用注入知识的压缩器，让医疗问答更准更可信。
K-COMP: Retrieval-Augmented Medical Domain Question Answering With Knowledge-Injected Compressor
- 先生成答题所需先验知识，再压缩检索文本
- 压缩后上下文与问题意图对齐，减少误导信息
- 适合需要高精度医疗问答的场景
检索增强型问答（QA）通过引入外部信息提升缺乏领域知识的阅读模型的准确性。然而，封闭领域检索到的文档需要专业知识才能理解，且包含数千个标记，其中部分与问题无关，可能包含错误信息，导致阅读模型不信任文本并产生幻觉。为此，我们提出K-comp（知识注入压缩器），在压缩检索文本前自动生成回答所需的先验知识，并将该知识融入压缩过程，实现问题意图与压缩后上下文的对齐。通过增强先验知识与精炼上下文，引导阅读模型聚焦相关答案，提升其对上下文的信任度。
原文摘要 · Abstract (English)
Retrieval-augmented question answering (QA) integrates external information and thereby increases the QA accuracy of reader models that lack domain knowledge. However, documents retrieved for closed domains require high expertise, so the reader model may have difficulty fully comprehending the text. Moreover, the retrieved documents contain thousands of tokens, some unrelated to the question. As a result, the documents include some inaccurate information, which could lead the reader model to mistrust the passages and could result in hallucinations. To solve these problems, we propose K-comp (Knowledge-injected compressor) which provides the knowledge required to answer correctly. The compressor automatically generates the prior knowledge necessary to facilitate the answer process prior to compression of the retrieved passages. Subsequently, the passages are compressed autoregressively, with the generated knowledge being integrated into the compression process. This process ensures alignment between the question intent and the compressed context. By augmenting this prior knowledge and concise context, the reader models are guided toward relevant answers and trust the context.
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。