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

• URL: http://arxiv.org/abs/2603.20673v1
• Date: Sat, 21 Mar 2026 06:23:21 GMT
• Title: PAVE: Premise-Aware Validation and Editing for Retrieval-Augmented LLMs
• Abstract summary: PAVE is an inference-time validation layer for evidence-grounded question answering.<n>It 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.
• Score: 8.082352336629816
• License: http://creativecommons.org/licenses/by-sa/4.0/
• 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.

Related papers

• From Trajectories to Evidence: Auditable Experimental Records for Industrial Research Agents [47.678562263387214]
  Research agents increasingly conduct multi-round machine-learning experiments in industrial recommendation settings.<n>Yet a completed trajectory is not automatically evidence: generated artifacts may be unsupported or incomplete, executed rounds may be invalid or confounded, and later modifications may obscure earlier findings.<n>We introduce an evidence-grounded framework that couples bounded verification of consequential artifacts with post-execution claim qualification.
  arXiv  Detail & Related papers  (2026-08-05T13:37:38Z)
• Align Documents to Questions: Question-Oriented Document Rewriting for Retrieval-Augmented Generation [51.55755193937205]
  We propose QREAM, a style-controlled rewriter that aligns retrieved documents with a question-oriented style while preserving facts.<n>Our framework consists of two stages: (1) QREAM-ICL, which uses stylistic seeds to guide iterative rewriting exploration; and (2) QREAM-FT, a lightweight student model distilled from denoised ICL outputs.
  arXiv  Detail & Related papers  (2026-04-19T08:39:21Z)
• Stateful Evidence-Driven Retrieval-Augmented Generation with Iterative Reasoning [7.701766930531068]
  Stateful Evidence-Driven RAG with Iterative Reasoning is a framework that models question answering as a progressive evidence accumulation process.<n>The framework performs evidence-driven deficiency analysis to identify gaps and conflicts and iteratively refines queries to guide subsequent retrieval.<n> Experiments on multiple question answering benchmarks demonstrate consistent improvements over standard RAG and multi-step baselines.
  arXiv  Detail & Related papers  (2026-03-25T06:57:49Z)
• CounterRefine: Answer-Conditioned Counterevidence Retrieval for Inference-Time Knowledge Repair in Factual Question Answering [1.1279808969568255]
  We present CounterRefine, a lightweight inference-time repair layer for retrieval-grounded question answering.<n>CounterRefine first produces a short answer from retrieved evidence, then gathers additional support and conflicting evidence with follow-up queries conditioned on that draft answer.<n>On the full SimpleQA benchmark, CounterRefine improves a matched GPT-5 Baseline-RAG by 5.8 points and reaches a 73.1 percent correct rate, while exceeding the reported one-shot GPT-5.4 score by roughly 40 points.
  arXiv  Detail & Related papers  (2026-03-17T03:27:25Z)
• Retrieve-Refine-Calibrate: A Framework for Complex Claim Fact-Checking [32.6738019397553]
  We propose a Retrieve-Refine-Calibrate (RRC) framework based on large language models (LLMs)<n>Specifically, the framework first identifies the entities mentioned in the claim and retrieves evidence relevant to them.<n>Then, it refines the retrieved evidence based on the claim to reduce irrelevant information.<n>Finally, it calibrates the verification process by re-evaluating low-confidence predictions.
  arXiv  Detail & Related papers  (2026-01-23T08:48:52Z)
• Look As You Think: Unifying Reasoning and Visual Evidence Attribution for Verifiable Document RAG via Reinforcement Learning [55.232400251303794]
  Look As You Think (LAT) is a reinforcement learning framework that trains models to produce verifiable reasoning paths with consistent attribution.<n>LAT consistently improves the vanilla model in both single- and multi-image settings, yielding average gains of 8.23% in soft exact match (EM) and 47.0% in IoU@0.5.
  arXiv  Detail & Related papers  (2025-11-15T02:50:23Z)
• VeriCite: Towards Reliable Citations in Retrieval-Augmented Generation via Rigorous Verification [107.75781898355562]
  We introduce a novel framework, called VeriCite, designed to rigorously validate supporting evidence and enhance answer attribution.<n>We conduct experiments across five open-source LLMs and four datasets, demonstrating that VeriCite can significantly improve citation quality while maintaining the correctness of the answers.
  arXiv  Detail & Related papers  (2025-10-13T13:38:54Z)
• CompassVerifier: A Unified and Robust Verifier for LLMs Evaluation and Outcome Reward [50.97588334916863]
  We develop CompassVerifier, an accurate and robust lightweight verifier model for evaluation and outcome reward.<n>It demonstrates multi-domain competency spanning math, knowledge, and diverse reasoning tasks, with the capability to process various answer types.<n>We introduce VerifierBench benchmark comprising model outputs collected from multiple data sources, augmented through manual analysis of metaerror patterns to enhance CompassVerifier.
  arXiv  Detail & Related papers  (2025-08-05T17:55:24Z)
• SUCEA: Reasoning-Intensive Retrieval for Adversarial Fact-checking through Claim Decomposition and Editing [30.84752573088322]
  adversarial claims are intentionally designed by humans to challenge fact-checking systems.<n>We propose a training-free method designed to rephrase the original claim, making it easier to locate supporting evidence.<n>Our framework significantly improves on both retrieval and entailment label accuracy, outperforming four strong claim-decomposition-based baselines.
  arXiv  Detail & Related papers  (2025-06-05T02:58:15Z)
• Faithfulness-Aware Uncertainty Quantification for Fact-Checking the Output of Retrieval Augmented Generation [108.13261761812517]
  We introduce FRANQ (Faithfulness-based Retrieval Augmented UNcertainty Quantification), a novel method for hallucination detection in RAG outputs.<n>We present a new long-form Question Answering (QA) dataset annotated for both factuality and faithfulness.
  arXiv  Detail & Related papers  (2025-05-27T11:56:59Z)
• Atomic Fact Decomposition Helps Attributed Question Answering [29.67882325906939]
  Attributed Question Answering (AQA) aims to provide both a trustworthy answer and a reliable attribution report for a question.<n>This paper proposes an Atomic fact decomposition-based Retrieval and Editing framework.<n>It decomposes the generated long-form answers into molecular clauses and atomic facts by the instruction-tuned LLMs.
  arXiv  Detail & Related papers  (2024-10-22T05:25:54Z)
• Contrastive Learning to Improve Retrieval for Real-world Fact Checking [84.57583869042791]
  We present Contrastive Fact-Checking Reranker (CFR), an improved retriever for fact-checking complex claims. We leverage the AVeriTeC dataset, which annotates subquestions for claims with human written answers from evidence documents. We find a 6% improvement in veracity classification accuracy on the dataset.
  arXiv  Detail & Related papers  (2024-10-07T00:09:50Z)
• From Relevance to Utility: Evidence Retrieval with Feedback for Fact Verification [118.03466985807331]
  We argue that, rather than relevance, for FV we need to focus on the utility that a claim verifier derives from the retrieved evidence.<n>We introduce the feedback-based evidence retriever(FER) that optimize the evidence retrieval process by incorporating feedback from the claim verifier.
  arXiv  Detail & Related papers  (2023-10-18T02:59:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.