Persona Switch: Mixing Distinct Perspectives in Decoding Time
On the map: LLM reasoning → Reasoning benchmarks and evaluation
Abstract (arXiv)
Role-play prompting is known to steer the behavior of language models by injecting a persona into the prompt, improving their zero-shot reasoning capabilities. However, such improvements are inconsistent across different tasks or instances. This inconsistency suggests that zero-shot and role-play prompting may offer complementary strengths rather than one being universally superior. Building on this insight, we propose Persona Switch, a novel decoding method that dynamically combines the benefits of both prompting strategies. Our method proceeds step-by-step, selecting the better output between zero-shot and role-play prompting at each step by comparing their output confidence, as measured by the logit gap. Experiments with widely-used LLMs demonstrate that Persona Switch consistently outperforms competitive baselines, achieving up to 5.13% accuracy improvement. Furthermore, we show that output confidence serves as an informative measure for selecting the more reliable output.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 14 of its 19 references that are in the map. First posted on arXiv 22 Jan 2026.
Builds on
14 of 19 references.
Closest ancestors · 2
Same direction, newest first
- 2023Bias Runs Deep: Implicit Reasoning Biases in Persona-Assigned LLMs8 Nov
- 2023Better Zero-Shot Reasoning with Role-Play Prompting15 Aug
Other references · 12
- 2020Language Models are Few-Shot Learnerscited by 32,199
- 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
- 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,747
- 2018CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledgecited by 1,793
- 2022Language Models (Mostly) Know What They Knowcited by 1,783
- 2017Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problemscited by 642
- 2024Chain-of-Thought Reasoning Without Promptingcited by 208
- 2023In-Context Impersonation Reveals Large Language Models' Strengths and Biasescited by 154
- 2023ExpertPrompting: Instructing Large Language Models to be Distinguished Expertscited by 140
- 2023Enhancing Uncertainty-Based Hallucination Detection with Stronger Focuscited by 98
- 2022Meet Your Favorite Character: Open-domain Chatbot Mimicking Fictional Characters with only a Few Utterancescited by 32
- 2024Step Guided Reasoning: Improving Mathematical Reasoning using Guidance Generation and Step Reasoningcited by 9
Built on by
Citing papers per year: 2026: 1.
1 paper.
Similar, not cited
Close in wording, no citation either way
- 2024Persona is a Double-edged Sword: Mitigating the Negative Impact of Role-playing Prompts in Zero-shot Reasoning Tasks
- 2026Cognitive Enhancement: Rethinking the Necessity of Role-Playing for Large Language Models
- 2026The Persona Hierarchy Model: Understanding Contextual Generalization in Fine-Tuning LLMs
- 2024PHAnToM: Persona-based Prompting Has An Effect on Theory-of-Mind Reasoning in Large Language Models
- 2026Enhancing Persona Following at Decoding Time via Dynamic Importance Estimation for Role-Playing Agents
- 2026OSPD: On-Policy Self-Distillation for Persona-Consistent Dialogue
- 2026PerMix-RLVR: Preserving Persona Expressivity under Verifiable-Reward Alignment
- 2025RoleMRC: A Fine-Grained Composite Benchmark for Role-Playing and Instruction-Following