超越语义相关性：为鲁棒检索增强生成的反事实风险最小化
Beyond Semantic Relevance: Counterfactual Risk Minimization for Robust Retrieval-Augmented Generation
AI总结：
本文提出CoRM-RAG框架，通过因果干预模拟用户偏差来提升检索鲁棒性，在对抗性场景中优于传统检索器和重排序器。
摘要：
标准检索增强生成（RAG）系统主要依赖语义相关性作为效用的代理。然而，在现实决策场景中，用户查询常包含认知偏差，如虚假前提或确认偏见，导致最大化相关性反而促进检索支持幻觉的迎合证据，造成关键失败——'相关性-鲁棒性差距'。为弥合这一差距，我们提出CoRM-RAG框架，通过因果干预引入认知扰动协议，在训练中模拟用户偏差，将其精炼为轻量级证据批评者。该评分模块学习识别具有足够证据强度的文档，以引导模型在对抗性查询扰动下趋向正确性。在决策基准测试中，CoRM-RAG在对抗性场景中显著优于强密集检索器和基于LLM的重排序器，并通过可靠的鲁棒性评分实现有效的风险感知退避。我们的代码可在https://github.com/PeiYangLiu/CoRM-RAG.git获取。
英文摘要：
Standard Retrieval-Augmented Generation (RAG) systems predominantly rely on semantic relevance as a proxy for utility. However, this assumption collapses in realistic decision-making scenarios where user queries are laden with cognitive biases, such as false premises or confirmation bias. In such cases, maximizing relevance paradoxically promotes the retrieval of sycophantic evidence that reinforces hallucinations, a critical failure we term the ``Relevance-Robustness Gap''. To bridge this gap, we propose CoRM-RAG (Counterfactual Risk Minimization for RAG), a framework that aligns retrieval with decision safety rather than mere similarity. Grounded in causal intervention, we introduce a Cognitive Perturbation Protocol to simulate user biases during training, which is then distilled into a lightweight Evidence Critic. This scoring module learns to identify documents that possess sufficient evidential strength to steer the model toward correctness despite adversarial query perturbations. Extensive experiments on decision-making benchmarks demonstrate that CoRM-RAG significantly outperforms strong dense retrievers and LLM-based rerankers in adversarial settings, while enabling effective risk-aware abstention through reliable robustness scoring. Our code is available at https://github.com/PeiYangLiu/CoRM-RAG.git.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
