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

• URL: http://arxiv.org/abs/2603.03080v1
• Date: Tue, 03 Mar 2026 15:24:51 GMT
• Title: Beyond Factual Correctness: Mitigating Preference-Inconsistent Explanations in Explainable Recommendation
• Authors: Chengkai Wang, Baisong Liu,
• Abstract summary: LLM-based explainable recommenders can produce explanations that are factually correct, yet still justify items using attributes that conflict with a user's historical preferences.<n>We formalize this failure mode and propose PURE, a preference-aware reasoning framework following a select-then-generate paradigm.<n>PURE 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.
• Score: 2.379349092029744
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Towards Generalizable Reasoning: Group Causal Counterfactual Policy Optimization for LLM Reasoning [50.352417879912515]
  Large language models (LLMs) excel at complex tasks with advances in reasoning capabilities.<n>We propose Group Causal Counterfactual Policy Optimization to explicitly train LLMs to learn generalizable reasoning patterns.<n>We then construct token-level advantages from this reward and optimize the policy, encouraging LLMs to favor reasoning patterns that are process-valid and counterfactually robust.
  arXiv  Detail & Related papers  (2026-02-06T08:03:11Z)
• COMMUNITYNOTES: A Dataset for Exploring the Helpfulness of Fact-Checking Explanations [89.37527535663433]
  We present a large-scale dataset of 104k posts with user-provided notes and helpfulness labels.<n>We propose a framework that automatically generates and improves reason definitions via automatic prompt optimization.<n>Our experiments show that the optimized definitions can improve both helpfulness and reason prediction.
  arXiv  Detail & Related papers  (2025-10-28T05:28:47Z)
• MADREC: A Multi-Aspect Driven LLM Agent for Explainable and Adaptive Recommendation [11.430206422495829]
  Multi-Aspect Driven LLM Agent MADRec is an autonomous recommender that constructs user and item profiles by unsupervised extraction of multi-aspect information from reviews.<n>MADRec generates structured profiles via aspect-category-based summarization and applies Re-Ranking to construct high-density inputs.<n>Experiments across multiple domains show that MADRec outperforms traditional and LLM-based baselines in both precision and explainability.
  arXiv  Detail & Related papers  (2025-10-15T10:03:29Z)
• Aligning Deep Implicit Preferences by Learning to Reason Defensively [22.548051297731416]
  We propose Critique-Driven Reasoning Alignment (CDRA) to bridge the preference inference gap.<n>CDRA reframes alignment from a scalar reward-matching task into a structured reasoning process.<n> Experiments demonstrate that CDRA excels at discovering and aligning with users' true preferences while executing robust reasoning.
  arXiv  Detail & Related papers  (2025-10-13T09:26:47Z)
• Mitigating Popularity Bias in Counterfactual Explanations using Large Language Models [1.7771454131646311]
  We propose a pre-processing step that leverages large language models to filter out-of-character history items.<n>We find that it creates counterfactuals that are more closely aligned with each user's popularity preferences than ACCENT alone.
  arXiv  Detail & Related papers  (2025-08-12T13:57:36Z)
• FIRE: Faithful Interpretable Recommendation Explanations [2.6499018693213316]
  Natural language explanations in recommender systems are often framed as a review generation task.<n>Fire is a lightweight and interpretable framework that combines SHAP-based feature attribution with structured, prompt-driven language generation.<n>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.
  arXiv  Detail & Related papers  (2025-08-07T10:11:02Z)
• SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models [55.60306377044225]
  "SelfCheckGPT" is a simple sampling-based approach to fact-check the responses of black-box models. We investigate this approach by using GPT-3 to generate passages about individuals from the WikiBio dataset.
  arXiv  Detail & Related papers  (2023-03-15T19:31:21Z)
• Explanation Selection Using Unlabeled Data for Chain-of-Thought Prompting [80.9896041501715]
  Explanations that have not been "tuned" for a task, such as off-the-shelf explanations written by nonexperts, may lead to mediocre performance. This paper tackles the problem of how to optimize explanation-infused prompts in a blackbox fashion.
  arXiv  Detail & Related papers  (2023-02-09T18:02:34Z)
• CoP: Factual Inconsistency Detection by Controlling the Preference [45.4045488637761]
  We propose an unsupervised framework named CoP by controlling the preference of the generation model with the help of prompt. With the properly designed prompt, our framework could evaluate specific preferences and serve as measurements for fine-grained categories of inconsistency. Experiments show that our framework achieves new SOTA results on three factual inconsistency detection tasks.
  arXiv  Detail & Related papers  (2022-12-03T13:05:24Z)
• ADEPT: A DEbiasing PrompT Framework [64.54665501064659]
  Finetuning is an applicable approach for debiasing contextualized word embeddings.<n> discrete prompts with semantic meanings have shown to be effective in debiasing tasks.<n>We propose ADEPT, a method to debias PLMs using prompt tuning while maintaining the delicate balance between removing biases and ensuring representation ability.
  arXiv  Detail & Related papers  (2022-11-10T08:41:40Z)
• Logical Satisfiability of Counterfactuals for Faithful Explanations in NLI [60.142926537264714]
  We introduce the methodology of Faithfulness-through-Counterfactuals. It generates a counterfactual hypothesis based on the logical predicates expressed in the explanation. It then evaluates if the model's prediction on the counterfactual is consistent with that expressed logic.
  arXiv  Detail & Related papers  (2022-05-25T03:40:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.