Beyond Factual Correctness: Mitigating Preference-Inconsistent Explanations in Explainable Recommendation

TL;DR

This paper introduces PURE, a framework that improves explainable recommendation systems by selecting user-preference-aligned evidence to generate more convincing and trustworthy explanations.

Contribution

PURE is a novel preference-aware reasoning framework that intervenes in evidence selection and uses structure-aware prompting to reduce preference-inconsistent explanations.

Findings

PURE reduces preference-inconsistent explanations in experiments

PURE maintains recommendation accuracy and explanation quality

PURE suppresses factual hallucinations in explanations

Abstract

LLM-based explainable recommenders can produce fluent explanations that are factually correct, yet still justify items using attributes that conflict with a user's historical preferences. Such preference-inconsistent explanations yield logically valid but unconvincing reasoning and are largely missed by standard hallucination or faithfulness metrics. We formalize this failure mode and propose PURE, a preference-aware reasoning framework following a select-then-generate paradigm. Instead of only improving generation, PURE intervenes in evidence selection, it selects a compact set of multi-hop item-centric reasoning paths that are both factually grounded and aligned with user preference structure, guided by user intent, specificity, and diversity to suppress generic, weakly personalized evidence. The selected evidence is then injected into LLM generation via structure-aware prompting that preserves relational constraints. To measure preference inconsistency, we introduce a feature-level, user-centric evaluation metric that reveals misalignment overlooked by factuality-based measures. Experiments on three real-world datasets show that PURE consistently reduces preference-inconsistent explanations and factual hallucinations while maintaining competitive recommendation accuracy, explanation quality, and inference efficiency. These results highlight that trustworthy explanations require not only factual correctness but also justification aligned with user preferences.