Grounding Language Model with Chunking-Free In-Context Retrieval

TL;DR

This paper introduces a Chunking-Free In-Context retrieval method for RAG systems that improves evidence grounding by using encoded document states and specialized decoding strategies, surpassing traditional chunking approaches.

Contribution

The paper proposes a novel CFIC retrieval approach that eliminates document chunking, enhancing efficiency and accuracy in evidence retrieval for RAG systems.

Findings

CFIC outperforms traditional chunking methods in evidence retrieval accuracy.

The approach maintains semantic coherence without disrupting document context.

Enhanced decoding strategies improve retrieval efficiency and fidelity.

Abstract

This paper presents a novel Chunking-Free In-Context (CFIC) retrieval approach, specifically tailored for Retrieval-Augmented Generation (RAG) systems. Traditional RAG systems often struggle with grounding responses using precise evidence text due to the challenges of processing lengthy documents and filtering out irrelevant content. Commonly employed solutions, such as document chunking and adapting language models to handle longer contexts, have their limitations. These methods either disrupt the semantic coherence of the text or fail to effectively address the issues of noise and inaccuracy in evidence retrieval. CFIC addresses these challenges by circumventing the conventional chunking process. It utilizes the encoded hidden states of documents for in-context retrieval, employing auto-aggressive decoding to accurately identify the specific evidence text required for user queries, eliminating the need for chunking. CFIC is further enhanced by incorporating two decoding strategies, namely Constrained Sentence Prefix Decoding and Skip Decoding. These strategies not only improve the efficiency of the retrieval process but also ensure that the fidelity of the generated grounding text evidence is maintained. Our evaluations of CFIC on a range of open QA datasets demonstrate its superiority in retrieving relevant and accurate evidence, offering a significant improvement over traditional methods. By doing away with the need for document chunking, CFIC presents a more streamlined, effective, and efficient retrieval solution, making it a valuable advancement in the field of RAG systems.