mlsanityData to 7 Oct 2026

RPM: Reasoning-Level Personalization for Black-Box Large Language Models

arXiv 2505.21082 ↗First posted 27 May 2025cs.CLcited by 2

On the map: LLM reasoning → Reinforcement learning for reasoning

Abstract (arXiv)

While black-box large language models are widely deployed, they produce generic outputs that overlook individual user preferences. Current personalization methods are fundamentally limited to response-level personalization; they only match final outputs, failing to model the underlying reasoning that connects user behavior to responses. To address this, this work introduces reasoning-level personalization as a new paradigm and proposes RPM, the first systematic framework that automatically discovers user-specific reasoning structures from raw behavioral data to guide the model's personalized inference. RPM constructs a structured model of user behavior-built from response-influential features and statistical factors-to create personalized reasoning paths and retrieve beneficial examples for guiding inference through a feature-based retrieval mechanism. Extensive experiments across four diverse tasks demonstrate that RPM consistently outperforms existing response-level methods while simultaneously enhancing both personalization performance and interpretability, providing a promising direction for black-box LLM personalization.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in Reinforcement learning for reasoning, one of 17 directions in LLM reasoning. Builds on 35 of its 40 references that are in the map. First posted on arXiv 27 May 2025.

Builds on

35 of 40 references.

References · 35

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2023GPT-4 Technical Reportcited by 18,132
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  4. 2020Measuring Massive Multitask Language Understandingcited by 7,768
  5. 2024GPT-4o System Cardcited by 4,467
  6. 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
  7. 2024Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextcited by 3,175
  8. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,155
  9. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,185
  10. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,203
  11. 2023LaMP: When Large Language Models Meet Personalizationcited by 425
  12. 2023Towards Measuring the Representation of Subjective Global Opinions in Language Modelscited by 424
23 more
  1. 2018Explainable Recommendation: A Survey and New Perspectivescited by 210
  2. 2023Is ChatGPT a Good Recommender? A Preliminary Studycited by 192
  3. 2023Uncovering ChatGPT's Capabilities in Recommender Systemscited by 160
  4. 2023Do LLMs Understand User Preferences? Evaluating LLMs On User Rating Predictioncited by 113
  5. 2024Personalization of Large Language Models: A Surveycited by 100
  6. 2023Aligning Language Models to User Opinionscited by 98
  7. 2024Optimization Methods for Personalizing Large Language Models through Retrieval Augmentationcited by 98
  8. 2023Personalisation within bounds: A risk taxonomy and policy framework for the alignment of large language models with personalised feedbackcited by 86
  9. 2024HYDRA: Model Factorization Framework for Black-Box LLM Personalizationcited by 59
  10. 2023Goal-Driven Explainable Clustering via Language Descriptionscited by 58
  11. 2023ONCE: Boosting Content-based Recommendation with Both Open- and Closed-source Large Language Modelscited by 54
  12. 2023Zero-Shot Next-Item Recommendation using Large Pretrained Language Modelscited by 53
  13. 2023Teach LLMs to Personalize -- An Approach inspired by Writing Educationcited by 48
  14. 2024Persona-DB: Efficient Large Language Model Personalization for Response Prediction with Collaborative Data Refinementcited by 47
  15. 2023Integrating Summarization and Retrieval for Enhanced Personalization via Large Language Modelscited by 40
  16. 2024Few-shot Personalization of LLMs with Mis-aligned Responsescited by 30
  17. 2023Evaluating ChatGPT as a Recommender System: A Rigorous Approachcited by 20
  18. 2024Review-driven Personalized Preference Reasoning with Large Language Models for Recommendationcited by 20
  19. 2023Explainable Recommendation with Personalized Review Retrieval and Aspect Learningcited by 19
  20. 2024Self-Consistent Reasoning-based Aspect-Sentiment Quad Prediction with Extract-Then-Assign Strategycited by 12
  21. 2025Towards Personalized Conversational Sales Agents: Contextual User Profiling for Strategic Actioncited by 6
  22. 2024Stop Playing the Guessing Game! Target-free User Simulation for Evaluating Conversational Recommender Systemscited by 4
  23. 2024Make Compound Sentences Simple to Analyze: Learning to Split Sentences for Aspect-based Sentiment Analysiscited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2025Think-While-Generating: On-the-Fly Reasoning for Personalized Long-Form Generationcited by 29
  2. 2026Reasoning-Based Personalized Generation for Users with Sparse Datacited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2025Reasoning Meets Personalization: Unleashing the Potential of Large Reasoning Model for Personalized Generation
  2. 2025PrefDisco: Benchmarking Proactive Personalized Reasoning
  3. 2025POPI: Personalizing LLMs via Optimized Natural Language Preference Inference
  4. 2026Preference Heads in Large Language Models: A Mechanistic Framework for Interpretable Personalization
  5. 2025PRIME: Large Language Model Personalization with Cognitive Dual-Memory and Personalized Thought Process
  6. 2026Rethinking Personalization in Large Language Models at the Token Level
  7. 2026VIBE-Bench: Evaluating Personalized Large Language Models When Profiles Don't Mean Preferences
  8. 2026HyperTrace: Hypothesis-Based Preference Tracing for Online LLM Personalization