FIRE: Faithful Interpretable Recommendation Explanations

TL;DR

FIRE introduces a novel framework for recommendation explanations that are faithful, diverse, and aligned with model reasoning, moving beyond review-based explanations to improve interpretability and accountability.

Contribution

The paper proposes FIRE, a lightweight, interpretable framework combining SHAP-based attribution with prompt-driven language generation for better explanations.

Findings

FIRE achieves competitive recommendation accuracy.

FIRE produces explanations that are more faithful and user-aligned.

The approach improves explanation diversity and structure.

Abstract

Natural language explanations in recommender systems are often framed as a review generation task, leveraging user reviews as ground-truth supervision. While convenient, this approach conflates a user's opinion with the system's reasoning, leading to explanations that may be fluent but fail to reflect the true logic behind recommendations. In this work, we revisit the core objective of explainable recommendation: to transparently communicate why an item is recommended by linking user needs to relevant item features. Through a comprehensive analysis of existing methods across multiple benchmark datasets, we identify common limitations-explanations that are weakly aligned with model predictions, vague or inaccurate in identifying user intents, and overly repetitive or generic. To overcome these challenges, we propose FIRE, a lightweight and interpretable framework that combines SHAP-based feature attribution with structured, prompt-driven language generation. FIRE produces faithful, diverse, and user-aligned explanations, grounded in the actual decision-making process of the model. Our results demonstrate that FIRE not only achieves competitive recommendation accuracy but also significantly improves explanation quality along critical dimensions such as alignment, structure, and faithfulness. This work highlights the need to move beyond the review-as-explanation paradigm and toward explanation methods that are both accountable and interpretable.