paper-with-me

홈 › Papers

Feature Extraction and Steering for Enhanced Chain-of-Thought Reasoning in Language Models

2025-05-21 · Zihao Li, Xu Wang, Yuzhe Yang, Ziyu Yao, Haoyi Xiong, Mengnan Du

Large Language Models (LLMs) demonstrate the ability to solve reasoning and mathematical problems using the Chain-of-Thought (CoT) technique. Expanding CoT length, as seen in models such as DeepSeek-R1, significantly enhances this reasoning for complex problems, but requires costly and high-quality long CoT data and fine-tuning. This work, inspired by the deep thinking paradigm of DeepSeek-R1, utilizes a steering technique to enhance the reasoning ability of an LLM without external datasets. Our method first employs Sparse Autoencoders (SAEs) to extract interpretable features from vanilla CoT. These features are then used to steer the LLM's internal states during generation. Recognizing that many LLMs do not have corresponding pre-trained SAEs, we further introduce a novel SAE-free steering algorithm, which directly computes steering directions from the residual activations of an LLM, obviating the need for an explicit SAE. Experimental results demonstrate that both our SAE-based and subsequent SAE-free steering algorithms significantly enhance the reasoning capabilities of LLMs.

📄 PDF Abstract BibTeX arXiv:2505.15634

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Chain-of-Thought Augmentation with Logit Contrast for Enhanced Reasoning in Language Models

2024-07-04 · Jay Shim, Grant Kruttschnitt, Alyssa Ma, Daniel Kim 외

Rapidly increasing model scales coupled with steering methods such as chain-of-thought prompting have led to drastic improvements in language model reasoning. At the same time, models struggle with compositional generali…

Language ModelingLanguage Modelling

GeoSteer: Faithful Chain-of-Thought Steering via Latent Manifold Gradients

2026-01-15 · Kentaro Kazama, Daiki Shirafuji, Tatsuhiko Saito arxiv

Recent advances in Large Language Models (LLMs) have demonstrated remarkable progress in their reasoning capabilities, such as Chain-of-Thought (CoT). Most approaches rely on CoT rationales. Previous studies have shown t…

Agentic Chain-of-Thought Steering for Efficient and Controllable LLM Reasoning

2026-06-02 · Yu Xia, Zhouhang Xie, Xin Xu, Byungkyu Kang 외 arxiv

Large language models improve final-answer accuracy through extended chain-of-thought reasoning, but often spend tokens inefficiently and offer little inference-time control. Existing efficient reasoning methods control …

Reinforcement Learning

Nudging Hidden States: Training-Free Model Steering for Chain-of-Thought Reasoning in Large Audio-Language Models

2026-03-15 · Lok-Lam Ieong, Chia-Chien Chen, Chih-Kai Yang, Yu-Han Huang 외 arxiv

Chain-of-thought (CoT) prompting has been extended to large audio-language models (LALMs) to elicit reasoning, yet enhancing its effectiveness without training remains challenging. We study inference-time model steering …

Uncovering Latent Chain of Thought Vectors in Language Models

2024-09-21 · Jason Zhang, Scott Viteri

As language models grow more influential and trusted in our society, our ability to reliably steer them toward favorable behaviors becomes increasingly paramount. For this, we investigate the technique of steering vector…

ARCGSM8KMMLU