mlsanityData to 7 Oct 2026

PersonaDual: Balancing Personalization and Objectivity via Adaptive Reasoning

arXiv 2601.08679 ↗First posted 13 Jan 2026cs.AIcited by 0

On the map: LLM reasoning → Reinforcement learning for reasoning

Abstract (arXiv)

As users increasingly expect LLMs to align with their preferences, personalized information becomes valuable. However, personalized information can be a double-edged sword: it can improve interaction but may compromise objectivity and factual correctness, especially when it is misaligned with the question. To alleviate this problem, we propose PersonaDual, a framework that supports both general-purpose objective reasoning and personalized reasoning in a single model, and adaptively switches modes based on context. PersonaDual is first trained with SFT to learn two reasoning patterns, and then further optimized via reinforcement learning with our proposed DualGRPO to improve mode selection. Experiments on objective and personalized benchmarks show that PersonaDual preserves the benefits of personalization while reducing interference, achieving near interference-free performance and better leveraging helpful personalized signals to improve objective problem-solving.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Reinforcement learning for reasoning, one of 17 directions in LLM reasoning. Builds on 32 of its 53 references that are in the map. First posted on arXiv 13 Jan 2026.

Builds on

32 of 53 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning22 Jan

Other references · 31

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2024The Llama 3 Herd of Modelscited by 14,192
  3. 2025Qwen3 Technical Reportcited by 8,195
  4. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,203
  5. 2024GPT-4o System Cardcited by 4,467
  6. 2025Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilitiescited by 3,655
  7. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,895
  8. 2024Mixtral of Expertscited by 1,785
  9. 2023Gemini: A Family of Highly Capable Multimodal Modelscited by 810
  10. 2023FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performancecited by 791
  11. 2023LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusioncited by 550
  12. 2024Scaling Synthetic Data Creation with 1,000,000,000 Personascited by 397
19 more
  1. 2023Toxicity in ChatGPT: Analyzing Persona-assigned Language Modelscited by 356
  2. 2023Bias Runs Deep: Implicit Reasoning Biases in Persona-Assigned LLMscited by 191
  3. 2023Simple synthetic data reduces sycophancy in large language modelscited by 174
  4. 2025AdaptThink: Reasoning Models Can Learn When to Thinkcited by 141
  5. 2025Thinkless: LLM Learns When to Thinkcited by 107
  6. 2025AdaCoT: Pareto-Optimal Adaptive Chain-of-Thought Triggering via Reinforcement Learningcited by 86
  7. 2025SuperGPQA: Scaling LLM Evaluation across 285 Graduate Disciplinescited by 67
  8. 2025Think Only When You Need with Large Hybrid-Reasoning Modelscited by 64
  9. 2025From 1,000,000 Users to Every User: Scaling Up Personalized Preference for User-level Alignmentcited by 28
  10. 2023User Modeling in the Era of Large Language Models: Current Research and Future Directionscited by 18
  11. 2025FSPO: Few-Shot Optimization of Synthetic Preferences Personalizes to Real Userscited by 14
  12. 2025PersonaFeedback: A Large-scale Human-annotated Benchmark For Personalizationcited by 13
  13. 2024Understanding the Role of User Profile in the Personalization of Large Language Modelscited by 10
  14. 2025Leveraging Dual Process Theory in Language Agent Framework for Real-time Simultaneous Human-AI Collaborationcited by 10
  15. 2025Mixture-of-Visual-Thoughts: Exploring Context-Adaptive Reasoning Mode Selection for General Visual Reasoningcited by 7
  16. 2023DUMA: a Dual-Mind Conversational Agent with Fast and Slow Thinkingcited by 4
  17. 2025Who's Asking? Evaluating LLM Robustness to Inquiry Personas in Factual Question Answeringcited by 4
  18. 2025The Geometry of Persona: Disentangling Personality from Reasoning in Large Language Modelscited by 3
  19. 2025FReM: A Flexible Reasoning Mechanism for Balancing Quick and Slow Thinking in Long-Context Question Answeringcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Learning to Reason for Multi-Step Retrieval of Personal Context in Personalized Question Answering
  2. 2025Whose Boat Does it Float? Improving Personalization in Preference Tuning via Inferred User Personas
  3. 2025PrefDisco: Benchmarking Proactive Personalized Reasoning
  4. 2025PersonaMem-v2: Towards Personalized Intelligence via Learning Implicit User Personas and Agentic Memory
  5. 2025Tagging the Thought: Unlocking Personalization Reasoning via Reinforcement Learning
  6. 2024PersonalLLM: Tailoring LLMs to Individual Preferences
  7. 2026Training LLMs with Reinforcement Learning for Intent-Aware Personalized Question Answering
  8. 2025SynthesizeMe! Inducing Persona-Guided Prompts for Personalized Reward Models in LLMs