VeriFact: Enhancing Long-Form Factuality Evaluation with Refined Fact Extraction and Reference Facts

Large language models (LLMs) excel at generating long-form responses, but evaluating their factuality remains challenging due to complex inter-sentence dependencies within the generated facts. Prior solutions predominantly follow a decompose-decontextualize-verify pipeline but often fail to capture essential context and miss key relational facts. In this paper, we introduce VERIFACT, a factuality evaluation framework designed to enhance fact extraction by identifying and resolving incomplete and missing facts to support more accurate verification results. Moreover, we introduce FACTR-BENCH 1 , a benchmark that evaluates both precision and recall in long-form model responses, whereas prior work primarily focuses on precision. FACTRBENCH provides reference fact sets from advanced LLMs and human-written answers, enabling recall assessment. Empirical evaluations show that VERIFACT significantly enhances fact completeness and preserves complex facts with critical relational information, resulting in more accurate factuality evaluation. Benchmarking various open-and close-weight LLMs on FACTRBENCH indicate that larger models within same model family improve precision and recall, but high precision does not always correlate with high recall, underscoring the importance of comprehensive factuality assessment. If there wasn't a demand for gold as jewelry, would its price drop enough to make it usable in consumer electronics? If the demand for gold as jewelry were to disappear, the price of gold could drop by 20-50% or more, making it more competitive with other materials like copper and silver. 1. There is a demand for gold as jewelry Anthropic. 2024. Claude 3.5 sonnet.