Improving LLM Reasoning through Interpretable Role-Playing Steering

• URL: http://arxiv.org/abs/2506.07335v1
• Date: Mon, 09 Jun 2025 00:31:17 GMT
• Title: Improving LLM Reasoning through Interpretable Role-Playing Steering
• Authors: Anyi Wang, Dong Shu, Yifan Wang, Yunpu Ma, Mengnan Du,
• Abstract summary: Role-playing has emerged as an effective technique for enhancing the reasoning capabilities of large language models (LLMs)<n>We introduce Sparse Autoencoder Role-Playing Steering (SRPS), a novel framework that identifies and manipulates internal model features associated with role-playing behavior.<n>Our approach extracts latent representations from role-play prompts, selects the most relevant features based on activation patterns, and constructs a steering vector that can be injected into the model's residual stream with controllable intensity.
• Score: 23.75554062102392
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Role-playing has emerged as an effective technique for enhancing the reasoning capabilities of large language models (LLMs). However, existing methods primarily rely on prompt engineering, which often lacks stability and interpretability. In this paper, we introduce Sparse Autoencoder Role-Playing Steering (SRPS), a novel framework that identifies and manipulates internal model features associated with role-playing behavior. Our approach extracts latent representations from role-play prompts, selects the most relevant features based on activation patterns, and constructs a steering vector that can be injected into the model's residual stream with controllable intensity. Our method enables fine-grained control over role-specific behavior and offers insights into how role information influences internal model activations. Extensive experiments across various reasoning benchmarks and model sizes demonstrate consistent performance gains. Notably, in the zero-shot chain-of-thought (CoT) setting, the accuracy of Llama3.1-8B on CSQA improves from 31.86% to 39.80%, while Gemma2-9B on SVAMP increases from 37.50% to 45.10%. These results highlight the potential of SRPS to enhance reasoning ability in LLMs, providing better interpretability and stability compared to traditional prompt-based role-playing.

