Cover Image

Improving LLM Reasoning through Interpretable Role-Playing Steering

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Anyi, Shu, Dong, Wang, Yifan, Ma, Yunpu, Du, Mengnan
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Enhancing LLM Steering through Sparse Autoencoder-Based Vector Refinement
by: Wang, Anyi, et al.
Published: (2025)

Comparative Analysis of Demonstration Selection Algorithms for LLM In-Context Learning
by: Shu, Dong, et al.
Published: (2024)

Denoising Concept Vectors with Sparse Autoencoders for Improved Language Model Steering
by: Zhao, Haiyan, et al.
Published: (2025)

SAIF: A Sparse Autoencoder Framework for Interpreting and Steering Instruction Following of Language Models
by: He, Zirui, et al.
Published: (2025)

DataFrame QA: A Universal LLM Framework on DataFrame Question Answering Without Data Exposure
by: Ye, Junyi, et al.
Published: (2024)

Reasoning Does Not Necessarily Improve Role-Playing Ability
by: Feng, Xiachong, et al.
Published: (2025)

Quantifying Risk Propensities of Large Language Models: Ethical Focus and Bias Detection through Role-Play
by: Zeng, Yifan, et al.
Published: (2024)

The Impact of Reasoning Step Length on Large Language Models
by: Jin, Mingyu, et al.
Published: (2024)

Controllable LLM Reasoning via Sparse Autoencoder-Based Steering
by: Fang, Yi, et al.
Published: (2026)

A Survey on Sparse Autoencoders: Interpreting the Internal Mechanisms of Large Language Models
by: Shu, Dong, et al.
Published: (2025)

Do Cognitively Interpretable Reasoning Traces Improve LLM Performance?
by: Bhambri, Siddhant, et al.
Published: (2025)

Activation Scaling for Steering and Interpreting Language Models
by: Stoehr, Niklas, et al.
Published: (2024)

Adaptive Activation Steering: A Tuning-Free LLM Truthfulness Improvement Method for Diverse Hallucinations Categories
by: Wang, Tianlong, et al.
Published: (2024)

Exploring the Personality Traits of LLMs through Latent Features Steering
by: Yang, Shu, et al.
Published: (2024)

Steer LLM Latents for Hallucination Detection
by: Park, Seongheon, et al.
Published: (2025)

Fine-Grained Interpretation of Political Opinions in Large Language Models
by: Hu, Jingyu, et al.
Published: (2025)

CoT-Kinetics: A Theoretical Modeling Assessing LRM Reasoning Process
by: Bi, Jinhe, et al.
Published: (2025)

RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language Models
by: Wang, Zekun Moore, et al.
Published: (2023)

DPRF: A Generalizable Dynamic Persona Refinement Framework for Optimizing Behavior Alignment Between Personalized LLM Role-Playing Agents and Humans
by: Yao, Bingsheng, et al.
Published: (2025)

LLM-Guided Semantic Relational Reasoning for Multimodal Intent Recognition
by: Zhou, Qianrui, et al.
Published: (2025)

Does Math Reasoning Improve General LLM Capabilities? Understanding Transferability of LLM Reasoning
by: Huan, Maggie, et al.
Published: (2025)

Beyond Input Activations: Identifying Influential Latents by Gradient Sparse Autoencoders
by: Shu, Dong, et al.
Published: (2025)

Improving LLM Code Reasoning via Semantic Equivalence Self-Play with Formal Verification
by: Barone, Antonio Valerio Miceli, et al.
Published: (2026)

SPC: Evolving Self-Play Critic via Adversarial Games for LLM Reasoning
by: Chen, Jiaqi, et al.
Published: (2025)

A Survey on Fairness in Large Language Models
by: Li, Yingji, et al.
Published: (2023)

CoSER: A Comprehensive Literary Dataset and Framework for Training and Evaluating LLM Role-Playing and Persona Simulation
by: Wang, Xintao, et al.
Published: (2025)

Interpreting and Controlling LLM Reasoning through Integrated Policy Gradient
by: Li, Changming, et al.
Published: (2026)

Better LLM Reasoning via Dual-Play
by: Zhang, Zhengxin, et al.
Published: (2025)

ERABAL: Enhancing Role-Playing Agents through Boundary-Aware Learning
by: Tang, Yihong, et al.
Published: (2024)

Too Good to be Bad: On the Failure of LLMs to Role-Play Villains
by: Yi, Zihao, et al.
Published: (2025)

Evaluating LLM-Generated Versus Human-Authored Responses in Role-Play Dialogues
by: Lu, Dongxu, et al.
Published: (2025)

A Systematic Analysis of the Impact of Persona Steering on LLM Capabilities
by: Chen, Jiaqi, et al.
Published: (2026)

Mitigating Content Effects on Reasoning in Language Models through Fine-Grained Activation Steering
by: Valentino, Marco, et al.
Published: (2025)

Memory-Driven Role-Playing: Evaluation and Enhancement of Persona Knowledge Utilization in LLMs
by: Wang, Kai, et al.
Published: (2026)

Effectively Steer LLM To Follow Preference via Building Confident Directions
by: Song, Bingqing, et al.
Published: (2025)

Voila: Voice-Language Foundation Models for Real-Time Autonomous Interaction and Voice Role-Play
by: Shi, Yemin, et al.
Published: (2025)

LLM CHESS: Benchmarking Reasoning and Instruction-Following in LLMs through Chess
by: Kolasani, Sai, et al.
Published: (2025)

Explore the Reasoning Capability of LLMs in the Chess Testbed
by: Wang, Shu, et al.
Published: (2024)

EasySteer: A Unified Framework for High-Performance and Extensible LLM Steering
by: Xu, Haolei, et al.
Published: (2025)

AdaMARP: An Adaptive Multi-Agent Interaction Framework for General Immersive Role-Playing
by: Xu, Zhenhua, et al.
Published: (2026)