IRMay 1

Can Explanations Improve Recommendations? Evidence from Prediction-Informed Explanations

arXiv:2502.1675984.12 citationsh-index: 4
AI Analysis

For recommender system designers, this work shows that explanations can improve rather than hinder performance, offering a new design paradigm for trust and data efficiency.

The paper tackles the trade-off between accuracy and explainability in recommender systems, proposing RecPIE, a framework that jointly optimizes predictions and LLM-generated explanations. RecPIE improves predictive accuracy by 3-4% over SOTA baselines, matches best performance with only 12% of training data, and is preferred 61.5% of the time in human evaluations.

Recommender systems are central to digital platforms, yet they face a fundamental trade-off between accuracy and explainability. Black-box models achieve strong performance but lack interpretability needed for trust and adoption. Existing explainable AI approaches either treat explanations as post-hoc or at the cost of accuracy. We challenge this view, proposing that explanations, when designed as an integral component of a system and aligned with prediction outcomes, can improve both interpretability and performance. We introduce RecPIE (Recommendation with Prediction-Informed Explanations), a framework that jointly optimizes recommendation predictions and natural-language explanations generated by LLMs. RecPIE embeds explanation generation into the learning loop: predictions guide explanation generation (prediction-informed explanations), which are fed back to refine subsequent predictions (explanation-informed predictions) via alternating training. The LLM is fine-tuned using LoRA and reinforcement learning with a customized reward derived from recommendation accuracy. Drawing on multi-environment statistical learning theory, we formally ground why explanation generation and prediction can be mutually reinforcing. We evaluate RecPIE on large-scale point-of-interest recommendation data from Google Maps, where user preferences span diverse place categories. RecPIE improves predictive accuracy by 3-4% over state-of-the-art baselines and matches the best performing model using only 12% of the training data. In human evaluations with 566 participants, RecPIE explanations are preferred 61.5% of the time (versus 16.6% for the best baseline) and rated closer to human-generated explanations. These results reframe explainability not as a constraint on performance but as a design lever for improving AI systems, with implications for trust, data efficiency, and marketplace deployment.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes