用多抽象层级检索提升问答准确率，解决信息过载问题
Multiple Abstraction Level Retrieve Augment Generation
- 引入多抽象层级文本块（从句子到文档）进行检索
- 在糖科学领域问答正确率提升25.739%
- 适合需要跨层次知识理解的科研问答场景
基于大语言模型的检索增强生成（RAG）模型能快速适应新数据与知识，且生成结果比预训练模型更专业化。然而，现有方法多依赖固定长度的前缀片段作为参考，仅支持单一抽象层级的问答，难以应对多层级抽象需求。当提供过多细节时，易出现‘迷失中间’问题并超出令牌限制。本文提出一种新型RAG方法，采用多抽象层级（MAL）的文本块——包括多句级、段落级、章节级和文档级——进行检索。在尚未充分探索的糖科学领域验证了该方法的有效性。相比传统单层级RAG，本方法在糖类相关论文上的AI评估问答正确率提升25.739%。
原文摘要 · Abstract (English)
A Retrieval-Augmented Generation (RAG) model powered by a large language model (LLM) provides a faster and more cost-effective solution for adapting to new data and knowledge. It also delivers more specialized responses compared to pre-trained LLMs. However, most existing approaches rely on retrieving prefix-sized chunks as references to support question-answering (Q/A). This approach is often deployed to address information needs at a single level of abstraction, as it struggles to generate answers across multiple levels of abstraction. In an RAG setting, while LLMs can summarize and answer questions effectively when provided with sufficient details, retrieving excessive information often leads to the 'lost in the middle' problem and exceeds token limitations. We propose a novel RAG approach that uses chunks of multiple abstraction levels (MAL), including multi-sentence-level, paragraph-level, section-level, and document-level. The effectiveness of our approach is demonstrated in an under-explored scientific domain of Glycoscience. Compared to traditional single-level RAG approaches, our approach improves AI evaluated answer correctness of Q/A by 25.739\% on Glyco-related papers.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。