Detecting Hidden Chain-of-Thought in Large Language Models with Linguistic, Behavioral, and Mechanistic Indicators
cs.CL
Submitted: 2026-08-30
Updated: 2026-08-30
Code: https://github.com/a4maan/detecting-hct
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Thought Anchors: Which LLM Reasoning Steps Matter?
- Reasoning Models Don't Always Say What They Think
- Training Verifiers to Solve Math Word Problems
- Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies
- Triggering Chain-of-Thought via Latent Feature Interventions in Large Language Models
- Implicit Reasoning in Transformers is Reasoning through Shortcuts
- Reasoning Models Can Be Effective Without Thinking
- Locating and Editing Factual Associations in GPT
- Finding the Cracks: Improving LLMs Reasoning with Paraphrastic Probing and Consistency Verification
- Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting
- Attention Is All You Need
- Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
- Qwen3 Technical Report
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering