通过对比解释激发检索增强语言模型中的批判性推理
Eliciting Critical Reasoning in Retrieval-Augmented Language Models via Contrastive Explanations
AI总结：
提出C-RAG框架，通过检索、筛选段落并生成对比相关性解释来激发RAG的批判性推理，从而以更少提示提升模型性能与抗噪鲁棒性。
摘要：
检索增强生成（RAG）已成为当代自然语言处理（NLP）中的一种关键机制，用于支持大型语言模型（LLM）系统性地获取更丰富的事实性上下文。然而，RAG机制的整合也带来了其固有挑战，因为LLM需要处理可能含噪的上下文。近期研究表明，LLM仍难以批判性地分析基于RAG的上下文信息，这一局限可能导致错误推理和幻觉。本文研究如何通过对比解释激发RAG中的批判性推理。具体而言，我们提出Contrastive-RAG（C-RAG）框架，该框架：（i）根据查询检索相关文档，（ii）选择并示例化相关段落，（iii）生成明确对比各段落相关性的解释，以（iv）支持最终答案。我们展示了C-RAG利用LLM构建对比推理示范来指导较小模型执行检索增强任务的影响。大量实验表明，C-RAG改进了最先进的RAG模型，同时（a）所需提示和示范显著减少，并且（b）对检索文档中的扰动具有鲁棒性。
英文摘要：
Retrieval-augmented generation (RAG) has emerged as a critical mechanism in contemporary NLP to support Large Language Models(LLMs) in systematically accessing richer factual context. However, the integration of RAG mechanisms brings its inherent challenges, as LLMs need to deal with potentially noisy contexts. Recent studies have shown that LLMs still struggle to critically analyse RAG-based in-context information, a limitation that may lead to incorrect inferences and hallucinations. In this paper, we investigate how to elicit critical reasoning in RAG via contrastive explanations. In particular, we propose Contrastive-RAG (C-RAG), a framework that (i) retrieves relevant documents given a query, (ii) selects and exemplifies relevant passages, and (iii) generates explanations that explicitly contrast the relevance of the passages to (iv) support the final answer. We show the impact of C-RAG building contrastive reasoning demonstrations from LLMs to instruct smaller models for retrieval-augmented tasks. Extensive experiments demonstrate that C-RAG improves state-of-the-art RAG models while (a) requiring significantly fewer prompts and demonstrations and (b) being robust to perturbations in the retrieved documents.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
