GRACE: Reinforcement Learning for Grounded Response and Abstention under Contextual Evidence

• URL: http://arxiv.org/abs/2601.04525v1
• Date: Thu, 08 Jan 2026 02:47:33 GMT
• Title: GRACE: Reinforcement Learning for Grounded Response and Abstention under Contextual Evidence
• Authors: Yibo Zhao, Jiapeng Zhu, Zichen Ding, Xiang Li,
• Abstract summary: Retrieval-Augmented Generation (RAG) integrates external knowledge to enhance Large Language Models (LLMs)<n>RAG is susceptible to two critical flaws: providing correct answers without explicit grounded evidence and producing fabricated responses when the retrieved context is insufficient.<n>We propose GRACE, a reinforcement-learning framework that simultaneously mitigates both types of flaws.
• Score: 9.80421132842862
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Retrieval-Augmented Generation (RAG) integrates external knowledge to enhance Large Language Models (LLMs), yet systems remain susceptible to two critical flaws: providing correct answers without explicit grounded evidence and producing fabricated responses when the retrieved context is insufficient. While prior research has addressed these issues independently, a unified framework that integrates evidence-based grounding and reliable abstention is currently lacking. In this paper, we propose GRACE, a reinforcement-learning framework that simultaneously mitigates both types of flaws. GRACE employs a data construction method that utilizes heterogeneous retrievers to generate diverse training samples without manual annotation. A multi-stage gated reward function is then employed to train the model to assess evidence sufficiency, extract key supporting evidence, and provide answers or explicitly abstain. Experimental results on two benchmarks demonstrate that GRACE achieves state-of-the-art overall accuracy and strikes a favorable balance between accurate response and rejection, while requiring only 10% of the annotation costs of prior methods. Our code is available at https://github.com/YiboZhao624/Grace..

Related papers

• From Verifiable Dot to Reward Chain: Harnessing Verifiable Reference-based Rewards for Reinforcement Learning of Open-ended Generation [52.62655622099456]
  We propose reinforcement learning with verifiable reference-based rewards (RLVRR)<n>Instead of checking the final answer, RLVRR extracts an ordered linguistic signal from high-quality references (i.e., reward chain)<n>In this way, RLVRR decomposes rewards into two dimensions: content, which preserves deterministic core concepts, and style, which evaluates adherence to stylistic properties.
  arXiv  Detail & Related papers  (2026-01-26T14:39:58Z)
• Bounding Hallucinations: Information-Theoretic Guarantees for RAG Systems via Merlin-Arthur Protocols [40.19713302778418]
  We introduce a training framework that treats the entire RAG pipeline as an interactive proof system.<n>We show that M/A-trained LLMs show improved groundedness, completeness, soundness, and reject behavior.<n>Our results demonstrate that autonomous interactive-proof-style supervision provides a principled and practical path toward reliable RAG systems.
  arXiv  Detail & Related papers  (2025-12-12T14:50:38Z)
• ReAG: Reasoning-Augmented Generation for Knowledge-based Visual Question Answering [54.72902502486611]
  ReAG is a Reasoning-Augmented Multimodal RAG approach that combines coarse- and fine-grained retrieval with a critic model that filters irrelevant passages.<n>ReAG significantly outperforms prior methods, improving answer accuracy and providing interpretable reasoning grounded in retrieved evidence.
  arXiv  Detail & Related papers  (2025-11-27T19:01:02Z)
• 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)
• Decomposition-Enhanced Training for Post-Hoc Attributions In Language Models [64.49342399229529]
  We argue that post-hoc attribution can be reframed as a reasoning problem, where answers are decomposed into constituent units, each tied to specific context.<n>We introduce DecompTune, a post-training method that teaches models to produce answer decompositions as intermediate reasoning steps.<n>Across extensive experiments and ablations, DecompTune substantially improves attribution quality, outperforming prior methods and matching or exceeding state-of-the-art frontier models.
  arXiv  Detail & Related papers  (2025-10-29T17:58:59Z)
• 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)
• EviNote-RAG: Enhancing RAG Models via Answer-Supportive Evidence Notes [39.61443457073034]
  We introduce EviNote-RAG, a framework that follows a retrieve-note-answer workflow.<n>Instead of reasoning directly over raw external information, the model first produces Supportive-Evidence Notes.<n>EviNote-RAG achieves state-of-the-art performance, improving answer accuracy, training stability, robustness, and efficiency.
  arXiv  Detail & Related papers  (2025-08-31T14:44:45Z)
• SEER: Self-Aligned Evidence Extraction for Retrieval-Augmented Generation [21.823931225182115]
  We propose a model-based evidence extraction learning framework, SEER, to optimize a vanilla model as an evidence extractor. Our method largely improves the final RAG performance, enhances the faithfulness, helpfulness, and conciseness of the extracted evidence, and reduces the evidence length by 9.25 times.
  arXiv  Detail & Related papers  (2024-10-15T06:26:24Z)
• Groundedness in Retrieval-augmented Long-form Generation: An Empirical Study [61.74571814707054]
  We evaluate whether every generated sentence is grounded in retrieved documents or the model's pre-training data. Across 3 datasets and 4 model families, our findings reveal that a significant fraction of generated sentences are consistently ungrounded. Our results show that while larger models tend to ground their outputs more effectively, a significant portion of correct answers remains compromised by hallucinations.
  arXiv  Detail & Related papers  (2024-04-10T14:50:10Z)
• Adversarial Contrastive Learning for Evidence-aware Fake News Detection with Graph Neural Networks [20.282527436527765]
  We propose a unified Graph-based sEmantic structure mining framework with ConTRAstive Learning, namely GETRAL in short. We first model claims and evidences as graph-structured data to capture the long-distance semantic dependency. Then the fine-grained semantic representations are fed into the claim-evidence interaction module for predictions.
  arXiv  Detail & Related papers  (2022-10-11T14:54:37Z)
• Distantly-Supervised Evidence Retrieval Enables Question Answering without Evidence Annotation [19.551623461082617]
  Open-domain question answering answers a question based on evidence retrieved from a large corpus. This paper investigates whether models can learn to find evidence from a large corpus, with only distant supervision from answer labels for model training. We introduce a novel approach (DistDR) that iteratively improves over a weak retriever by alternately finding evidence from the up-to-date model and encouraging the model to learn the most likely evidence.
  arXiv  Detail & Related papers  (2021-10-10T20:01:27Z)

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.