When Chains of Thought Don't Matter: Causal Bypass in Large Language Models
This reveals a critical transparency failure in interpretability methods for AI researchers, showing that CoT may not ensure faithful reasoning.
The study investigated whether chain-of-thought (CoT) prompting truly exposes reasoning in large language models, finding that model answers are often causally independent of CoT content, with bypass scores showing near-total bypass in many QA items (CMI ≈ 0) and up to 0.56 mediation in some logic problems.
Chain-of-thought (CoT) prompting is widely assumed to expose a model's reasoning process and improve transparency. We attempted to enforce this assumption by penalizing unfaithful reasoning, but found that surface-level compliance does not guarantee causal reliance. Our central finding is negative: even when CoT is verbose, strategic, and flagged by surface-level manipulation detectors, model answers are often causally independent of the CoT content. We present a diagnostic framework for auditing this failure mode: it combines (i) an interpretable behavioral module that scores manipulation-relevant signals in CoT text and (ii) a causal probe that measures CoT-mediated influence (CMI) via hidden-state patching and reports a bypass score ($1-\mathrm{CMI}$), quantifying the degree to which the answer is produced by a bypass circuit independent of the rationale. In pilot evaluations, audit-aware prompting increases detectable manipulation signals (mean risk-score delta: $+5.10$), yet causal probes reveal task-dependent mediation: many QA items exhibit near-total bypass (CMI $\approx 0$), while some logic problems show stronger mediation (CMI up to $0.56$). Layer-wise analysis reveals narrow and task-dependent ``reasoning windows'' even when mean CMI is low.