Counterfactual Reasoning for Retrieval-Augmented Generation

ICLR 2026 Conference Submission18985 Authors

Keywords: Retrieval-Augmented Generation, Large Language Models, Counterfactual Reasoning

Abstract: While Retrieval-Augmented Generation (RAG) has advanced knowledge-intensive tasks, we identify a fundamental vulnerability: the Correlation Trap. Existing systems cannot distinguish causally decisive evidence from overwhelmingly correlated yet misleading information, leading to systematic failures. We introduce Counterfactual RAG (CF-RAG), a new framework that operationalizes causal reasoning to overcome this limitation. CF-RAG systematically generates and evaluates counterfactual queries to identify causally relevant distinctions, and employs a parallel arbitration mechanism to reconcile conflicting evidence without interference. On challenging benchmarks, CF-RAG substantially improves robustness against the Correlation Trap, achieving state-of-the-art performance while maintaining comparable efficiency to standard RAG models.

Primary Area: foundation or frontier models, including LLMs

Submission Number: 18985