Decoding Answers Before Chain-of-Thought: Evidence from Pre-CoT Probes and Activation Steering

• URL: http://arxiv.org/abs/2603.01437v1
• Date: Mon, 02 Mar 2026 04:33:55 GMT
• Title: Decoding Answers Before Chain-of-Thought: Evidence from Pre-CoT Probes and Activation Steering
• Authors: Kyle Cox, Darius Kianersi, Adrià Garriga-Alonso,
• Abstract summary: Chain-of-thought (CoT) has become central to scaling reasoning capabilities in large language models.<n>We show that instruction-tuned models often determine their answer before generating CoT.
• Score: 5.427346259545067
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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. However, the utility of CoT toward interpretability depends upon its faithfulness -- whether the model's stated reasoning reflects the underlying decision process. We provide mechanistic evidence that instruction-tuned models often determine their answer before generating CoT. Training linear probes on residual stream activations at the last token before CoT, we can predict the model's final answer with 0.9 AUC on most tasks. We find that these directions are not only predictive, but also causal: steering activations along the probe direction flips model answers in over 50% of cases, significantly exceeding orthogonal baselines. When steering induces incorrect answers, we observe two distinct failure modes: non-entailment (stating correct premises but drawing unsupported conclusions) and confabulation (fabricating false premises). While post-hoc reasoning may be instrumentally useful when the model has a correct pre-CoT belief, these failure modes suggest it can result in undesirable behaviors when reasoning from a false belief.

Related papers

• Temporal Predictors of Outcome in Reasoning Language Models [0.0]
  Chain-of-thought (CoT) paradigm uses the elicitation of step-by-step rationales as a proxy for reasoning.<n>We show that, for harder questions, a drop in predictive accuracy highlights a selection artifact.<n>Overall, our results imply that for reasoning models, internal self-assessment of success tends to emerge after only a few tokens.
  arXiv  Detail & Related papers  (2025-11-03T08:57:18Z)
• Reasoning Models Sometimes Output Illegible Chains of Thought [0.0]
  Language models trained via outcome-based reinforcement learning (RL) to reason using chain-of-thought (CoT) have shown remarkable performance.<n>We study CoT legibility across 14 reasoning models, finding that RL often causes reasoning to become illegible to both humans and AI monitors.<n>We show that models use illegible reasoning to reach correct answers (accuracy dropping by 53% when forced to use only legible portions) yet find no correlation between legibility and performance when resampling.
  arXiv  Detail & Related papers  (2025-10-31T10:16:35Z)
• AdvChain: Adversarial Chain-of-Thought Tuning for Robust Safety Alignment of Large Reasoning Models [62.70575022567081]
  We propose AdvChain, an alignment paradigm that teaches models dynamic self-correction through adversarial CoT tuning.<n>Our work establishes a new direction for building more robust and reliable reasoning models.
  arXiv  Detail & Related papers  (2025-09-29T04:27:23Z)
• Unveiling Confirmation Bias in Chain-of-Thought Reasoning [12.150655660758359]
  Chain-of-thought (CoT) prompting has been widely adopted to enhance the reasoning capabilities of large language models (LLMs)<n>This work presents a novel perspective to understand CoT behavior through the lens of textitconfirmation bias in cognitive psychology.
  arXiv  Detail & Related papers  (2025-06-14T01:30:17Z)
• Counterfactual reasoning: an analysis of in-context emergence [57.118735341305786]
  We show that language models are capable of counterfactual reasoning.<n>We find that self-attention, model depth and pre-training data diversity drive performance.<n>Our findings extend to counterfactual reasoning under SDE dynamics.
  arXiv  Detail & Related papers  (2025-06-05T16:02:07Z)
• A Closer Look at Bias and Chain-of-Thought Faithfulness of Large (Vision) Language Models [58.32070787537946]
  Chain-of-thought (CoT) reasoning enhances performance of large language models.<n>We present the first comprehensive study of CoT faithfulness in large vision-language models.
  arXiv  Detail & Related papers  (2025-05-29T18:55:05Z)
• SEAL: Steerable Reasoning Calibration of Large Language Models for Free [58.931194824519935]
  Large Language Models (LLMs) have demonstrated compelling capabilities for complex reasoning tasks via the extended chain-of-thought (CoT) reasoning mechanism.<n>Recent studies reveal substantial redundancy in the CoT reasoning traces, which negatively impacts model performance.<n>We introduce SEAL, a training-free approach that seamlessly calibrates the CoT process, improving accuracy while demonstrating significant efficiency gains.
  arXiv  Detail & Related papers  (2025-04-07T02:42:07Z)
• Chain-of-Probe: Examining the Necessity and Accuracy of CoT Step-by-Step [81.50681925980135]
  We propose a method to probe changes in the mind during the model's reasoning.<n>By analyzing patterns in mind change, we examine the correctness of the model's reasoning.<n>Our validation reveals that many responses, although correct in their final answer, contain errors in their reasoning process.
  arXiv  Detail & Related papers  (2024-06-23T15:50:22Z)
• Measuring Faithfulness in Chain-of-Thought Reasoning [19.074147845029355]
  Large language models (LLMs) perform better when they produce step-by-step, "Chain-of-Thought" (CoT) reasoning before answering a question. It is unclear if the stated reasoning is a faithful explanation of the model's actual reasoning (i.e., its process for answering the question) We investigate hypotheses for how CoT reasoning may be unfaithful, by examining how the model predictions change when we intervene on the CoT.
  arXiv  Detail & Related papers  (2023-07-17T01:08:39Z)
• Advancing Counterfactual Inference through Nonlinear Quantile Regression [77.28323341329461]
  We propose a framework for efficient and effective counterfactual inference implemented with neural networks. The proposed approach enhances the capacity to generalize estimated counterfactual outcomes to unseen data. Empirical results conducted on multiple datasets offer compelling support for our theoretical assertions.
  arXiv  Detail & Related papers  (2023-06-09T08:30:51Z)
• Logical Satisfiability of Counterfactuals for Faithful Explanations in NLI [60.142926537264714]
  We introduce the methodology of Faithfulness-through-Counterfactuals. It generates a counterfactual hypothesis based on the logical predicates expressed in the explanation. It then evaluates if the model's prediction on the counterfactual is consistent with that expressed logic.
  arXiv  Detail & Related papers  (2022-05-25T03:40:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.