Enhancing Retrieval-Augmented Generation with Dehallucinating Parallel Context Extension

Zexiong Ma, Shengnan An, Zeqi Lin, Yanzhen Zou, Jian-Guang Lou, Bing Xie

Keywords: Retrieval-Augmented Generation, Parallel Context Extension

TL;DR: This work introduces DePaC to alleviate the hallucination issue of parallel context extension on RAG.

Abstract: Large language models (LLMs) are susceptible to generating hallucinated information, despite the integration of retrieval-augmented generation (RAG). Parallel context extension (PCE) is a line of research attempting to effectively integrating parallel (unordered) contexts, while it still suffers from in-context hallucinations when adapted to RAG scenarios. In this paper, we propose **DePaC** (**De**hallucinating **Pa**rallel **C**ontext Extension), which alleviates the in-context hallucination problem with **context-aware negative training** and **information-calibrated aggregation**. DePaC is designed to alleviate two types of in-context hallucination: **fact fabrication** (i.e., LLMs present claims that are not supported by the contexts) and **fact omission** (i.e., LLMs fail to present claims that can be supported by the contexts). Specifically, (1) for fact fabrication, we apply the context-aware negative training that fine-tunes the LLMs with negative supervisions, thus explicitly guiding the LLMs to refuse to answer when contexts are not related to questions; (2) for fact omission, we propose the information-calibrated aggregation which prioritizes context windows with higher information increment from their contexts.

Submission Number: 30