# RLPF: Reinforcement Learning from Prediction Feedback for User Summarization with LLMs

arXiv: https://arxiv.org/abs/2409.04421 · HTML: https://mlsanity.com/paper/2409.04421/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 34 references that are in the map.
- First posted on arXiv 6 Sep 2024.

## Builds on (most cited first, 25 of 25)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [Adafactor: Adaptive Learning Rates with Sublinear Memory Cost](https://mlsanity.com/paper/1804.04235/) (2018)
- [SummEval: Re-evaluating Summarization Evaluation](https://mlsanity.com/paper/2007.12626/) (2020)
- [RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback](https://mlsanity.com/paper/2309.00267/) (2023)
- [Evaluating the Factual Consistency of Abstractive Text Summarization](https://mlsanity.com/paper/1910.12840/) (2019)
- [Ups and Downs: Modeling the Visual Evolution of Fashion Trends with One-Class Collaborative Filtering](https://mlsanity.com/paper/1602.01585/) (2016)
- [A Discourse-Aware Attention Model for Abstractive Summarization of Long Documents](https://mlsanity.com/paper/1804.05685/) (2018)
- [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)
- [FEQA: A Question Answering Evaluation Framework for Faithfulness Assessment in Abstractive Summarization](https://mlsanity.com/paper/2005.03754/) (2020)
- [QAFactEval: Improved QA-Based Factual Consistency Evaluation for Summarization](https://mlsanity.com/paper/2112.08542/) (2021)
- [Is ChatGPT a Good Recommender? A Preliminary Study](https://mlsanity.com/paper/2304.10149/) (2023)
- [BookSum: A Collection of Datasets for Long-form Narrative Summarization](https://mlsanity.com/paper/2105.08209/) (2021)
- [CTRLsum: Towards Generic Controllable Text Summarization](https://mlsanity.com/paper/2012.04281/) (2020)
- [Towards Question-Answering as an Automatic Metric for Evaluating the Content Quality of a Summary](https://mlsanity.com/paper/2010.00490/) (2020)
- [User-LLM: Efficient LLM Contextualization with User Embeddings](https://mlsanity.com/paper/2402.13598/) (2024)
- [Factually Consistent Summarization via Reinforcement Learning with Textual Entailment Feedback](https://mlsanity.com/paper/2306.00186/) (2023)
- [Can ChatGPT Assess Human Personalities? A General Evaluation Framework](https://mlsanity.com/paper/2303.01248/) (2023)
- [Exploring the Upper Limits of Text-Based Collaborative Filtering Using Large Language Models: Discoveries and Insights](https://mlsanity.com/paper/2305.11700/) (2023)
- [Personalized Showcases: Generating Multi-Modal Explanations for Recommendations](https://mlsanity.com/paper/2207.00422/) (2022)
- [Z-Code++: A Pre-trained Language Model Optimized for Abstractive Summarization](https://mlsanity.com/paper/2208.09770/) (2022)
- [User Embedding Model for Personalized Language Prompting](https://mlsanity.com/paper/2401.04858/) (2024)

## Built on by (most cited first, 13 of 13)

- [Enhancing Personalized Multi-Turn Dialogue with Curiosity Reward](https://mlsanity.com/paper/2504.03206/) (2025)
- [Toward Personalized LLM-Powered Agents: Foundations, Evaluation, and Future Directions](https://mlsanity.com/paper/2602.22680/) (2026)
- [Learning to summarize user information for personalized reinforcement learning from human feedback](https://mlsanity.com/paper/2507.13579/) (2025)
- [TrackRec: Iterative Alternating Feedback with Chain-of-Thought via Preference Alignment for Recommendation](https://mlsanity.com/paper/2508.15388/) (2025)
- [POPI: Personalizing LLMs via Optimized Natural Language Preference Inference](https://mlsanity.com/paper/2510.17881/) (2025)
- [Zero-shot Large Language Models for Automatic Readability Assessment](https://mlsanity.com/paper/2604.24470/) (2026)
- [Know You Before You Speak: User-State Modeling for LLM Personalization in Multi-Turn Conversation](https://mlsanity.com/paper/2605.24647/) (2026)
- [Netflix Artwork Personalization via LLM Post-training](https://mlsanity.com/paper/2601.02764/) (2026)
- [Owen-Shapley Policy Optimization: A Principled RL Algorithm for Generative Search LLMs](https://mlsanity.com/paper/2601.08403/) (2026)
- [FlexRec: Adapting LLM-based Recommenders for Flexible Needs via Reinforcement Learning](https://mlsanity.com/paper/2603.11901/) (2026)
- [Bridging Textual Profiles and Latent User Embeddings for Personalization](https://mlsanity.com/paper/2605.06981/) (2026)
- [RASPER: Reward-Aligned Summarization of Clinical Notes for EHR Outcome Prediction](https://mlsanity.com/paper/2610.02979/) (2026)
- [Vela: User Behavior as Supervision Sparks LLM Intelligence](https://mlsanity.com/paper/2610.14709/) (2026)

## Abstract (arXiv)

LLM-powered personalization agent systems employ Large Language Models (LLMs) to predict users' behavior from their past activities. However, their effectiveness often hinges on the ability to effectively leverage extensive, long user historical data due to its inherent noise and length of such data. Existing pretrained LLMs may generate summaries that are concise but lack the necessary context for downstream tasks, hindering their utility in personalization systems. To address these challenges, we introduce Reinforcement Learning from Prediction Feedback (RLPF). RLPF fine-tunes LLMs to generate concise, human-readable user summaries that are optimized for downstream task performance. By maximizing the usefulness of the generated summaries, RLPF effectively distills extensive user history data while preserving essential information for downstream tasks. Our empirical evaluation demonstrates significant improvements in both extrinsic downstream task utility and intrinsic summary quality, surpassing baseline methods by up to 22% on downstream task performance and achieving an up to 84.59% win rate on Factuality, Abstractiveness, and Readability. RLPF also achieves a remarkable 74% reduction in context length while improving performance on 16 out of 19 unseen tasks and/or datasets, showcasing its generalizability. This approach offers a promising solution for enhancing LLM personalization by effectively transforming long, noisy user histories into informative and human-readable representations.