Cover Image

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

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Kazama, Kentaro, Shirafuji, Daiki, Saito, Tatsuhiko
Format:	Preprint
Published:	2026
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Bridging the Modality Gap by Similarity Standardization with Pseudo-Positive Samples
by: Yamashita, Shuhei, et al.
Published: (2025)

An Empirical Survey of Model Merging Algorithms for Social Bias Mitigation
by: Shirafuji, Daiki, et al.
Published: (2025)

A Hybrid Search for Complex Table Question Answering in Securities Report
by: Shirafuji, Daiki, et al.
Published: (2025)

Feature Extraction and Steering for Enhanced Chain-of-Thought Reasoning in Language Models
by: Li, Zihao, et al.
Published: (2025)

GeoFaith: A Spatio-Temporal Dual View of Faithful Chain-of-Thought
by: Lv, Weijiang, et al.
Published: (2026)

Bias Vector: Mitigating Biases in Language Models with Task Arithmetic Approach
by: Shirafuji, Daiki, et al.
Published: (2024)

Faithful Logical Reasoning via Symbolic Chain-of-Thought
by: Xu, Jundong, et al.
Published: (2024)

Steered Generation via Gradient Descent on Sparse Features
by: Bhattacharyya, Sumanta, et al.
Published: (2025)

Steering Language Model to Stable Speech Emotion Recognition via Contextual Perception and Chain of Thought
by: Zhao, Zhixian, et al.
Published: (2025)

SALT: Steering Activations towards Leakage-free Thinking in Chain of Thought
by: Batra, Shourya, et al.
Published: (2025)

LF-Steering: Latent Feature Activation Steering for Enhancing Semantic Consistency in Large Language Models
by: Yang, Jingyuan, et al.
Published: (2025)

Mitigating Overthinking in Large Reasoning Models via Manifold Steering
by: Huang, Yao, et al.
Published: (2025)

Faithful Bi-Directional Model Steering via Distribution Matching and Distributed Interchange Interventions
by: Bao, Yuntai, et al.
Published: (2026)

Mechanistic Evidence for Faithfulness Decay in Chain-of-Thought Reasoning
by: Ye, Donald, et al.
Published: (2026)

Measuring Chain of Thought Faithfulness by Unlearning Reasoning Steps
by: Tutek, Martin, et al.
Published: (2025)

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

Faithfulness as Information Flow: Evaluating and Training Faithful Chain-of-Thought Reasoning
by: Jia, Jinghan, et al.
Published: (2026)

Counterfactual Simulation Training for Chain-of-Thought Faithfulness
by: Hase, Peter, et al.
Published: (2026)

SteerX: Disentangled Steering for LLM Personalization
by: Zhao, Xiaoyan, et al.
Published: (2025)

Model Tells Itself Where to Attend: Faithfulness Meets Automatic Attention Steering
by: Zhang, Qingru, et al.
Published: (2024)

Critical-Questions-of-Thought: Steering LLM reasoning with Argumentative Querying
by: Castagna, Federico, et al.
Published: (2024)

Evaluating GRPO and DPO for Faithful Chain-of-Thought Reasoning in LLMs
by: Mohammadi, Hadi, et al.
Published: (2025)

On the Hardness of Faithful Chain-of-Thought Reasoning in Large Language Models
by: Tanneru, Sree Harsha, et al.
Published: (2024)

ContextFocus: Activation Steering for Contextual Faithfulness in Large Language Models
by: Anand, Nikhil, et al.
Published: (2026)

Steering LLMs toward Korean Local Speech: Iterative Refinement Framework for Faithful Dialect Translation
by: Park, Keunhyeung, et al.
Published: (2025)

Chain-of-Thought Reasoning In The Wild Is Not Always Faithful
by: Arcuschin, Iván, et al.
Published: (2025)

Steering the CensorShip: Uncovering Representation Vectors for LLM "Thought" Control
by: Cyberey, Hannah, et al.
Published: (2025)

Fine-Grained Activation Steering: Steering Less, Achieving More
by: Feng, Zijian, et al.
Published: (2026)

Steering off Course: Reliability Challenges in Steering Language Models
by: Da Silva, Patrick Queiroz, et al.
Published: (2025)

Is Chain-of-Thought Really Not Explainability? Chain-of-Thought Can Be Faithful without Hint Verbalization
by: Zaman, Kerem, et al.
Published: (2025)

SteerConf: Steering LLMs for Confidence Elicitation
by: Zhou, Ziang, et al.
Published: (2025)

CoSteer: Collaborative Decoding-Time Personalization via Local Delta Steering
by: Lv, Hang, et al.
Published: (2025)

Making Reasoning Matter: Measuring and Improving Faithfulness of Chain-of-Thought Reasoning
by: Paul, Debjit, et al.
Published: (2024)

On Effects of Steering Latent Representation for Large Language Model Unlearning
by: Huu-Tien, Dang, et al.
Published: (2024)

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

Steer2Edit: From Activation Steering to Component-Level Editing
by: Sun, Chung-En, et al.
Published: (2026)

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering
by: Li, Yichen, et al.
Published: (2025)

Towards Better Chain-of-Thought: A Reflection on Effectiveness and Faithfulness
by: Li, Jiachun, et al.
Published: (2024)

Steering Awareness: Detecting Activation Steering from Within
by: Rivera, Joshua Fonseca, et al.
Published: (2025)

C2-Faith: Benchmarking LLM Judges for Causal and Coverage Faithfulness in Chain-of-Thought Reasoning
by: Mittal, Avni, et al.
Published: (2026)