Related papers

• Agentic Reinforced Policy Optimization [66.96989268893932]
  Large-scale reinforcement learning with verifiable rewards (RLVR) has demonstrated its effectiveness in harnessing the potential of large language models (LLMs) for single-turn reasoning tasks.<n>Current RL algorithms inadequately balance the models' intrinsic long-horizon reasoning capabilities and their proficiency in multi-turn tool interactions.<n>We propose Agentic Reinforced Policy Optimization (ARPO), a novel agentic RL algorithm tailored for training multi-turn LLM-based agents.
  arXiv  Detail & Related papers  (2025-07-26T07:53:11Z)
• GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs [56.93583799109029]
  GrAInS is an inference-time steering approach that operates across both language-only and vision-language models and tasks.<n>During inference, GrAInS hidden activations at transformer layers guided by token-level attribution signals, and normalizes activations to preserve representational scale.<n>It consistently outperforms both fine-tuning and existing steering baselines.
  arXiv  Detail & Related papers  (2025-07-24T02:34:13Z)
• Enhancing Cross-task Transfer of Large Language Models via Activation Steering [75.41750053623298]
  Cross-task in-context learning offers a direct solution for transferring knowledge across tasks.<n>We investigate whether cross-task transfer can be achieved via latent space steering without parameter updates or input expansion.<n>We propose a novel Cross-task Activation Steering Transfer framework that enables effective transfer by manipulating the model's internal activation states.
  arXiv  Detail & Related papers  (2025-07-17T15:47:22Z)
• Exploring and Exploiting the Inherent Efficiency within Large Reasoning Models for Self-Guided Efficiency Enhancement [101.77467538102924]
  Large reasoning models (LRMs) exhibit overthinking, which hinders efficiency and inflates inference cost.<n>We propose two lightweight methods to enhance LRM efficiency.<n>First, we introduce Efficiency Steering, a training-free activation steering technique that modulates reasoning behavior via a single direction.<n>Second, we develop Self-Rewarded Efficiency RL, a reinforcement learning framework that dynamically balances task accuracy and brevity.
  arXiv  Detail & Related papers  (2025-06-18T17:18:12Z)
• RAIDEN-R1: Improving Role-awareness of LLMs via GRPO with Verifiable Reward [7.9399136525335585]
  RAIDEN-R1 is a novel reinforcement learning framework that integrates Verifiable Role-Awareness Reward (VRAR)<n>We construct a high-quality, role-aware Chain-of-Thought dataset through multi-LLM collaboration.<n> Experiments on the RAIDEN benchmark demonstrate RAIDEN-R1's superiority.
  arXiv  Detail & Related papers  (2025-05-15T12:22:10Z)
• Enhancing Persona Consistency for LLMs' Role-Playing using Persona-Aware Contrastive Learning [7.836439251883518]
  We propose a novel framework named textbfunderlinePersona-Aware textbfunderlineContrastive textbfunderlineLearning (PCL) to align model role-playing behavior.<n>We show that PCL significantly outperform vanilla LLMs under automatic evaluation methods and human expert evaluation.
  arXiv  Detail & Related papers  (2025-03-22T06:12:34Z)
• Reasoning Does Not Necessarily Improve Role-Playing Ability [46.441264660062195]
  The application of role-playing large language models (LLMs) is rapidly expanding in both academic and commercial domains.<n>We compare the effectiveness of direct zero-shot role-playing, role-playing with Chain-of-Thought (CoT), and role-playing using reasoning-optimized LLMs.<n>Our findings reveal that CoT may reduce role-playing performance, reasoning-optimized LLMs are unsuitable for role-playing, and Chinese role-playing performance surpasses English role-playing performance.
  arXiv  Detail & Related papers  (2025-02-24T08:08:41Z)
• SD-LoRA: Scalable Decoupled Low-Rank Adaptation for Class Incremental Learning [73.93639228235622]
  Continual Learning with foundation models has emerged as a promising paradigm to exploit abundant knowledge acquired during pre-training for tackling sequential tasks.<n>Existing prompt-based and Low-Rank Adaptation-based (LoRA-based) methods often require expanding a prompt/LoRA pool or retaining samples of previous tasks.<n>We propose Scalable Decoupled LoRA (SD-LoRA) for class incremental learning, which continually separates the learning of the magnitude and direction of LoRA components without rehearsal.
  arXiv  Detail & Related papers  (2025-01-22T20:00:41Z)
• Language Models are Hidden Reasoners: Unlocking Latent Reasoning Capabilities via Self-Rewarding [74.31981011985681]
  Large language models (LLMs) have shown impressive capabilities, but still struggle with complex reasoning tasks requiring multiple steps. We introduce LaTent Reasoning Optimization (LaTRO), a principled framework that formulates reasoning as sampling from a latent distribution. We validate LaTRO through experiments on GSM8K and ARC-Challenge datasets using multiple model architectures.
  arXiv  Detail & Related papers  (2024-11-06T22:02:30Z)
• Role-Play Paradox in Large Language Models: Reasoning Performance Gains and Ethical Dilemmas [7.677029165197536]
  Role-play in large language models (LLMs) enhances their ability to generate contextually relevant and high-quality responses.<n>We demonstrate that autotuning, a method used to auto-select models' roles based on the question, can lead to the generation of harmful outputs.
  arXiv  Detail & Related papers  (2024-09-21T02:09:13Z)
• Large Language Models are Superpositions of All Characters: Attaining Arbitrary Role-play via Self-Alignment [62.898963074989766]
  We introduce Ditto, a self-alignment method for role-play. This method creates a role-play training set comprising 4,000 characters, surpassing the scale of currently available datasets by tenfold. We present the first comprehensive cross-supervision alignment experiment in the role-play domain.
  arXiv  Detail & Related papers  (2024-01-23T03:56:22Z)
• Augmenting Unsupervised Reinforcement Learning with Self-Reference [63.68018737038331]
  Humans possess the ability to draw on past experiences explicitly when learning new tasks. We propose the Self-Reference (SR) approach, an add-on module explicitly designed to leverage historical information. Our approach achieves state-of-the-art results in terms of Interquartile Mean (IQM) performance and Optimality Gap reduction on the Unsupervised Reinforcement Learning Benchmark.
  arXiv  Detail & Related papers  (2023-11-16T09:07:34Z)
• Better Zero-Shot Reasoning with Role-Play Prompting [10.90357246745529]
  Role-play prompting consistently surpasses the standard zero-shot approach across most datasets. This highlights its potential to augment the reasoning capabilities of large language models.
  arXiv  Detail & Related papers  (2023-08-15T11:08:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.