Detecting Hidden Chain-of-Thought in Large Language Models with Linguistic, Behavioral, and Mechanistic Indicators
On the map: LLM reasoning → Prompting and chain-of-thought reasoning
Abstract (arXiv)
Large language models often answer complex reasoning questions without revealing intermediate steps, raising whether they reason latently or complete patterns. We propose the Hidden CoT Detection Score (HCDS), a comparative behavioral and mechanistic signal measuring whether neutral-prompt behavior aligns more closely with explicit CoT or explicit no- CoT. Here, hidden CoT operationally denotes this neutral-prompt CoT-like alignment; HCDS does not directly observe or prove an unexposed reasoning trace. On GSM8K, HCDS is significantly positive for both Qwen3-4B variants (Thinking +1.87, p = 1.2 × 10-7; Instruct +1.41, p = 1.9 × 10-4), replicates across a different inference stack and quantization within 0.08 (+1.80 and +1.45), and is not significantly positive in seven of eight length-adjusted calibration-control cells. The unadjusted score produces large positive scores on single-step arithmetic and numeric factual lookup. The variants also respond differently to no-CoT instructions: Instruct complies from the prompt alone, whereas Thinking continues reasoning and requires intervention. These findings show stronger, less prompt-conditional CoT-like behavior in the reasoning-tuned model, consistent with but not proof of latent reasoning. HCDS thus investigates latent reasoning without relying on models' self-reported traces.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Prompting and chain-of-thought reasoning, one of 17 directions in LLM reasoning. Builds on 13 of its 15 references that are in the map. First posted on arXiv 30 Aug 2026.
Builds on
13 of 15 references.
Closest ancestors · 5
Same direction, newest first
- 2026Triggering Chain-of-Thought via Latent Feature Interventions in Large Language Models12 Jan
- 2025Thought Anchors: Which LLM Reasoning Steps Matter?23 Jun
- 2025Reasoning Models Don't Always Say What They Think8 May
- 2023Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting7 May
- 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Models28 Jan
Other references · 8
- 2017Attention Is All You Needcited by 60,361
- 2021Training Verifiers to Solve Math Word Problemscited by 10,109
- 2025Qwen3 Technical Reportcited by 8,820
- 2022Locating and Editing Factual Associations in GPTcited by 2,691
- 2021Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategiescited by 743
- 2025Reasoning Models Can Be Effective Without Thinkingcited by 187
- 2025Implicit Reasoning in Transformers is Reasoning through Shortcutscited by 14
- 2026Finding the Cracks: Improving LLMs Reasoning with Paraphrastic Probing and Consistency Verificationcited by 2
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026The Fragility of Chain-of-Thought Monitoring Across Typologically Diverse Languages
- 2026Facts Don't Speak Louder than Words: The Behavioral Essence of Long-CoT Distillation
- 2024Understanding Hidden Computations in Chain-of-Thought Reasoning
- 2026Bypassing the Rationale: Causal Auditing of Implicit Reasoning in Language Models
- 2026Does Out-of-Sight Equal Out-of-Mind in CoT Monitorability?
- 2023Measuring Faithfulness in Chain-of-Thought Reasoning
- 2025Deep Hidden Cognition Facilitates Reliable Chain-of-Thought Reasoning
- 2025FaithCoT-Bench: Benchmarking Instance-Level Faithfulness of Chain-of-Thought Reasoning