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

TL;DR

GRACE is a reinforcement learning framework that improves retrieval-augmented language models by ensuring grounded responses and reliable abstention, reducing annotation costs and enhancing accuracy.

Contribution

It introduces a unified reinforcement learning approach with a novel data construction and reward system to address grounding and abstention issues simultaneously.

Findings

Achieves state-of-the-art accuracy on benchmarks.

Balances response correctness and abstention effectively.

Reduces annotation costs by 90%.

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..