Claim-Level Feedback Signals for Prompt Optimization in Open-Ended Generation

Optimizing prompts for frozen language models typically relies on scalar rewards or holistic feedback over entire responses. In open-ended generation, however, a response may contain many factual claims, making such coarse feedback insufficient to identify what should be corrected. We formulate prompt refinement around fine-grained, claim-level error signals. Our approach decomposes model responses and reference answers into atomic claims, identifies coverage gaps and contradictions, and abstracts these errors into content-invariant patterns that capture recurring failure modes across examples. The resulting patterns are clustered into error types from which corrective prompt directives are proposed. Each directive is adopted only when its improvement over the current prompt satisfies both a gain margin and a paired-bootstrap stability criterion. Across four language-model backbones and three open-ended factuality benchmarks—K-QA, TruthfulQA, and FActScore—the resulting prompts improve the balance between factual coverage and reliability, including higher comprehensiveness and lower hallucination on K-QA. These results show that decomposed error signals provide a more actionable objective for prompt optimization than treating an open-ended response as a single evaluation unit.