# Shielded RecRL: Explanation Generation for Recommender Systems without Ranking Degradation

arXiv: https://arxiv.org/abs/2601.03608 · HTML: https://mlsanity.com/paper/2601.03608/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 30 references that are in the map.
- First posted on arXiv 14 Oct 2025.

## Builds on (most cited first, 20 of 20)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation](https://mlsanity.com/paper/2002.02126/) (2020)
- [Image-based Recommendations on Styles and Substitutes](https://mlsanity.com/paper/1506.04757/) (2015)
- [Neural Graph Collaborative Filtering](https://mlsanity.com/paper/1905.08108/) (2019)
- [Graph Neural Networks in Recommender Systems: A Survey](https://mlsanity.com/paper/2011.02260/) (2020)
- [A Survey on Large Language Models for Recommendation](https://mlsanity.com/paper/2305.19860/) (2023)
- [TALLRec: An Effective and Efficient Tuning Framework to Align Large Language Model with Recommendation](https://mlsanity.com/paper/2305.00447/) (2023)
- [Variational Autoencoders for Collaborative Filtering](https://mlsanity.com/paper/1802.05814/) (2018)
- [Explainable Recommendation: A Survey and New Perspectives](https://mlsanity.com/paper/1804.11192/) (2018)
- [Do LLMs Understand User Preferences? Evaluating LLMs On User Rating Prediction](https://mlsanity.com/paper/2305.06474/) (2023)
- [A Survey on Accuracy-oriented Neural Recommendation: From Collaborative Filtering to Information-rich Recommendation](https://mlsanity.com/paper/2104.13030/) (2021)
- [Neural Rating Regression with Abstractive Tips Generation for Recommendation](https://mlsanity.com/paper/1708.00154/) (2017)
- [PRINCE: Provider-side Interpretability with Counterfactual Explanations in Recommender Systems](https://mlsanity.com/paper/1911.08378/) (2019)
- [Towards Next-Generation LLM-based Recommender Systems: A Survey and Beyond](https://mlsanity.com/paper/2410.19744/) (2024)
- [Automatic Generation of Natural Language Explanations](https://mlsanity.com/paper/1707.01561/) (2017)

## Abstract (arXiv)

We introduce Shielded RecRL, a reinforcement learning approach to generate personalized explanations for recommender systems without sacrificing the system's original ranking performance. Unlike prior RLHF-based recommender methods that directly optimize item rankings, our two-tower architecture keeps the recommender's ranking model intact while a language model learns to produce helpful explanations. We design a composite reward signal combining explanation length, content relevance, and coherence, and apply proximal policy optimization (PPO) with a KL-divergence constraint to fine-tune a large language model with only 0.4% of its parameters trainable via LoRA adapters. In experiments on an Amazon Books dataset (approximately 50K interactions in the fantasy and romance genres), Shielded RecRL improved the relative click-through rate (CTR) by 22.5% (1.225x over baseline) while keeping the recommender's item-ranking behavior virtually unchanged. An extensive ablation study confirms that our gradient shielding strategy and reward design effectively balance explanation quality and policy drift. Our results demonstrate that Shielded RecRL enhances user-facing aspects of recommendations through rich, personalized explanations without degrading core recommendation accuracy.