mlsanityData to 14 Oct 2026

From latent factors to language: a user study on LLM-generated explanations for an inherently interpretable matrix-based recommender system

arXiv 2509.18980 ↗First posted 23 Sep 2025cs.AI cs.HC cs.IRcited by 0

Not on the map. Why?

Abstract (arXiv)

We investigate whether large language models (LLMs) can generate effective, user-facing explanations from a mathematically interpretable recommendation model. The model is based on constrained matrix factorization, where user types are explicitly represented and predicted item scores share the same scale as observed ratings, making the model's internal representations and predicted scores directly interpretable. This structure is translated into natural language explanations using carefully designed LLM prompts. Many works in explainable AI rely on automatic evaluation metrics, which often fail to capture users' actual needs and perceptions. In contrast, we adopt a user-centered approach: we conduct a study with 326 participants who assessed the quality of the explanations across five key dimensions-transparency, effectiveness, persuasion, trust, and satisfaction-as well as the recommendations themselves. To evaluate how different explanation strategies are perceived, we generate multiple explanation types from the same underlying model, varying the input information provided to the LLM. Our analysis reveals that all explanation types are generally well received, with moderate statistical differences between strategies. User comments further underscore how participants react to each type of explanation, offering complementary insights beyond the quantitative results.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 17 of its 37 references that are in the map. First posted on arXiv 23 Sep 2025.

Builds on

17 of 37 references.

References · 17

  1. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  2. 2023Chat-REC: Towards Interactive and Explainable LLMs-Augmented Recommender Systemcited by 242
  3. 2023Recommender Systems in the Era of Large Language Models (LLMs)cited by 189
  4. 2023How Can Recommender Systems Benefit from Large Language Models: A Surveycited by 142
  5. 2020Proxy Tasks and Subjective Measures Can Be Misleading in Evaluating Explainable AI Systemscited by 139
  6. 2022Towards Human-centered Explainable AI: A Survey of User Studies for Model Explanationscited by 85
  7. 2025A Survey on LLM-powered Agents for Recommender Systemscited by 50
  8. 2023Unlocking the Potential of Large Language Models for Explainable Recommendationscited by 18
  9. 2023RecExplainer: Aligning Large Language Models for Explaining Recommendation Modelscited by 14
  10. 2024ReasoningRec: Bridging Personalized Recommendations and Human-Interpretable Explanations through LLM Reasoningcited by 14
  11. 2024Exploring the Impact of Large Language Models on Recommender Systems: An Extensive Reviewcited by 12
  12. 2023A Survey on Large Language Models for Personalized and Explainable Recommendationscited by 11
5 more
  1. 2024LLM-Powered Explanations: Unraveling Recommendations Through Subgraph Reasoningcited by 10
  2. 2024LANE: Logic Alignment of Non-tuning Large Language Models and Online Recommendation Systems for Explainable Reason Generationcited by 6
  3. 2022Bounded Simplex-Structured Matrix Factorization: Algorithms, Identifiability and Applicationscited by 5
  4. 2025Contextualizing Recommendation Explanations with LLMs: A User Studycited by 4
  5. 2025Can Explanations Improve Recommendations? Evidence from Prediction-Informed Explanationscited by 1

Built on by

Not cited yet.