CIRR: Causal-Invariant Retrieval-Augmented Recommendation with Faithful Explanations under Distribution Shift

TL;DR

CIRR is a recommendation framework that uses causal inference to learn environment-invariant preferences, ensuring robust performance under distribution shifts and providing faithful, interpretable explanations.

Contribution

It introduces a causal-invariant learning approach combined with consistency constraints for faithful explanations in retrieval-augmented recommendation systems.

Findings

Significantly reduces performance degradation under distribution shifts.

Improves faithfulness of explanations by 26%.

Achieves robust recommendation performance in real-world datasets.

Abstract

Recent advances in retrieval-augmented generation (RAG) have shown promise in enhancing recommendation systems with external knowledge. However, existing RAG-based recommenders face two critical challenges: (1) vulnerability to distribution shifts across different environments (e.g., time periods, user segments), leading to performance degradation in out-of-distribution (OOD) scenarios, and (2) lack of faithful explanations that can be verified against retrieved evidence. In this paper, we propose CIRR, a Causal-Invariant Retrieval-Augmented Recommendation framework that addresses both challenges simultaneously. CIRR learns environment-invariant user preference representations through causal inference, which guide a debiased retrieval process to select relevant evidence from multiple sources. Furthermore, we introduce consistency constraints that enforce faithfulness between retrieved evidence, generated explanations, and recommendation outputs. Extensive experiments on two real-world datasets demonstrate that CIRR achieves robust performance under distribution shifts, reducing performance degradation from 15.4% (baseline) to only 5.6% in OOD scenarios, while providing more faithful and interpretable explanations (26% improvement in faithfulness score) compared to state-of-the-art baselines.