{"ID":5938000,"CreatedAt":"2026-07-07T03:14:33.014478982Z","UpdatedAt":"2026-07-07T15:35:27.467248499Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.03929","arxiv_id":"2607.03929","title":"Probe, Don't Prompt: A Hidden-State Probe for Metadata Filtering in Multi-Meta-RAG","abstract":"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.","short_abstract":"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...","url_abs":"https://arxiv.org/abs/2607.03929","url_pdf":"https://arxiv.org/pdf/2607.03929v1","authors":"[\"Mykhailo Poliakov\",\"Nadiya Shvai\"]","published":"2026-07-04T15:47:38Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.AI\",\"cs.LG\"]","methods":"[\"Language Model\"]","has_code":false,"code_links":[{"ID":614004,"CreatedAt":"2026-07-07T03:14:33.014478982Z","UpdatedAt":"2026-07-07T03:14:33.014478982Z","DeletedAt":null,"paper_id":5938000,"paper_url":"https://arxiv.org/abs/2607.03929","paper_title":"Probe, Don't Prompt: A Hidden-State Probe for Metadata Filtering in Multi-Meta-RAG","repo_url":"https://github.com/mxpoliakov/Multi-Meta-RAG","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}