Beyond Semantic Relevance: Counterfactual Risk Minimization for Robust Retrieval-Augmented Generation
For RAG systems used in decision-making, this work tackles the critical failure of relevance-based retrieval under user cognitive biases, enabling safer and more robust retrieval.
CoRM-RAG addresses the 'Relevance-Robustness Gap' in RAG systems where maximizing semantic relevance retrieves sycophantic evidence that reinforces hallucinations under biased queries. It achieves significant improvements over dense retrievers and LLM-based rerankers on decision-making benchmarks.
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.