홈 › Papers

PersonaDual: Balancing Personalization and Objectivity via Adaptive Reasoning

2026-01-13 · Xiaoyou Liu, Xinyi Mou, Shengbin Yue, Liang Wang, Yuqing Wang, Qiexiang Wang, Tianrui Qin, Zhongyu Wei 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.

📄 PDF Abstract BibTeX arXiv:2601.08679

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Beyond Accuracy: How Humans Evaluate Legally Correct but Socially Controversial Legal Advice from Machines

2026-07-06 · Benjamin Minhao Chen, Zhiyu Li arxiv

AI systems are increasingly used to provide legal advice, raising questions about whether laypeople accept guidance from algorithms--especially when that advice is legally correct but socially controversial. We report a …

Recommendation Systems Legal Reasoning

Building Knowledge from Interactions: An LLM-Based Architecture for Adaptive Tutoring and Social Reasoning

2025-04-02 · Luca Garello, Giulia Belgiovine, Gabriele Russo, Francesco Rea 외

Integrating robotics into everyday scenarios like tutoring or physical training requires robots capable of adaptive, socially engaging, and goal-oriented interactions. While Large Language Models show promise in human-li…

Decision Making

Adaptive Expert Models for Personalization in Federated Learning

2022-06-15 · Martin Isaksson, Edvin Listo Zec, Rickard Cöster, Daniel Gillblad 외

Federated Learning (FL) is a promising framework for distributed learning when data is private and sensitive. However, the state-of-the-art solutions in this framework are not optimal when data is heterogeneous and non-I…

Federated Learning Mixture-of-Experts Personalized Federated Learning

pMixFed: Efficient Personalized Federated Learning through Adaptive Layer-Wise Mixup

2025-01-19 · Yasaman Saadati, Mohammad Rostami, M. Hadi Amini

Traditional Federated Learning (FL) methods encounter significant challenges when dealing with heterogeneous data and providing personalized solutions for non-IID scenarios. Personalized Federated Learning (PFL) approach…

Federated Learning Personalized Federated Learning

Personalized Federated Learning with Adaptive Feature Aggregation and Knowledge Transfer

2024-10-19 · Keting Yin, Jiayi Mao

Federated Learning(FL) is popular as a privacy-preserving machine learning paradigm for generating a single model on decentralized data. However, statistical heterogeneity poses a significant challenge for FL. As a subfi…

Federated Learning Personalized Federated Learning Privacy Preserving Transfer Learning