PAVE: Premise-Aware Validation and Editing for Retrieval-Augmented LLMs

Tianyi Huang, Caden Yang, Emily Yin, Eric Wang, Michael Zhang

Track: long paper (up to 10 pages)

Keywords: retrieval-augmented generation, large language models, evidence-grounded reasoning, reliability

TL;DR: PAVE improves evidence-grounded question answering in RAG by turning retrieved context into explicit premises and checking answer support before returning a final response.

Abstract: Retrieval-augmented language models can retrieve relevant evidence yet still commit to answers before explicitly checking whether the retrieved context supports the conclusion. We present PAVE (Premise-Grounded Answer Validation and Editing), an inference-time validation layer for evidence-grounded question answering. PAVE decomposes retrieved context into question-conditioned atomic facts, drafts an answer, scores how well that draft is supported by the extracted premises, and revises low-support outputs before finalization. The resulting trace makes answer commitment auditable at the level of explicit premises, support scores, and revision decisions. In controlled ablations with a fixed retriever and backbone, PAVE outperforms simpler post-retrieval baselines in two evidence-grounded QA settings, with the largest gain reaching 32.7 accuracy points on a span-grounded benchmark. We view these findings as proof-of-concept evidence that explicit premise extraction plus support-gated revision can strengthen evidence-grounded consistency in retrieval-augmented LLM systems.

Anonymization: This submission has been anonymized for double-blind review via the removal of identifying information such as names, affiliations, and identifying URLs.

Submission Number: 192