arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2412.02563cs.CLcs.AI
收藏

检索增强生成中的语义 Token

Semantic Tokens in Retrieval Augmented Generation

Joel Suro

AI总结:

本文提出 Comparative RAG,通过评估器比较外部建议与检索文档块,使结果兼具语义相关性与逻辑可验证性,从而提升 RAG 问答的准确性、可靠性与可扩展性。

摘要:

检索增强生成(Retrieval-Augmented Generation,RAG)架构近期因其提升自然语言处理任务中事实依据与连贯性的能力而受到广泛关注。然而,随着 RAG 系统访问数据量的增加,其生成准确答案的可靠性会下降。即使在较小的数据集上,这些系统有时也无法处理简单查询。该问题源于它们依赖最先进的大语言模型(LLM),而 LLM 可能会给系统输出引入不确定性。在本研究中,我提出了一种新颖的 Comparative RAG 系统,该系统引入评估器模块,以弥合概率性 RAG 系统与可确定性验证的响应之间的差距。评估器将外部建议与检索到的文档块进行比较,并增加一个决策层,从而增强系统的可靠性。该方法确保检索到的文档块既具有语义相关性,又与确定性洞察在逻辑上保持一致,从而提高 RAG 系统的准确性和整体效率。该框架为在要求高精度和可验证性的领域中构建更可靠、可扩展的问答应用铺平了道路。

英文摘要:

Retrieval-Augmented Generation (RAG) architectures have recently garnered significant attention for their ability to improve truth grounding and coherence in natural language processing tasks. However, the reliability of RAG systems in producing accurate answers diminishes as the volume of data they access increases. Even with smaller datasets, these systems occasionally fail to address simple queries. This issue arises from their dependence on state-of-the-art large language models (LLMs), which can introduce uncertainty into the system's outputs. In this work, I propose a novel Comparative RAG system that introduces an evaluator module to bridge the gap between probabilistic RAG systems and deterministically verifiable responses. The evaluator compares external recommendations with the retrieved document chunks, adding a decision-making layer that enhances the system's reliability. This approach ensures that the chunks retrieved are both semantically relevant and logically consistent with deterministic insights, thereby improving the accuracy and overall efficiency of RAG systems. This framework paves the way for more reliable and scalable question-answering applications in domains requiring high precision and verifiability.

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。

↑