新闻
Tracing and Taming Hallucinated Terms via Subsequence-Association Filtering and Breadth-Aware Selection for LLM Query Expansion
arXiv cs.AI · 发布于 · 阅读约3分钟
30秒读懂
- 发生了什么
- Researchers propose SAFE-QE, a method to filter hallucinated terms from LLM-generated query expansions using corpus reproducibility and coverage optimization.
- 为何重要
- Search engineers building retrieval systems should care when using LLMs to expand queries, as hallucinations degrade ranking quality.
- 注意
- The method is evaluated only on TREC and BEIR benchmarks; real-world performance on production search systems remains undemonstrated.
- llm
- language model
- retriever
- hallucinat
这条新闻背后的模式
- Query Transformation Retrieval
- Cost-Aware Model Selection
- Structure-Aware Codebase Retrieval (Repo Map)
每个模式都讲清楚技术如何运作、何时值得投入，以及在哪里会失效。
The Agent Architect
每周一个模式、一个权衡、一个生产事故案例。为构建智能体系统的人准备的每周简报。
每周一封邮件,一键退订。您的地址仅用于发送简报。