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

arXiv: https://arxiv.org/abs/2509.18980 · HTML: https://mlsanity.com/paper/2509.18980/

## 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 (most cited first, 17 of 17)

- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Chat-REC: Towards Interactive and Explainable LLMs-Augmented Recommender System](https://mlsanity.com/paper/2303.14524/) (2023)
- [Recommender Systems in the Era of Large Language Models (LLMs)](https://mlsanity.com/paper/2307.02046/) (2023)
- [How Can Recommender Systems Benefit from Large Language Models: A Survey](https://mlsanity.com/paper/2306.05817/) (2023)
- [Proxy Tasks and Subjective Measures Can Be Misleading in Evaluating Explainable AI Systems](https://mlsanity.com/paper/2001.08298/) (2020)
- [Towards Human-centered Explainable AI: A Survey of User Studies for Model Explanations](https://mlsanity.com/paper/2210.11584/) (2022)
- [A Survey on LLM-powered Agents for Recommender Systems](https://mlsanity.com/paper/2502.10050/) (2025)
- [Unlocking the Potential of Large Language Models for Explainable Recommendations](https://mlsanity.com/paper/2312.15661/) (2023)
- [RecExplainer: Aligning Large Language Models for Explaining Recommendation Models](https://mlsanity.com/paper/2311.10947/) (2023)
- [ReasoningRec: Bridging Personalized Recommendations and Human-Interpretable Explanations through LLM Reasoning](https://mlsanity.com/paper/2410.23180/) (2024)
- [Exploring the Impact of Large Language Models on Recommender Systems: An Extensive Review](https://mlsanity.com/paper/2402.18590/) (2024)
- [A Survey on Large Language Models for Personalized and Explainable Recommendations](https://mlsanity.com/paper/2311.12338/) (2023)
- [LLM-Powered Explanations: Unraveling Recommendations Through Subgraph Reasoning](https://mlsanity.com/paper/2406.15859/) (2024)
- [LANE: Logic Alignment of Non-tuning Large Language Models and Online Recommendation Systems for Explainable Reason Generation](https://mlsanity.com/paper/2407.02833/) (2024)
- [Bounded Simplex-Structured Matrix Factorization: Algorithms, Identifiability and Applications](https://mlsanity.com/paper/2209.12638/) (2022)
- [Contextualizing Recommendation Explanations with LLMs: A User Study](https://mlsanity.com/paper/2501.12152/) (2025)
- [Can Explanations Improve Recommendations? Evidence from Prediction-Informed Explanations](https://mlsanity.com/paper/2502.16759/) (2025)

## 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.