mlsanityData to 7 Oct 2026

Do LLMs Recognize Your Preferences? Evaluating Personalized Preference Following in LLMs

arXiv 2502.09597 ↗First posted 13 Feb 2025cs.LG cs.CLcited by 142

Not on the map. Why?

Cited by 43 in LLM agents and tool use, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Large Language Models (LLMs) are increasingly used as chatbots, yet their ability to personalize responses to user preferences remains limited. We introduce PrefEval, a benchmark for evaluating LLMs' ability to infer, memorize and adhere to user preferences in a long-context conversational setting. PrefEval comprises 3,000 manually curated user preference and query pairs spanning 20 topics. PrefEval contains user personalization or preference information in both explicit and implicit forms, and evaluates LLM performance using a generation and a classification task. With PrefEval, we evaluated the aforementioned preference following capabilities of 10 open-source and proprietary LLMs in multi-session conversations with varying context lengths up to 100k tokens. We benchmark with various prompting, iterative feedback, and retrieval-augmented generation methods. Our benchmarking effort reveals that state-of-the-art LLMs face significant challenges in proactively following users' preferences during conversations. In particular, in zero-shot settings, preference following accuracy falls below 10% at merely 10 turns (~3k tokens) across most evaluated models. Even with advanced prompting and retrieval methods, preference following still deteriorates in long-context conversations. Furthermore, we show that fine-tuning on PrefEval significantly improves performance. We believe PrefEval serves as a valuable resource for measuring, understanding, and enhancing LLMs' preference following abilities, paving the way for personalized conversational agents. Our code and dataset are available at https://prefeval.github.io/.

Key facts. Cited by 142 papers in the map (data through 7 Oct 2026). Builds on 39 of its 46 references that are in the map. First posted on arXiv 13 Feb 2025.

Builds on

39 of 46 references.

References · 39

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2022Training language models to follow instructions with human feedbackcited by 15,712
  3. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  4. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
  5. 2024Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextcited by 3,175
  6. 2021SimCSE: Simple Contrastive Learning of Sentence Embeddingscited by 2,168
  7. 2023LongBench: A Bilingual, Multitask Benchmark for Long Context Understandingcited by 1,378
  8. 2023Instruction-Following Evaluation for Large Language Modelscited by 1,143
  9. 2023Large Language Models Cannot Self-Correct Reasoning Yetcited by 965
  10. 2018Personalizing Dialogue Agents: I have a dog, do you have pets too?cited by 820
  11. 2017The NarrativeQA Reading Comprehension Challengecited by 590
  12. 2021A Dataset of Information-Seeking Questions and Answers Anchored in Research Paperscited by 475
27 more
  1. 2023LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation Datasetcited by 449
  2. 2023LaMP: When Large Language Models Meet Personalizationcited by 425
  3. 2024∞Bench: Extending Long Context Evaluation Beyond 100K Tokenscited by 360
  4. 2021Efficient Attentions for Long Document Summarizationcited by 342
  5. 2023TALLRec: An Effective and Efficient Tuning Framework to Align Large Language Model with Recommendationcited by 336
  6. 2023Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Mergingcited by 271
  7. 2023L-Eval: Instituting Standardized Evaluation for Long Context Language Modelscited by 232
  8. 2024BABILong: Testing the Limits of LLMs with Long Context Reasoning-in-a-Haystackcited by 211
  9. 2024Many-Shot In-Context Learningcited by 203
  10. 2023LooGLE: Can Long-Context Language Models Understand Long Contexts?cited by 200
  11. 2023RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language Modelscited by 173
  12. 2018Training Millions of Personalized Dialogue Agentscited by 126
  13. 2024In-Context Learning with Long-Context Models: An In-Depth Explorationcited by 126
  14. 2024Democratizing Large Language Models via Personalized Parameter-Efficient Fine-tuningcited by 87
  15. 2024Aligning to Thousands of Preferences via System Message Generalizationcited by 84
  16. 2023Group Preference Optimization: Few-Shot Alignment of Large Language Modelscited by 61
  17. 2024HYDRA: Model Factorization Framework for Black-Box LLM Personalizationcited by 59
  18. 2023Teach LLMs to Personalize -- An Approach inspired by Writing Educationcited by 48
  19. 2022Less is More: Learning to Refine Dialogue History for Personalized Dialogue Generationcited by 47
  20. 2024Aligning Language Models with Demonstrated Feedbackcited by 32
  21. 2024LLMs + Persona-Plug = Personalized LLMscited by 29
  22. 2019Towards Controllable and Personalized Review Generationcited by 24
  23. 2023Instruction Tuned Models are Quick Learnerscited by 21
  24. 2024TimeChara: Evaluating Point-in-Time Character Hallucination of Role-Playing Large Language Modelscited by 21
  25. 2024Dissecting Human and LLM Preferencescited by 17
  26. 2024Law of the Weakest Link: Cross Capabilities of Large Language Modelscited by 12
  27. 2023Reference-less Analysis of Context Specificity in Translation with Personalised Language Modelscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 39; 2026: 103.

142 papers.

