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

2026-01-08 · Yibo Zhao, Jiapeng Zhu, Zichen Ding, Xiang Li arxiv

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..

📄 PDF Abstract BibTeX arXiv:2601.04525

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

GRACE: Step-Level Benchmark for Faithful Reasoning over Context

2026-06-15 · Hoang Pham, Dong Le, Anh Tuan Luu arxiv

Many reasoning tasks require models to reason over input context, from document-grounded question answering to rule-based deduction. Chain-of-Thought (CoT) prompting produces traces that appear transparent, yet individua…

Reinforcement Learning Question Answering

Twin Worlds: Equivariance-Based Abstention for Evidence-Grounded Reasoning

2026-08-28 · Vy Nguyen, Ziqi Xu, Jeffrey Chan, Estrid He 외 arxiv

Knowledge-intensive reasoning requires Large Language Models (LLMs) to ground answers in provided evidence. When evidence is insufficient, it is desirable that models abstain rather than confidently generating unsupporte…

Rewarding Intellectual Humility Learning When Not To Answer In Large Language Models

2026-01-27 · Abha Jha, Akanksha Mahajan, Ashwath Vaithinathan Aravindan, Praveen Saravanan 외 arxiv

Large Language Models (LLMs) often produce hallucinated or unverifiable content, undermining their reliability in factual domains. This work investigates Reinforcement Learning with Verifiable Rewards (RLVR) as a trainin…

Reinforcement Learning Question Answering

Knowing When to Quit: A Principled Framework for Dynamic Abstention in LLM Reasoning

2026-04-20 · Hen Davidov, Nachshon Cohen, Oren Kalinsky, Yaron Fairstein 외 arxiv

LLMs utilizing chain-of-thought reasoning often waste substantial compute by producing long, incorrect responses. Abstention can mitigate this by withholding outputs unlikely to be correct. While most abstention methods …

Mathematical Reasoning Reinforcement Learning

Boundary-Aware NL2SQL: Integrating Reliability through Hybrid Reward and Data Synthesis

2026-01-15 · Songsong Tian, Kongsheng Zhuo, Zhendong Wang, Rong Shen 외 arxiv

In this paper, we present BAR-SQL (Boundary-Aware Reliable NL2SQL), a unified training framework that embeds reliability and boundary awareness directly into the generation process. We introduce a Seed Mutation data synt…