When Chain-of-Thought Fails, the Solution Hides in the Hidden States
Authors: Houman Mehrafarin, Amit Parekh, Ioannis Konstas
Organizations: Heriot-Watt University, Edinburgh, United Kingdom · University of Edinburgh, Edinburgh, United Kingdom
Abstract
Whether intermediate reasoning is computationally useful or merely explanatory depends on whether chain-of-thought (CoT) tokens contain task-relevant information. We present a mechanistic causal analysis of CoT on GSM8K using activation patching: transferring token-level hidden states from a CoT generation to a direct-answer run for the same question, then measuring the effect on final-answer accuracy. Across models, generating after patching yields substantially higher accuracy than both direct-answer prompting and the original CoT trace, revealing that individual CoT tokens can encode sufficient information to recover the correct answer, even when the original trace is incorrect. This task-relevant information is more prevalent in correct than incorrect CoT runs and is unevenly distributed across tokens, concentrating in mid-to-late layers and appearing earlier in the reasoning trace. Moreover, patching language tokens such as verbs and entities carry task-solving information that steers generation toward correct reasoning, whereas mathematical tokens encode answer-proximal content that rarely succeeds. Patched outputs are often shorter and yet exceed the accuracy of a full CoT trace, suggesting complete reasoning chains are not always necessary. Together, these findings demonstrate that CoT encodes recoverable, token-level problem-solving information, offering new insight into how reasoning is represented and where it breaks down.
Chain-of-thought (CoT) prompting reliably improves language-model accuracy, but which properties of a rationale text drive the improvement is poorly understood. Prior work has largely studied generation-time behavior. We instead ask a probe-time question: given a fixed rationale in context, what in that text changes the answer? We identify two complementary sources of the gain. First, even a globally word-shuffled rationale substantially outperforms the no-rationale baseline, indicating a strong lexical activation effect. More importantly, the additional gain from structured text appears to arise less from sentence-level logical ordering and more from short-range token adjacency. Preserving contiguous windows of just n⋆=2--3 tokens recovers most of the remaining gain toward full CoT performance. Supporting experiments rule out copying of explicit answer declarations or answer values, as well as full grammatical realization, as primary drivers. Further generalization experiments show that the qualitative pattern remains stable across multiple model families, parameter scales, and datasets. These results support a local co-occurrence activation (LCA) account of probe-time CoT, in which the observed gains appear to arise primarily from lexical activation and short-range token co-occurrence rather than sentence-level logical derivation.
Chain-of-thought (CoT) prompting assumes that generated reasoning reflects a model's internal computation. We show this assumption is wrong in a specific, measurable way: models internally detect their own reasoning errors but outwardly express confidence in them. A linear probe on hidden states predicts trace correctness with 0.95 AUROC -- from the very first reasoning step (0.79) -- while verbalized confidence for wrong traces is 4.55/5, nearly identical to correct ones (4.87/5). A text-surface classifier achieves only 0.59 on the same data, confirming a 0.20-point gap invisible in the generated text. This hidden error awareness holds across three model families (Qwen, Llama, Phi), 1.5B-72B parameters, and RL-trained reasoning models (DeepSeek-R1, 0.852 AUROC). The natural question is whether this signal can fix the errors it detects. It cannot. Four interventions -- activation steering, probe-guided best-of-N, self-correction, and activation patching -- all fail; patching destroys output coherence entirely. The signal is diagnostic, not causal: a readout of computation quality, not a lever to redirect it. This delineates a boundary for mechanistic interpretability: error representations during reasoning are fundamentally different from the factual knowledge representations that prior work has successfully edited.
Chain-of-thought (CoT) reasoning improves multi-step problem solving, but long reasoning traces inflate inference cost. Token-level CoT compression reduces this cost by pruning full reasoning chains into shorter traces for model adaptation, making token selection the central challenge. Existing methods often rely on external scorers or heuristic signals only indirectly tied to the model's internal answer computation. We instead adopt a model-internal perspective: as the model forms an answer, each reasoning token leaves a ripple in the residual stream, the model's \emph{stream of thought}, and the magnitude of this ripple reflects the token's contribution to the answer computation. Building on this view, we propose \textsc{MIST} (Model-Internal Saliency for Token-level CoT compression), which defines token importance along two complementary axes: \emph{necessity}, the drop in answer likelihood when a token's internal contribution is removed, and \emph{sufficiency}, the gain in answer likelihood when that contribution alone is provided. Combining the two yields a unified importance score for pruning. Across four reasoning benchmarks and four models, \textsc{MIST} consistently outperforms baseline methods, suggesting that model-internal saliency provides an effective proxy for reasoning-token importance.