arXiv AI September 21, 2026 By Gaoxiang Huang, Lei Qi

When Steering Fails in Latent Reasoning: A Latent-to-Language Transition Gap

The paper investigates the effectiveness of activation steering in latent chain-of-thought (CoT) reasoning compared to explicit CoT. It finds that steering continuous latent thoughts yields weaker impacts on language generation, even when hidden representations are shifted similarly. The authors propose a latent-to-language transition gap, supported by evidence of abrupt output distribution changes at the transition boundary and weaker bidirectional control in latent CoT.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv Machine Learning

Aug 5

The Illusion of Superposition? A Principled Analysis of Latent Thinking in Language Models

arXiv:2604. 06374v2 Announce Type: replace-cross Abstract: Latent reasoning via continuous chain-of-thoughts (Latent CoT) has emerged as a promising alternative to discrete CoT reasoning.

By Michael Rizvi-Martel, Guillaume Rabusseau, Marius Mosbach

llms rag fine-tuning

arXiv Computation and Language

Sep 1

Reasoning Beyond Language: A Comprehensive Survey on Latent Chain-of-Thought Reasoning

arXiv:2505.16782v3 Announce Type: replace Abstract: Large Language Models (LLMs) have shown impressive performance on complex tasks through Chain-of-Thought (CoT) reasoning. However, conventional CoT...

By Xinghao Chen, Anhao Zhao, Heming Xia, Xuan Lu, Hanlin Wang, Yanjun Chen, Wei Zhang, Jian Wang, Wenjie Li, Xiaoyu Shen

llms nlp

arXiv AI

Sep 1

Triggering Chain-of-Thought via Latent Feature Interventions in Large Language Models

arXiv:2601.08058v2 Announce Type: replace-cross Abstract: Chain-of-Thought (CoT) prompting often improves the reasoning performance of large language models (LLMs), but the internal signal that trigg...

By Zhenghao He, Guangzhi Xiong, Bohan Liu, Sanchit Sinha, Aidong Zhang

llms benchmarks

arXiv Machine Learning

Sep 10

Think Wider: Mitigating Latent Rank Collapse in Implicit Chain-of-Thought Reasoning

arXiv:2609.07406v1 Announce Type: new Abstract: Chain-of-thought (CoT) reasoning improves the reasoning ability of large language models by introducing intermediate computation, but explicit rational...

By Yuwen Hao, Menglin Yang

llms

arXiv AI

Jun 3

LatentChem: From Textual CoT to Latent Thinking in Chemical Reasoning

arXiv:2602. 07075v5 Announce Type: replace-cross Abstract: Current chemical large language models (LLMs) predominantly rely on explicit Chain-of-Thought (CoT) to solve complex reasoning problems.

By Xinwu Ye, Yicheng Mao, Yuxuan Liao, Jia Zhang, Yimeng Liu, Li Hao, Fang Wu, Zhiwei Li, Zehong Wang, Zhiyuan Liu, Zhenfei Yin, Li Yuan, Philip Torr, Huan Sun, xiangxiang Zeng, Mengdi Wang, Le Cong, Shenghua Gao, Xiangru Tang

llms benchmarks

arXiv AI

Jul 24

Post-Hoc Reasoning in Chain of Thought: Decoding and Steering Pre-Committed Answers

arXiv:2603. 01437v2 Announce Type: replace Abstract: As chain of thought (CoT) has become central to scaling reasoning capabilities in large language models (LLMs), it has also emerged as a promising tool for interpretability, suggesting the opportunity to understand model decisions through verbalized reasoning.

By Kyle Cox, Darius Kianersi, Adri\`a Garriga-Alonso

llms safety

One email a morning, machine-written

Related stories

The Illusion of Superposition? A Principled Analysis of Latent Thinking in Language Models

Reasoning Beyond Language: A Comprehensive Survey on Latent Chain-of-Thought Reasoning

Triggering Chain-of-Thought via Latent Feature Interventions in Large Language Models

Think Wider: Mitigating Latent Rank Collapse in Implicit Chain-of-Thought Reasoning

LatentChem: From Textual CoT to Latent Thinking in Chemical Reasoning

Post-Hoc Reasoning in Chain of Thought: Decoding and Steering Pre-Committed Answers