# COPE: Continual Personalization of LLMs under Sparse User Feedback via User Embeddings and Self-Evaluation

arXiv: https://arxiv.org/abs/2609.26853 · HTML: https://mlsanity.com/paper/2609.26853/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 35 references that are in the map.
- First posted on arXiv 22 Sep 2026.

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

- [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)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [High-Dimensional Continuous Control Using Generalized Advantage Estimation](https://mlsanity.com/paper/1506.02438/) (2015)
- [Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models](https://mlsanity.com/paper/2506.05176/) (2025)
- [Instruction-Following Evaluation for Large Language Models](https://mlsanity.com/paper/2311.07911/) (2023)
- [Aligning AI With Shared Human Values](https://mlsanity.com/paper/2008.02275/) (2020)
- [LaMP: When Large Language Models Meet Personalization](https://mlsanity.com/paper/2304.11406/) (2023)
- [Fine-Grained Human Feedback Gives Better Rewards for Language Model Training](https://mlsanity.com/paper/2306.01693/) (2023)
- [Distributional Preference Learning: Understanding and Accounting for Hidden Context in RLHF](https://mlsanity.com/paper/2312.08358/) (2023)
- [Beyond One-Preference-Fits-All Alignment: Multi-Objective Direct Preference Optimization](https://mlsanity.com/paper/2310.03708/) (2023)
- [Aligning to Thousands of Preferences via System Message Generalization](https://mlsanity.com/paper/2405.17977/) (2024)
- [User-LLM: Efficient LLM Contextualization with User Embeddings](https://mlsanity.com/paper/2402.13598/) (2024)
- [A Survey of Personalized Large Language Models: Progress and Future Directions](https://mlsanity.com/paper/2502.11528/) (2025)
- [Beyond a Million Tokens: Benchmarking and Enhancing Long-Term Memory in LLMs](https://mlsanity.com/paper/2510.27246/) (2025)
- [ONCE: Boosting Content-based Recommendation with Both Open- and Closed-source Large Language Models](https://mlsanity.com/paper/2305.06566/) (2023)
- [PersonaLens: A Benchmark for Personalization Evaluation in Conversational AI Assistants](https://mlsanity.com/paper/2506.09902/) (2025)
- [Measuring What Makes You Unique: Difference-Aware User Modeling for Enhancing LLM Personalization](https://mlsanity.com/paper/2503.02450/) (2025)
- [A Survey on Personalized Alignment -- The Missing Piece for Large Language Models in Real-World Applications](https://mlsanity.com/paper/2503.17003/) (2025)
- [Teaching Language Models to Evolve with Users: Dynamic Profile Modeling for Personalized Alignment](https://mlsanity.com/paper/2505.15456/) (2025)
- [Personalized LoRA for Human-Centered Text Understanding](https://mlsanity.com/paper/2403.06208/) (2024)
- [SPRInG: Continual LLM Personalization via Selective Parametric Adaptation and Retrieval-Interpolated Generation](https://mlsanity.com/paper/2601.09974/) (2026)
- [Personalizing LLMs with Binary Feedback: A Preference-Corrected Optimization Framework](https://mlsanity.com/paper/2605.10043/) (2026)

## Abstract (arXiv)

While Large Language Models (LLMs) have achieved remarkable results across various benchmarks, their alignment with normative values often results in homogenized responses that fail to address diverse user preferences. Existing training-free methods often occupy valuable context windows through prompt engineering, while training-based methods typically remain static post-training, failing to support the continual optimization required in real-world settings. To address these challenges, we propose COPE (Continual Optimization with Personalized embedding and self-Evaluation), a novel optimization framework tailored for real-world-motivated interaction settings with sparse user feedback. Our framework assigns learnable personalized embeddings to each user and synergistically integrates preference capture, self-evaluation calibration, and personalized response optimization within a single update step. A key innovation of our method is the use of self-evaluation to generate proxy rewards, enabling continuous model updates even when explicit user feedback is unavailable. Experiments show that COPE consistently outperforms strong training-free and training-based baselines under sparse feedback, and remains complementary to Retrieval-Augmented Prompting (RAP). Further analyses confirm COPE's reliable self-evaluation, meaningful preference patterns, stable general capabilities, and robustness under shifting preferences and alternative evaluators.