The Blessing of Reasoning: LLM-Based Contrastive Explanations in Black-Box Recommender Systems

2025-02-24

AI Summary

This work addresses the fundamental trade-off between interpretability and accuracy in black-box recommender systems. We propose LR-Recsys, the first framework that synergistically integrates the intrinsic reasoning capabilities of large language models (LLMs) with deep neural networks (DNNs) without requiring external knowledge injection—enabling end-to-end generation of contrastive natural-language explanations (positive vs. negative rationale) directly embedded within the recommendation prediction pipeline. We theoretically establish that LR-Recsys achieves learning efficiency gains under high-dimensional, multi-environment settings. Empirically, it outperforms state-of-the-art baselines by 3–14% across three real-world datasets. Moreover, the generated explanations are actionable: user studies confirm significant improvements in user trust, platform controllability, and merchant item-selection decision support.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Data Mining & Knowledge Management: Recommender Systems
• Natural Language Processing: (Large) Language Models

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Modern recommender systems use ML models to predict consumer preferences from consumption history. Although these"black-box"models achieve impressive predictive performance, they often suffer from a lack of transparency and explainability. Contrary to the presumed tradeoff between explainability and accuracy, we show that integrating large language models (LLMs) with deep neural networks (DNNs) can improve both. We propose LR-Recsys, which augments DNN-based systems with LLM reasoning capabilities. LR-Recsys introduces a contrastive-explanation generator that produces human-readable positive explanations and negative explanations. These explanations are embedded via a fine-tuned autoencoder and combined with consumer and product features to improve predictions. Beyond offering explainability, we show that LR-Recsys also improves learning efficiency and predictive accuracy, as supported by high-dimensional, multi-environment statistical learning theory. LR-Recsys outperforms state-of-the-art recommender systems by 3-14% on three real-world datasets. Importantly, our analysis reveals that these gains primarily derive from LLMs' reasoning capabilities rather than their external domain knowledge. LR-RecSys presents an effective approach to combine LLMs with traditional DNNs, two of the most widely used ML models today. The explanations generated by LR-Recsys provide actionable insights for consumers, sellers, and platforms, helping to build trust, optimize product offerings, and inform targeting strategies.

Problem

• Enhance transparency in black-box recommender systems
• Integrate LLMs with DNNs for better predictions
• Generate contrastive explanations to improve user trust

Innovation

• Integrates LLMs with DNNs for explainability
• Uses contrastive explanations to enhance predictions
• Improves accuracy and learning efficiency simultaneously