• Computer Science > Artificial Intelligence [Submitted on 25 Feb 2026] Title:Distill and Align Decomposition for Enhanced Claim Verification View PDFAbstract:Complex claim verification requires decomposing sentences into verifiable subclaims, yet existing methods struggle to align decomposition quality with verification performance • We propose a reinforcement learning (RL) approach that jointly optimizes decomposition quality and verifier alignment using Group Relative Policy Optimization (GRPO) • Our method integrates: (i) structured sequential reasoning; (ii) supervised finetuning on teacher-distilled exemplars; and (iii) a multi-objective reward balancing format compliance, verifier alignment, and decomposition quality • Across six evaluation settings, our trained 8B decomposer improves downstream verification performance to (71 • 75%) macro-F1, outperforming prompt-based approaches ((+1 • 24)) and existing RL methods ((+5

Article Summaries:

  • Computer Science > Artificial Intelligence [Submitted on 25 Feb 2026] Title:Distill and Align Decomposition for Enhanced Claim Verification View PDFAbstract:Complex claim verification requires decomposing sentences into verifiable subclaims, yet existing methods struggle to align decomposition quality with verification performance. We propose a reinforcement learning (RL) approach that jointly optimizes decomposition quality and verifier alignment using Group Relative Policy Optimization (GRPO). Our method integrates: (i) structured sequential reasoning; (ii) supervised finetuning on teacher-d

Sources: