Injecting External Knowledge into the Reasoning Process Enhances Retrieval-Augmented Generation

TL;DR

This paper introduces Passage Injection, a method that explicitly incorporates retrieved passages into large language models' reasoning process to improve robustness and performance in retrieval-augmented generation, especially under noisy retrieval conditions.

Contribution

The paper proposes Passage Injection, a novel technique that enhances LLMs' ability to recognize and resist noisy passages in RAG systems, improving robustness and accuracy.

Findings

Significant performance gains in RAG tasks with Passage Injection.

Improved robustness against noisy and misleading passages.

Effective leverage of helpful passages in reasoning.

Abstract

Retrieval-augmented generation (RAG) has been widely adopted to augment large language models (LLMs) with external knowledge for knowledge-intensive tasks. However, its effectiveness is often undermined by the presence of noisy (i.e., low-quality) retrieved passages. Enhancing LLMs' robustness to such noise is critical for improving the reliability of RAG systems. Recent advances have equipped LLMs with strong reasoning and self-reflection capabilities, allowing them to identify and correct errors in their reasoning process. Inspired by this ability, we propose Passage Injection-a simple yet effective method that explicitly incorporates retrieved passages into LLMs' reasoning process, aiming to enhance the model's ability to recognize and resist noisy passages. We validate Passage Injection under general RAG settings using BM25 as the retriever. Experiments on four reasoning-enhanced LLMs across four factual QA datasets demonstrate that Passage Injection significantly improves overall RAG performance. Further analysis on two noisy retrieval settings-random noise, where the model is provided irrelevant passages, and counterfactual noise, where it is given misleading passages-shows that Passage Injection consistently improves robustness. Controlled experiments confirm that Passage Injection can also effectively leverage helpful passages. These findings suggest that incorporating passages in LLMs' reasoning process is a promising direction for building more robust RAG systems. The code can be found \href{here}{https://github.com/Trustworthy-Information-Access/Passage-Injection}.