Multi-Source Knowledge Pruning for Retrieval-Augmented Generation: A Benchmark and Empirical Study

ACL ARR 2025 February Submission3651 Authors

Abstract: Retrieval-augmented generation (RAG) is increasingly recognized as an effective approach to mitigating the hallucination of large language models (LLMs) through the integration of external knowledge. While numerous efforts, most studies focus on a single type of external knowledge source. In contrast, most real-world applications involve diverse knowledge from various sources, a scenario that has been relatively underexplored. The main dilemma is the lack of a suitable dataset incorporating multiple knowledge sources and pre-exploration of the associated issues. To address these challenges, we standardize a benchmark dataset that combines structured and unstructured knowledge across diverse and complementary domains. Building upon the dataset, we identify the limitations of existing methods under such conditions. Therefore, we develop PruningRAG, a plug-and-play RAG framework that uses multi-granularity pruning strategies to more effectively incorporate relevant context and mitigate the negative impact of misleading information. Extensive experimental results demonstrate superior performance of PruningRAG and our insightful findings are also reported. Our dataset and code are publicly available\footnote{https://anonymous.4open.science/r/PruningRAG-BBAC}.

Paper Type: Long

Research Area: Generation

Research Area Keywords: retrieval-augmented generation, automatic evaluation

Contribution Types: Data resources, Theory

Languages Studied: English

Submission Number: 3651