用大模型生成搜索结果的解释，提升用户定位信息效率
Generating Search Explanations using Large Language Models
- 用编码器-解码器和仅解码器大模型生成搜索解释
- 生成解释比基线模型更准确、更可信
- 适合需要可解释搜索系统的研究人员和开发者
面向特定方面的搜索结果解释通常为简洁文本片段，置于检索文档旁，帮助用户高效定位相关信息。尽管大型语言模型（LLMs）在多项任务中表现出色，但其在生成搜索结果解释方面的潜力尚未被探索。本研究通过利用编码器-解码器和仅解码器类大模型，生成搜索结果的解释。实验表明，所生成的解释在准确性和可信度上均优于多种基线模型。
原文摘要 · Abstract (English)
Aspect-oriented explanations in search results are typically concise text snippets placed alongside retrieved documents to serve as explanations that assist users in efficiently locating relevant information. While Large Language Models (LLMs) have demonstrated exceptional performance for a range of problems, their potential to generate explanations for search results has not been explored. This study addresses that gap by leveraging both encoder-decoder and decoder-only LLMs to generate explanations for search results. The explanations generated are consistently more accurate and plausible explanations than those produced by a range of baseline models.
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。