Beyond Semantic Relevance: Counterfactual Risk Minimization for Robust Retrieval-Augmented Generation
Peiyang Liu, Qiang Yan, Ziqiang Cui, Di Liang, Xi Wang, Wei Ye
Abstract
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.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
- TruthfulQA: Measuring How Models Mimic Human Falsehoods cites Training language models to follow instructions with human feedback
- Training language models to follow instructions with human feedback cites TruthfulQA: Measuring How Models Mimic Human Falsehoods
- TruthfulQA: Measuring How Models Mimic Human Falsehoods cites Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
- Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection cites Training language models to follow instructions with human feedback
- Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection cites Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
- Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection cites Retrieval Augmented Language Model Pre-Training
Builds on37
- Training language models to follow instructions with human feedbackLong Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida et al.NeurIPS 2022 · 24,707 citations
- Retrieval-Augmented Generation for Knowledge-Intensive NLP TasksPatrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni et al.NeurIPS 2020 · 19,162 citations
- TruthfulQA: Measuring How Models Mimic Human FalsehoodsStephanie Lin, Jacob Hilton, Owain EvansACL 2022 · 3,228 citations
- Retrieval Augmented Language Model Pre-TrainingKelvin Guu, Kenton Lee, Zora Tung, Panupong Pasupat et al.ICML 2020 · 2,937 citations
- Self-RAG: Learning to Retrieve, Generate, and Critique through Self-ReflectionAkari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil et al.ICLR 2024 · 1,798 citations
Related papers
- From Extraction to Deduction: Resolving Functional Misalignment in RAG via a Collaborative Critic-Reasoner FrameworkYufei Chen, Yao Wang, Haibin Zhang, Hualin zhou et al.ICML 2026
- Counterfactual Reasoning for Retrieval-Augmented GenerationHuaiyu Qin, Chunyu Wei, Yueguo Chen, Yunhai WangICLR 2026
- Controlling Risk of Retrieval-augmented Generation: A Counterfactual Prompting FrameworkLu Chen, Ruqing Zhang, Jiafeng Guo, Yixing Fan et al.EMNLP Findings 2024 · 7 citations
- Conflict-Aware RAG: Multi-Stage Learning with Conflict Signals for Robust Retrieval-Augmented GenerationHaiyan Wu, Chenchen Wang, Chaoqun Sun, Chengxiong Lu et al.WWW 2026
- Conflict-Aware Soft Prompting for Retrieval-Augmented GenerationEunseong Choi, June Park, Hyeri Lee, Jongwuk LeeEMNLP 2025 · 1 citation
