不微调模型，用自身概率判断该信记忆还是检索结果。
TrustMargin: Training-Free Arbitration between Parametric Memory and Retrieved Evidence in Large Language Models
- 用模型自身似然值计算两个答案的可信度差值
- 在2WIKIMQA和CWQA上超越直接生成与基线RAG
- 适合作为无需训练的通用检索增强方案
大型语言模型在回答知识密集型问题时同时依赖参数化记忆和检索证据，但两者可靠性不一。检索可填补知识空白，但干扰片段可能覆盖正确闭书答案。本文将此生成后冲突视为答案级源仲裁：给定同一冻结模型产生的直接生成答案与RAG答案，决定信任哪个来源。提出TRUSTMARGIN，一种无需训练、即插即用的仲裁层，利用模型自身似然对两个候选答案进行评分。其结合参数先验差距（检验记忆是否接受检索答案）与证据绑定差距（抑制仅依赖片段显著性，衡量问题特异性支持）。TRUSTMARGIN在不微调、无外部判别器或额外生成的前提下，在2WIKIMQA和CWQA数据集上使用三个规模的LLaMA模型，持续优于直接生成与BM25-RAG，恢复了部分直接生成与RAG最优组合间的差距，并泛化至多个无需训练的RAG流程。
原文摘要 · Abstract (English)
Large language models answer knowledge-intensive questions using both parametric memory and retrieved evidence, but neither source is uniformly reliable. Retrieval can fill knowledge gaps, yet distracting passages may override correct closed-book answers. We study this post-generation conflict as answer-level source arbitration: given Direct and RAG answers from the same frozen model, decide which source to trust. We propose TRUSTMARGIN, a training-free, plug-and-play arbitration layer that scores the two existing candidates with the model's own likelihoods. It combines a parametric-prior margin, which tests whether memory accepts the retrieved answer, with an evidence-binding margin, which discounts passage-only salience and measures question-specific support. TRUSTMARGIN selects between Direct and RAG without fine-tuning, external judges, or additional generation. Across 2WIKIMQA and CWQA with three LLaMA scales, TRUSTMARGIN consistently improves over Direct generation and BM25-RAG, recovers part of the Direct/RAG oracle gap, and generalizes to multiple training-free RAG pipelines.
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。