DecMetrics: Structured Claim Decomposition Scoring for Factually Consistent LLM Outputs
This addresses the need for better evaluation in fact-checking systems, though it is incremental as it builds on existing decomposition methods.
The paper tackles the problem of evaluating the quality of decomposed atomic claims in fact-checking by introducing DecMetrics, a set of three new metrics (COMPLETENESS, CORRECTNESS, and SEMANTIC ENTROPY) for automatic assessment, and uses them to develop a lightweight model that sets a benchmark for claim decomposition.
Claim decomposition plays a crucial role in the fact-checking process by breaking down complex claims into simpler atomic components and identifying their unfactual elements. Despite its importance, current research primarily focuses on generative methods for decomposition, with insufficient emphasis on evaluating the quality of these decomposed atomic claims. To bridge this gap, we introduce \textbf{DecMetrics}, which comprises three new metrics: \texttt{COMPLETENESS}, \texttt{CORRECTNESS}, and \texttt{SEMANTIC ENTROPY}, designed to automatically assess the quality of claims produced by decomposition models. Utilizing these metrics, we develop a lightweight claim decomposition model, optimizing its performance through the integration of these metrics as a reward function. Through automatic evaluation, our approach aims to set a benchmark for claim decomposition, enhancing both the reliability and effectiveness of fact-checking systems.