Not Just the Destination, But the Journey: Reasoning Traces Causally Shape Generalization Behaviors

• URL: http://arxiv.org/abs/2603.12397v1
• Date: Thu, 12 Mar 2026 19:19:10 GMT
• Title: Not Just the Destination, But the Journey: Reasoning Traces Causally Shape Generalization Behaviors
• Abstract summary: Chain-of-Thought (CoT) is often viewed as a window into LLM decision-making, yet recent work suggests it may function merely as post-hoc rationalization.<n>This raises a critical alignment question: Does the reasoning trace causally shape model generalization independent of the final answer?<n>To isolate reasoning's causal effect, we design a controlled experiment holding final harmful answers constant while varying reasoning paths.
• Score: 23.685279059830204
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Chain-of-Thought (CoT) is often viewed as a window into LLM decision-making, yet recent work suggests it may function merely as post-hoc rationalization. This raises a critical alignment question: Does the reasoning trace causally shape model generalization independent of the final answer? To isolate reasoning's causal effect, we design a controlled experiment holding final harmful answers constant while varying reasoning paths. We construct datasets with \textit{Evil} reasoning embracing malice, \textit{Misleading} reasoning rationalizing harm, and \textit{Submissive} reasoning yielding to pressure. We train models (0.6B--14B parameters) under multiple paradigms, including question-thinking-answer (QTA), question-thinking (QT), and thinking-only (T-only), and evaluate them in both think and no-think modes. We find that: (1) CoT training could amplify harmful generalization more than standard fine-tuning; (2) distinct reasoning types induce distinct behavioral patterns aligned with their semantics, despite identical final answers; (3) training on reasoning without answer supervision (QT or T-only) is sufficient to alter behavior, proving reasoning carries an independent signal; and (4) these effects persist even when generating answers without reasoning, indicating deep internalization. Our findings demonstrate that reasoning content is causally potent, challenging alignment strategies that supervise only outputs.

Related papers

• Ulterior Motives: Detecting Misaligned Reasoning in Continuous Thought Models [0.0]
  Chain-of-Thought (CoT) reasoning has emerged as a key technique for eliciting complex reasoning in Large Language Models (LLMs)<n>We introduce MoralChain, a benchmark of 12,000 social scenarios with parallel moral/immoral reasoning paths.<n>We show that continuous thought models can exhibit misaligned latent reasoning while producing aligned outputs.
  arXiv  Detail & Related papers  (2026-04-25T22:43:15Z)
• Thinking to Recall: How Reasoning Unlocks Parametric Knowledge in LLMs [45.274171760492685]
  We find that enabling reasoning substantially expands the capability boundary of the model's parametric knowledge recall.<n>We show that our insights can be harnessed to directly improve model accuracy by prioritizing reasoning trajectories that contain hallucination-free factual statements.
  arXiv  Detail & Related papers  (2026-03-10T16:59:20Z)
• Decoding Answers Before Chain-of-Thought: Evidence from Pre-CoT Probes and Activation Steering [5.427346259545067]
  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.
  arXiv  Detail & Related papers  (2026-03-02T04:33:55Z)
• CausalFlip: A Benchmark for LLM Causal Judgment Beyond Semantic Matching [50.65932158912512]
  We propose a new causal reasoning benchmark, CausalFlip, to encourage the development of new large language models.<n>CaulFlip consists of causal judgment questions built over event triples that could form different confounder, chain, and collider relations.<n>We evaluate LLMs under multiple training paradigms, including answer-only training, explicit Chain-of-Thought supervision, and a proposed internalized causal reasoning approach.
  arXiv  Detail & Related papers  (2026-02-23T18:06:15Z)
• Towards Generalizable Reasoning: Group Causal Counterfactual Policy Optimization for LLM Reasoning [50.352417879912515]
  Large language models (LLMs) excel at complex tasks with advances in reasoning capabilities.<n>We propose Group Causal Counterfactual Policy Optimization to explicitly train LLMs to learn generalizable reasoning patterns.<n>We then construct token-level advantages from this reward and optimize the policy, encouraging LLMs to favor reasoning patterns that are process-valid and counterfactually robust.
  arXiv  Detail & Related papers  (2026-02-06T08:03:11Z)
• 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)
• Revisiting Overthinking in Long Chain-of-Thought from the Perspective of Self-Doubt [74.35891434097053]
  Reasoning Large Language Models (RLLMs) have demonstrated impressive performance on complex tasks.<n>They often exhibit overthinking -- performing unnecessary reasoning steps even after arriving at the correct answer.<n>We present a quantitative analysis of overthinking from the perspective of self-doubt.<n>We introduce a simple and effective prompting method to reduce the model's over-reliance on input questions.
  arXiv  Detail & Related papers  (2025-05-29T14:30:02Z)
• The First Impression Problem: Internal Bias Triggers Overthinking in Reasoning Models [38.11937119873932]
  Reasoning models often exhibit overthinking, characterized by redundant reasoning steps.<n>We identify internal bias elicited by the input question as a key trigger of such behavior.
  arXiv  Detail & Related papers  (2025-05-22T09:35:52Z)
• Chain-of-Thought Reasoning In The Wild Is Not Always Faithful [3.048751803239144]
  Chain-of-Thought (CoT) reasoning has significantly advanced state-of-the-art AI capabilities.<n>We show that unfaithful CoT can also occur on realistic prompts with no artificial bias.
  arXiv  Detail & Related papers  (2025-03-11T17:56:30Z)
• 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)
• Distilling Reasoning Ability from Large Language Models with Adaptive Thinking [54.047761094420174]
  Chain of thought finetuning (cot-finetuning) aims to endow small language models (SLM) with reasoning ability to improve their performance towards specific tasks.<n>Most existing cot-finetuning methods adopt a pre-thinking mechanism, allowing the SLM to generate a rationale before providing an answer.<n>This mechanism enables SLM to analyze and think about complex questions, but it also makes answer correctness highly sensitive to minor errors in rationale.<n>We propose a robust post-thinking mechanism to generate answers before rationale.
  arXiv  Detail & Related papers  (2024-04-14T07:19:27Z)
• Mitigating Misleading Chain-of-Thought Reasoning with Selective Filtering [59.495717939664246]
  Large language models have manifested remarkable capabilities by leveraging chain-of-thought (CoT) reasoning techniques to solve intricate questions. We propose a novel approach called the selective filtering reasoner (SelF-Reasoner) that assesses the entailment relationship between the question and the candidate reasoning chain. SelF-Reasoner improves the fine-tuned T5 baseline consistently over the ScienceQA, ECQA, and LastLetter tasks.
  arXiv  Detail & Related papers  (2024-03-28T06:28:35Z)
• Self-Contradictory Reasoning Evaluation and Detection [31.452161594896978]
  We investigate self-contradictory (Self-Contra) reasoning, where the model reasoning does not support its answers. We find that LLMs often contradict themselves in reasoning tasks involving contextual information understanding or commonsense. We find that GPT-4 can detect Self-Contra with a 52.2% F1 score, much lower compared to 66.7% for humans.
  arXiv  Detail & Related papers  (2023-11-16T06:22:17Z)
• Implicit Chain of Thought Reasoning via Knowledge Distillation [58.80851216530288]
  Instead of explicitly producing the chain of thought reasoning steps, we use the language model's internal hidden states to perform implicit reasoning. We find that this approach enables solving tasks previously not solvable without explicit chain-of-thought, at a speed comparable to no chain-of-thought.
  arXiv  Detail & Related papers  (2023-11-02T17:59:49Z)

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.