# PrLM: Learning Explicit Reasoning for Personalized RAG via Contrastive Reward Optimization

arXiv: https://arxiv.org/abs/2508.07342 · HTML: https://mlsanity.com/paper/2508.07342/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning.
- Builds on 24 of its 37 references that are in the map.
- First posted on arXiv 10 Aug 2025.

## Placed in

- LLM reasoning / [Knowledge- and tool-augmented reasoning](https://mlsanity.com/lr/knowledge-and-tool-augmented-reasoning/)
- Retrieval-augmented generation / [RAG pipeline design and evaluation](https://mlsanity.com/rag/rag-pipeline-design-and-evaluation/)
- LLM alignment / RLHF / preference optimisation / [Preference alignment for recommenders and RAG](https://mlsanity.com/alignment/preference-alignment-for-recommenders-and-rag/)

## Builds on (most cited first, 24 of 24)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [C-Pack: Packed Resources For General Chinese Embeddings](https://mlsanity.com/paper/2309.07597/) (2023)
- [LIMO: Less is More for Reasoning](https://mlsanity.com/paper/2502.03387/) (2025)
- [L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning](https://mlsanity.com/paper/2503.04697/) (2025)
- [Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models](https://mlsanity.com/paper/2503.09567/) (2025)
- [From System 1 to System 2: A Survey of Reasoning Large Language Models](https://mlsanity.com/paper/2502.17419/) (2025)
- [Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models](https://mlsanity.com/paper/2501.09686/) (2025)
- [HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMs](https://mlsanity.com/paper/2412.18925/) (2024)
- [Logic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement Learning](https://mlsanity.com/paper/2502.14768/) (2025)
- [Pearl: Personalizing Large Language Model Writing Assistants with Generation-Calibrated Retrievers](https://mlsanity.com/paper/2311.09180/) (2023)
- [Teach LLMs to Personalize -- An Approach inspired by Writing Education](https://mlsanity.com/paper/2308.07968/) (2023)
- [Integrating Summarization and Retrieval for Enhanced Personalization via Large Language Models](https://mlsanity.com/paper/2310.20081/) (2023)
- [Rec-R1: Bridging Generative Large Language Models and User-Centric Recommendation Systems via Reinforcement Learning](https://mlsanity.com/paper/2503.24289/) (2025)
- [Retrieval Augmented Generation with Collaborative Filtering for Personalized Text Generation](https://mlsanity.com/paper/2504.05731/) (2025)
- [CitaLaw: Enhancing LLM with Citations in Legal Domain](https://mlsanity.com/paper/2412.14556/) (2024)
- [QE-RAG: A Robust Retrieval-Augmented Generation Benchmark for Query Entry Errors](https://mlsanity.com/paper/2504.04062/) (2025)
- [Legal Mathematical Reasoning with LLMs: Procedural Alignment through Two-Stage Reinforcement Learning](https://mlsanity.com/paper/2504.02590/) (2025)
- [Beyond Guilt: Legal Judgment Prediction with Trichotomous Reasoning](https://mlsanity.com/paper/2412.14588/) (2024)
- [Bridging Search and Recommendation through Latent Cross Reasoning](https://mlsanity.com/paper/2508.04152/) (2025)
- [Unified Generative Search and Recommendation](https://mlsanity.com/paper/2504.05730/) (2025)
- [An Explicit Syllogistic Legal Reasoning Framework for Large Language Models](https://mlsanity.com/paper/2504.04042/) (2025)
- [Balancing Stylization and Truth via Disentangled Representation Steering](https://mlsanity.com/paper/2508.04530/) (2025)
- [Benefit from Rich: Tackling Search Interaction Sparsity in Search Enhanced Recommendation](https://mlsanity.com/paper/2508.04145/) (2025)

## Built on by (most cited first, 8 of 8)

- [Tagging the Thought: Unlocking Personalization Reasoning via Reinforcement Learning](https://mlsanity.com/paper/2509.23140/) (2025)
- [Rethinking Reasoning: A Survey on Reasoning-based Backdoors in LLMs](https://mlsanity.com/paper/2510.07697/) (2025)
- [Training LLMs with Reinforcement Learning for Intent-Aware Personalized Question Answering](https://mlsanity.com/paper/2605.12645/) (2026)
- [Preference-Aware Rubric Learning for Personalized Evaluation](https://mlsanity.com/paper/2605.31545/) (2026)
- [Improving User Privacy in Personalized Generation: Client-Side Retrieval-Augmented Modification of Server-Side Generated Speculations](https://mlsanity.com/paper/2601.17569/) (2026)
- [ReLay: Personalized LLM-Generated Plain-Language Summaries for Better Understanding, but at What Cost?](https://mlsanity.com/paper/2605.00468/) (2026)
- [Forgotten History or Test-of-Time? Retrospect and Prospect on RAG from an IR Perspective](https://mlsanity.com/paper/2608.08445/) (2026)
- [Rubric-Aware On-Policy Self-Distillation for LLM Personalization](https://mlsanity.com/paper/2609.35262/) (2026)

## Abstract (arXiv)

Personalized retrieval-augmented generation (RAG) aims to produce user-tailored responses by incorporating retrieved user profiles alongside the input query. Existing methods primarily focus on improving retrieval and rely on large language models (LLMs) to implicitly integrate the retrieved context with the query. However, such models are often sensitive to retrieval quality and may generate responses that are misaligned with user preferences. To address this limitation, we propose PrLM, a reinforcement learning framework that trains LLMs to explicitly reason over retrieved user profiles. Guided by a contrastively trained personalization reward model, PrLM effectively learns from user responses without requiring annotated reasoning paths. Experiments on three personalized text generation datasets show that PrLM outperforms existing methods and remains robust across varying numbers of retrieved profiles and different retrievers.