# Learning to summarize user information for personalized reinforcement learning from human feedback

arXiv: https://arxiv.org/abs/2507.13579 · HTML: https://mlsanity.com/paper/2507.13579/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Placed in Human values and AI feedback alignment, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 27 of its 35 references that are in the map.
- First posted on arXiv 17 Jul 2025.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Human values and AI feedback alignment](https://mlsanity.com/alignment/human-values-and-ai-feedback-alignment/)

## Builds on (most cited first, 27 of 27)

- [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)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [High-Dimensional Continuous Control Using Generalized Advantage Estimation](https://mlsanity.com/paper/1506.02438/) (2015)
- [SimPO: Simple Preference Optimization with a Reference-Free Reward](https://mlsanity.com/paper/2405.14734/) (2024)
- [The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games](https://mlsanity.com/paper/2103.01955/) (2021)
- [LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation Dataset](https://mlsanity.com/paper/2309.11998/) (2023)
- [Benchmarking Large Language Models for News Summarization](https://mlsanity.com/paper/2301.13848/) (2023)
- [UltraFeedback: Boosting Language Models with Scaled AI Feedback](https://mlsanity.com/paper/2310.01377/) (2023)
- [Is Independent Learning All You Need in the StarCraft Multi-Agent Challenge?](https://mlsanity.com/paper/2011.09533/) (2020)
- [A Roadmap to Pluralistic Alignment](https://mlsanity.com/paper/2402.05070/) (2024)
- [Personalizing Reinforcement Learning from Human Feedback with Variational Preference Learning](https://mlsanity.com/paper/2408.10075/) (2024)
- [The PRISM Alignment Dataset: What Participatory, Representative and Individualised Human Feedback Reveals About the Subjective and Multicultural Alignment of Large Language Models](https://mlsanity.com/paper/2404.16019/) (2024)
- [Distributional Preference Learning: Understanding and Accounting for Hidden Context in RLHF](https://mlsanity.com/paper/2312.08358/) (2023)
- [Personalized Language Modeling from Personalized Human Feedback](https://mlsanity.com/paper/2402.05133/) (2024)
- [Value Kaleidoscope: Engaging AI with Pluralistic Human Values, Rights, and Duties](https://mlsanity.com/paper/2309.00779/) (2023)
- [Group Preference Optimization: Few-Shot Alignment of Large Language Models](https://mlsanity.com/paper/2310.11523/) (2023)
- [The Past, Present and Better Future of Feedback Learning in Large Language Models for Subjective Human Preferences and Values](https://mlsanity.com/paper/2310.07629/) (2023)
- [The Trickle-down Impact of Reward (In-)consistency on RLHF](https://mlsanity.com/paper/2309.16155/) (2023)
- [Learning to Summarize from LLM-generated Feedback](https://mlsanity.com/paper/2410.13116/) (2024)
- [MallowsPO: Fine-Tune Your LLM with Preference Dispersions](https://mlsanity.com/paper/2405.14953/) (2024)
- [RLPF: Reinforcement Learning from Prediction Feedback for User Summarization with LLMs](https://mlsanity.com/paper/2409.04421/) (2024)
- [A Shared Low-Rank Adaptation Approach to Personalized RLHF](https://mlsanity.com/paper/2503.19201/) (2025)

## Built on by (most cited first, 10 of 10)

- [Toward Personalized LLM-Powered Agents: Foundations, Evaluation, and Future Directions](https://mlsanity.com/paper/2602.22680/) (2026)
- [POPI: Personalizing LLMs via Optimized Natural Language Preference Inference](https://mlsanity.com/paper/2510.17881/) (2025)
- [Text as a Universal Interface for Transferable Personalization](https://mlsanity.com/paper/2601.04963/) (2026)
- [PRISM-X: Experiments on Personalised Fine-Tuning with Human and Simulated Users](https://mlsanity.com/paper/2605.13307/) (2026)
- [Learning to Adapt Cross-Domain Preferences via Meta-LoRA for LLM Personalization](https://mlsanity.com/paper/2608.12389/) (2026)
- [Hypotheses-Guided Self Distillation for Continual Personalization](https://mlsanity.com/paper/2609.00251/) (2026)
- [Maximizing Mutual Information Between Prompt and Response Improves LLM Performance With No Additional Data](https://mlsanity.com/paper/2603.19294/) (2026)
- [Learning Preference Adaptation for Large Language Model Personalization via Verbal Reinforcement Learning](https://mlsanity.com/paper/2608.09507/) (2026)
- [Using Context Is Not Enough: Test-Time Training for Personalized Reward Modeling](https://mlsanity.com/paper/2609.35109/) (2026)
- [Gradient-Aligned Pair Selection for Personalized Preference Optimization](https://mlsanity.com/paper/2610.00061/) (2026)

## Abstract (arXiv)

As everyday use cases of large language model (LLM) AI assistants have expanded, it is becoming increasingly important to personalize responses to align to different users' preferences and goals. While reinforcement learning from human feedback (RLHF) is effective at improving LLMs to be generally more helpful and fluent, it does not account for variability across users, as it models the entire user population with a single reward model, meaning it assumes that everyone's preferences are the same. We present a novel framework, Preference Learning Using Summarization (PLUS), that uses reinforcement learning (RL) to learn to produce text-based summaries of each user's preferences, characteristics, and past conversations. These summaries condition the reward model, enabling it to make personalized predictions about the types of responses valued by each user. Both the user-summarization model and reward model are trained simultaneously, creating an online co-adaptation loop. We show that in contrast to the standard Bradley-Terry model, summaries produced by PLUS capture diverse aspects of user preferences, achieving a 11-77/% improvement in reward model accuracy. Key strengths of PLUS are: (1) robust performance with new users and conversation topics, achieving a 25% improvement over the best personalized reward model technique used for RLHF; (2) zero-shot personalization with state-of-the-art proprietary models like GPT-4 (e.g., PLUS-summary-conditioned responses achieved a 72% win rate compared to 28% for default GPT-4o); (3) learning from flexible user contexts beyond preference labels, and (4) interpretable representation of users, enabling greater transparency and user control in pluralistic LLM alignment.