fact-checking with Iterative Retrieval and Verification](https://mlsanity.com/paper/2411.00784/) (2024)
- [Real-Time Detection of Hallucinated Entities in Long-Form Generation](https://mlsanity.com/paper/2509.03531/) (2025)
- [Search Self-play: Pushing the Frontier of Agent Capability without Supervision](https://mlsanity.com/paper/2510.18821/) (2025)
- [GraphEval: A Knowledge-Graph Based LLM Hallucination Evaluation Framework](https://mlsanity.com/paper/2407.10793/) (2024)
- [OpenFactCheck: A Unified Framework for Factuality Evaluation of LLMs](https://mlsanity.com/paper/2408.11832/) (2024)
- [DARG: Dynamic Evaluation of Large Language Models via Adaptive Reasoning Graph](https://mlsanity.com/paper/2406.17271/) (2024)
- [FactBench: A Dynamic Benchmark for In-the-Wild Language Model Factuality Evaluation](https://mlsanity.com/paper/2410.22257/) (2024)
- [RARE: Retrieval-Augmented Reasoning Enhancement for Large Language Models](https://mlsanity.com/paper/2412.02830/) (2024)
- [Claim Verification in the Age of Large Language Models: A Survey](https://mlsanity.com/paper/2408.14317/) (2024)
- [Can Knowledge Graphs Make Large Language Models More Trustworthy? An Empirical Study Over Open-ended Question Answering](https://mlsanity.com/paper/2410.08085/) (2024)
- [Mask-DPO: Generalizable Fine-grained Factuality Alignment of LLMs](https://mlsanity.com/paper/2503.02846/) (2025)
- [OLAPH: Improving Factuality in Biomedical Long-form Question Answering](https://mlsanity.com/paper/2405.12701/) (2024)
- [Small Agent Can Also Rock! Empowering Small Language Models as Hallucination Detector](https://mlsanity.com/paper/2406.11277/) (2024)
- [Conformal Linguistic Calibration: Trading-off between Factuality and Specificity](https://mlsanity.com/paper/2502.19110/) (2025)
- [ToolScan: A Benchmark for Characterizing Errors in Tool-Use LLMs](https://mlsanity.com/paper/2411.13547/) (2024)
- [OmniThink: Expanding Knowledge Boundaries in Machine Writing through Thinking](https://mlsanity.com/paper/2501.09751/) (2025)

## Abstract (arXiv)

Large language models (LLMs) often generate content that contains factual errors when responding to fact-seeking prompts on open-ended topics. To benchmark a model's long-form factuality in open domains, we first use GPT-4 to generate LongFact, a prompt set comprising thousands of questions spanning 38 topics. We then propose that LLM agents can be used as automated evaluators for long-form factuality through a method which we call Search-Augmented Factuality Evaluator (SAFE). SAFE utilizes an LLM to break down a long-form response into a set of individual facts and to evaluate the accuracy of each fact using a multi-step reasoning process comprising sending search queries to Google Search and determining whether a fact is supported by the search results. Furthermore, we propose extending F1 score as an aggregated metric for long-form factuality. To do so, we balance the percentage of supported facts in a response (precision) with the percentage of provided facts relative to a hyperparameter representing a user's preferred response length (recall). Empirically, we demonstrate that LLM agents can outperform crowdsourced human annotators - on a set of ~16k individual facts, SAFE agrees with crowdsourced human annotators 72% of the time, and on a random subset of 100 disagreement cases, SAFE wins 76% of the time. At the same time, SAFE is more than 20 times cheaper than human annotators. We also benchmark thirteen language models on LongFact across four model families (Gemini, GPT, Claude, and PaLM-2), finding that larger language models generally achieve better long-form factuality. LongFact, SAFE, and all experimental code are available at https://github.com/google-deepmind/long-form-factuality.