{"ID":2873342,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.06472","arxiv_id":"2509.06472","title":"Rethinking LLM Parametric Knowledge as Post-retrieval Confidence for Dynamic Retrieval and Reranking","abstract":"Large Language Models (LLMs) often generate inaccurate responses (hallucinations) when faced with questions beyond their knowledge scope. Retrieval-Augmented Generation (RAG) addresses this by leveraging external knowledge, but a critical challenge remains: determining whether retrieved contexts effectively enhance the model`s ability to answer specific queries. This challenge underscores the importance of knowledge boundary awareness, which current methods-relying on discrete labels or limited signals-fail to address adequately, as they overlook the rich information in LLMs` continuous internal hidden states. To tackle this, we propose a novel post-retrieval knowledge filtering approach. First, we construct a confidence detection model based on LLMs` internal hidden states to quantify how retrieved contexts enhance the model`s confidence. Using this model, we build a preference dataset (NQ_Rerank) to fine-tune a reranker, enabling it to prioritize contexts preferred by the downstream LLM during reranking. Additionally, we introduce Confidence-Based Dynamic Retrieval (CBDR), which adaptively triggers retrieval based on the LLM`s initial confidence in the original question, reducing knowledge conflicts and improving efficiency. Experimental results demonstrate significant improvements in accuracy for context screening and end-to-end RAG performance, along with a notable reduction in retrieval costs while maintaining competitive accuracy.","short_abstract":"Large Language Models (LLMs) often generate inaccurate responses (hallucinations) when faced with questions beyond their knowledge scope. Retrieval-Augmented Generation (RAG) addresses this by leveraging external knowledge, but a critical challenge remains: determining whether retrieved contexts effectively enhance the...","url_abs":"https://arxiv.org/abs/2509.06472","url_pdf":"https://arxiv.org/pdf/2509.06472v2","authors":"[\"Haoxiang Jin\",\"Ronghan Li\",\"Zixiang Lu\",\"Qiguang Miao\"]","published":"2025-09-08T09:37:20Z","proceeding":"cs.IR","tasks":"[\"cs.IR\"]","methods":"[\"RAG\",\"Large Language Model\",\"Language Model\"]","has_code":false}