探测而非提示：用于多元RAG中元数据过滤的隐藏状态探测器
Probe, Don't Prompt: A Hidden-State Probe for Metadata Filtering in Multi-Meta-RAG
- National University of Kyiv-Mohyla Academy（基辅莫希拉学院国家大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
研究改进多跳问答检索，用基于小型开源语言模型隐藏状态训练的确定性探测器取代专有提取器，探测器在准确率上有优势且输出空间固定，介绍了使其工作的设计选择及低成本输出方式。
AI中文摘要：
多元RAG通过提示gpt - 3.5 - turbo从每个查询中提取元数据（新闻源）来过滤向量存储，改进多跳问答检索。本文表明可用基于小型开源语言模型隐藏状态训练的本地确定性探测器取代此专有提取器。探测器在准确率上有优势，介绍了其工作的设计选择及低成本输出方式，代码可获取。
英文摘要：
Multi-Meta-RAG improves retrieval for multi-hop question answering by filtering a vector store on metadata (the news source) that it extracts from each query by prompting gpt-3.5-turbo. We show this proprietary, free-form extractor can be replaced by a local, deterministic probe trained on the hidden states of a small open-source language model. On all 2556 MultiHop-RAG queries the probe reaches 90.9% set-exact accuracy against 88.0% for a model-free substring baseline and 80.9% for GPT-3.5, a margin that comes entirely from null queries, on which GPT-3.5 never abstains; on non-null queries all three stay within about a point. Because the probe's output space is exactly the fixed 49-source vocabulary, it cannot drift outside the allow-list as the prompted model does. Three design choices make it work: selecting a shallow layer, mean pooling, and class-imbalance-aware multi-label training over the long tail of sources. A 135M-parameter model lands within ~1.5 points of a 1.5B one, so the filter is cheap to output: a partial forward pass through the first few layers plus one linear head, with no API. The code is available at https://github.com/mxpoliakov/Multi-Meta-RAG.
