Skip to content
conftrace_
2026 EMNLP EMNLP 2026

Joint Constraint Aggregation for Qualifier-Sensitive Retrieval-Augmented QA

AbstractRetrieval-augmented QA can fail even when the correct answer is in the retrieved evidence. This can happen when a competing answer satisfies some, but not all, of the question’s requirements and is mentioned frequently in the retrieved documents, making it look like a strong choice. To test whether this retrieval skew actually affects the decision, we manipulate it directly: increasing the prevalence of passages that favor the competing answer makes models more likely to select it. This points to a decision problem that candidate-level support alone cannot resolve. We therefore introduce Joint Constraint Aggregation (JCA), which compares candidates against the same question-derived requirements using the retrieved evidence. Across our evaluation settings, JCA improves overall accuracy, and its advantage grows when retrieval favors a competing answer. Together, these results suggest that when partial matches and retrieval prominence pull models toward a competing answer, comparing candidates against the question’s full requirements can make selection more reliable.

More from EMNLP 2026

All EMNLP 2026 papers →