Skip to main content

Spring Deadline: Sunday, March 1 @ 11:59pm PT. Click here to apply.

Back to Research
Accepted to NAACL SRW 2025

ChunkRAG: Novel LLM-Chunk Filtering Method for RAG Systems

Ishneet Singh, Ritvik Aggarwal, Ibrahim Allahverdiyev, Muhammad Taha

Abstract

Retrieval-Augmented Generation (RAG) systems using large language models (LLMs) often generate inaccurate responses due to the retrieval of irrelevant or loosely related information. Existing methods, which operate at the document level, fail to effectively filter out such content. We propose LLM-driven chunk filtering, ChunkRAG, a framework that enhances RAG systems by evaluating and filtering retrieved information at the chunk level. Our approach employs semantic chunking to divide documents into coherent sections and utilizes LLM-based relevance scoring to assess each chunk's alignment with the user's query. By filtering out less pertinent chunks before the generation phase, we significantly reduce hallucinations and improve factual accuracy. Empirical evaluations on the PopQA, PubHealth and Biography dataset indicate that ChunkRAG improves response accuracy over state-of-the-art RAG methods.

Citation

Ishneet Singh, Ritvik Aggarwal, Ibrahim Allahverdiyev, Muhammad Taha. "ChunkRAG: Novel LLM-Chunk Filtering Method for RAG Systems". Accepted to NAACL SRW 2025.

Details

Conference
Accepted to NAACL SRW 2025
Authors
4 authors

Publish Your Research

Join Algoverse and work with world-class mentors to publish at top AI conferences.

Start Your Application