mlsanityData to 14 Oct 2026

HyperTrace: Hypothesis-Based Preference Tracing for Online LLM Personalization

arXiv 2609.09835 ↗First posted 9 Sep 2026cs.CLcited by 0

On the map: LLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment

Abstract (arXiv)

Personalized language models aim to adapt responses to individual users, whose preferences are often latent and revealed gradually through interaction. Existing training-free methods rely on stored histories or retrieved memories, but they often struggle to reconcile long- term preferences with short-term topic-specific needs. To address this issue, we propose HyperTrace, a training-free framework that formulates online personalization as latent preference tracing. HyperTrace maintains interpretable natural-language hypotheses over short-term intent and long-term preferences, and updates them through an SMC-style reweight process using an LLM-based surrogate choice model. By updating these hypotheses across turns and sessions, HyperTrace enables personalization without parameter updates. Experiments on PRISM and PersonaMem-v2 show that HyperTrace improves response alignment, preference prediction, and profile consistency over strong online baselines, demonstrating the effectiveness of tracing latent user preferences for robust personalization. Code and scripts are available in the repository: https://github.com/jiseshen/HyperTrace.

Key facts. No citing papers in the map yet (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 32 of its 49 references that are in the map. First posted on arXiv 9 Sep 2026.

Builds on

32 of 49 references.

Closest ancestors · 6

Same direction, newest first

  1. 2026Grading Scale Impact on LLM-as-a-Judge: Human-LLM Alignment Is Highest on 0-5 Grading Scale6 Jan
  2. 2025A Survey on Personalized Alignment -- The Missing Piece for Large Language Models in Real-World Applications21 Mar
  3. 2024WildFeedback: Aligning LLMs With In-situ User Interactions And Feedback28 Aug
  4. 2024PERSONA: A Reproducible Testbed for Pluralistic Alignment24 Jul
  5. 2024LLM Evaluators Recognize and Favor Their Own Generations15 Apr
  6. 2023Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Merging17 Oct

Other references · 26

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2026DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligencecited by 1,040
  3. 2024LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memorycited by 707
  4. 2026GLM-5: from Vibe Coding to Agentic Engineeringcited by 587
  5. 2023LaMP: When Large Language Models Meet Personalizationcited by 437
  6. 2024Two Tales of Persona in LLMs: A Survey of Role-Playing and Personalizationcited by 208
  7. 2025Know Me, Respond to Me: Benchmarking LLMs for Dynamic User Profiling and Personalized Responses at Scalecited by 178
  8. 2025Do LLMs Recognize Your Preferences? Evaluating Personalized Preference Following in LLMscited by 148
  9. 2024Can LLM be a Personalized Judge?cited by 100
  10. 2024Optimization Methods for Personalizing Large Language Models through Retrieval Augmentationcited by 99
  11. 2025PersonaMem-v2: Towards Personalized Intelligence via Learning Implicit User Personas and Agentic Memorycited by 88
  12. 2024User-LLM: Efficient LLM Contextualization with User Embeddingscited by 76
14 more
  1. 2023Cue-CoT: Chain-of-thought Prompting for Responding to In-depth Dialogue Questions with LLMscited by 62
  2. 2024HYDRA: Model Factorization Framework for Black-Box LLM Personalizationcited by 60
  3. 2025Measuring What Makes You Unique: Difference-Aware User Modeling for Enhancing LLM Personalizationcited by 45
  4. 2023Learning to Rewrite Prompts for Personalized Text Generationcited by 40
  5. 2025Hypothesis-Driven Theory-of-Mind Reasoning for Large Language Modelscited by 29
  6. 2025Amulet: ReAlignment During Test Time for Personalized Preference Adaptation of LLMscited by 29
  7. 2025PROPER: A Progressive Learning Framework for Personalized Large Language Models with Group-Level Adaptationcited by 24
  8. 2024On the Way to LLM Personalization: Learning to Remember User Conversationscited by 21
  9. 2025Latent Inter-User Difference Modeling for LLM Personalizationcited by 21
  10. 2025Instant Personalized Large Language Model Adaptation via Hypernetworkcited by 18
  11. 2026Learning Personalized Agents from Human Feedbackcited by 18
  12. 2024Personalized LoRA for Human-Centered Text Understandingcited by 17
  13. 2025The Era of Real-World Human Interaction: RL from User Conversationscited by 13
  14. 2026ThoughtTrace: Understanding User Thoughts in Real-World LLM Interactionscited by 7

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Online LLM Personalization from Pairwise Preferences Across Users
  2. 2024PersonalLLM: Tailoring LLMs to Individual Preferences
  3. 2026Preference Heads in Large Language Models: A Mechanistic Framework for Interpretable Personalization
  4. 2026Towards Natural Personalization: Evaluating Long-Horizon Preference Following in Personalized User-LLM Interactions
  5. 2025When Personalization Meets Reality: A Multi-Faceted Analysis of Personalized Preference Learning
  6. 2025POPI: Personalizing LLMs via Optimized Natural Language Preference Inference
  7. 2026Text as a Universal Interface for Transferable Personalization
  8. 2026Personalizing LLMs with Binary Feedback: A Preference-Corrected Optimization Framework