Sort:

By area:

  1. 2025Know Me, Respond to Me: Benchmarking LLMs for Dynamic User Profiling and Personalized Responses at Scalecited by 163
  2. 2025MemOS: A Memory OS for AI Systemcited by 129
  3. 2025PersonaMem-v2: Towards Personalized Intelligence via Learning Implicit User Personas and Agentic Memorycited by 82
  4. 2025UserBench: An Interactive Gym Environment for User-Centric Agentscited by 69
  5. 2025A Survey of Personalized Large Language Models: Progress and Future Directionscited by 65
  6. 2025HaluMem: Evaluating Hallucinations in Memory Systems of Agentscited by 51
  7. 2025Measuring What Makes You Unique: Difference-Aware User Modeling for Enhancing LLM Personalizationcited by 44
  8. 2025A Survey on Personalized Alignment -- The Missing Piece for Large Language Models in Real-World Applicationscited by 40
  9. 2025Bayesian Teaching Enables Probabilistic Reasoning in Large Language Modelscited by 36
  10. 2025Consistently Simulating Human Personas with Multi-Turn Reinforcement Learningcited by 35
  11. 2025Think-While-Generating: On-the-Fly Reasoning for Personalized Long-Form Generationcited by 29
  12. 2025UserRL: Training Interactive User-Centric Agent via Reinforcement Learningcited by 27
38 more
  1. 2025A Survey on Personalized and Pluralistic Preference Alignment in Large Language Modelscited by 25
  2. 2025AgentRecBench: Benchmarking LLM Agent-based Personalized Recommender Systemscited by 23
  3. 2025Teaching Language Models to Evolve with Users: Dynamic Profile Modeling for Personalized Alignmentcited by 22
  4. 2026Graph-based Agent Memory: Taxonomy, Techniques, and Applicationscited by 22
  5. 2025Latent Inter-User Difference Modeling for LLM Personalizationcited by 20
  6. 2025CUPID: Evaluating Personalized and Contextualized Alignment of LLMs from Interactionscited by 20
  7. 2026From Storage to Experience: A Survey on the Evolution of LLM Agent Memory Mechanismscited by 19
  8. 2026OP-Bench: Benchmarking Over-Personalization for Memory-Augmented Personalized Conversational Agentscited by 18
  9. 2025Evaluating Personalized Tool-Augmented LLMs from the Perspectives of Personalization and Proactivitycited by 17
  10. 2026Evaluating Long-Horizon Memory for Multi-Party Collaborative Dialoguescited by 16
  11. 2025Evaluating Long-Context Reasoning in LLM-Based WebAgentscited by 15
  12. 2026MemoryCD: Benchmarking Long-Context User Memory of LLM Agents for Lifelong Cross-Domain Personalizationcited by 15
  13. 2025MMPB: It's Time for Multi-Modal Personalizationcited by 14
  14. 2026Persona2Web: Benchmarking Personalized Web Agents for Contextual Reasoning with User Historycited by 14
  15. 2026HorizonBench: Long-Horizon Personalization with Evolving Preferencescited by 14
  16. 2026PERMA: Benchmarking Personalized Memory Agents via Event-Driven Preference and Realistic Task Environmentscited by 13
  17. 2026LifeSim: Long-Horizon User Life Simulator for Personalized Assistant Evaluationcited by 11
  18. 2026VitaBench 2.0: Evaluating Personalized and Proactive Agents in Long-Term User Interactionscited by 11
  19. 2026Toward Personalized LLM-Powered Agents: Foundations, Evaluation, and Future Directionscited by 10
  20. 2026PersonaVLM: Long-Term Personalized Multimodal LLMscited by 10
  21. 2026InfoPO: Information-Driven Policy Optimization for User-Centric Agentscited by 8
  22. 2026Towards Natural Personalization: Evaluating Long-Horizon Preference Following in Personalized User-LLM Interactionscited by 8
  23. 2026GateMem: Benchmarking Memory Governance in Multi-Principal Shared-Memory Agentscited by 8
  24. 2025PrefDisco: Benchmarking Proactive Personalized Reasoningcited by 7
  25. 2026MultiSessionCollab: Learning User Preferences with Memory to Improve Long-Term Collaborationcited by 7
  26. 2026How Does Personalized Memory Shape LLM Behavior? Benchmarking Rational Preference Utilization in Personalized Assistantscited by 7
  27. 2026BenchPreS: A Benchmark for Context-Aware Personalized Preference Selectivity of Persistent-Memory LLMscited by 7
  28. 2025FlowKV: Enhancing Multi-Turn Conversational Coherence in LLMs via Isolated Key-Value Cache Managementcited by 6
  29. 2026AlpsBench: An LLM Personalization Benchmark for Real-Dialogue Memorization and Preference Alignmentcited by 6
  30. 2026AdaPlanBench: Evaluating Adaptive Planning in Large Language Model Agents under World and User Constraintscited by 6
  31. 2026Beyond Similarity: Trustworthy Memory Search for Personal AI Agentscited by 6
  32. 2025Extended Inductive Reasoning for Personalized Preference Inference from Behavioral Signalscited by 5
  33. 2025FaST: Feature-aware Sampling and Tuning for Personalized Preference Alignment with Limited Datacited by 5
  34. 2025PREF: Reference-Free Evaluation of Personalised Text Generation in LLMscited by 5
  35. 2026Long Context, Less Focus: A Scaling Gap in LLMs Revealed through Privacy and Personalizationcited by 5
  36. 2026MemTrace: Tracing and Attributing Errors in Large Language Model Memory Systemscited by 5
  37. 2026When Memory Updates but Behavior Does Not: Repairing Implicit Stale Dependencies in Personalized Agent Responsescited by 5
  38. 2025Benchmarking and Improving LLM Robustness for Personalized Generationcited by 4

50 most cited of 142 All 142 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024WildFeedback: Aligning LLMs With In-situ User Interactions And Feedback
  2. 2024PersonalLLM: Tailoring LLMs to Individual Preferences
  3. 2024Aligning LLMs with Individual Preferences via Interaction
  4. 2026Personalized Benchmarking: Evaluating LLMs by Individual Preferences
  5. 2025Group Preference Alignment: Customized LLM Response Generation from In-Situ Conversations
  6. 2024Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference
  7. 2025Users as Annotators: LLM Preference Learning from Comparison Mode
  8. 2026APM: Evaluating Style Personalization in LLMs with Arbitrary Preference Mappings