Correct Reasoning Paths Visit Shared Decision Pivots

• URL: http://arxiv.org/abs/2509.21549v2
• Date: Sun, 26 Oct 2025 14:08:06 GMT
• Title: Correct Reasoning Paths Visit Shared Decision Pivots
• Abstract summary: We introduce the idea of decision pivots-minimal, verifiable checkpoints that any correct reasoning path must visit.<n>We propose a self-training pipeline that samples diverse reasoning paths and mines shared decision pivots.<n>The proposed method aligns reasoning without ground truth reasoning data or external metrics.
• Score: 11.42890083738685
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Chain-of-thought (CoT) reasoning exposes the intermediate thinking process of large language models (LLMs), yet verifying those traces at scale remains unsolved. In response, we introduce the idea of decision pivots-minimal, verifiable checkpoints that any correct reasoning path must visit. We hypothesize that correct reasoning, though stylistically diverse, converge on the same pivot set, while incorrect ones violate at least one pivot. Leveraging this property, we propose a self-training pipeline that (i) samples diverse reasoning paths and mines shared decision pivots, (ii) compresses each trace into pivot-focused short-path reasoning using an auxiliary verifier, and (iii) post-trains the model using its self-generated outputs. The proposed method aligns reasoning without ground truth reasoning data or external metrics. Experiments on standard benchmarks such as LogiQA, MedQA, and MATH500 show the effectiveness of our method.

Related papers

• Scaling LLM Reasoning from Minimal Labels: A Semi-Supervised Framework with a Lightweight Verifier [21.154049003675897]
  This paper presents a semi-supervised framework that scales reasoning learning from minimal supervision.<n>An entropy-based confidence threshold filters out unreliable samples, and the remaining high-confidence reasoning traces are used to fine-tune the model.<n> Experiments on Verifiable Math Problems (Orca-Math subset) and Question Answering on Image Scene Graphs (GQA) with Visual Programming show that our method achieves accuracy comparable to using 10-15x more labeled data.
  arXiv  Detail & Related papers  (2026-06-15T14:55:18Z)
• Reasoning with Sampling: Cutting at Decision Points [7.438249964230582]
  We show that sampling from a sharpened version of the base model's distribution elicits comparable reasoning without additional training, curated datasets, or verifiers.<n>A sampler needs to "mix" to the power distribution, which necessitates moving between modes of the target distribution.<n>We introduce an algorithm that uses the base model's next-token entropy as a proxy to identify key decision points and resample from those positions.
  arXiv  Detail & Related papers  (2026-05-28T17:57:32Z)
• LC-ERD: Mining Latent Logic for Self-Evolving Reasoning via Consistency-Regulated Reward Decomposition [55.572260012037084]
  We introduce LC-ERD (Logic-Consistent Endogenous Reward Decomposition), a framework framing self-alignment as latent structure mining.<n>We derive a Variational Logic Potential by aggregating consensus from the model's Latent Logic Expertise.<n>Experiments show LC-ERD delivers a robust self-evolution path, uncovering trade-offs between logic consistency and accuracy.
  arXiv  Detail & Related papers  (2026-05-19T07:27:50Z)
• 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)
• Directional Reasoning Trajectory Change (DRTC): Identifying Critical Trace Segments in Reasoning Models [0.0]
  Directional Reasoning Trajectory Change (DRTC) is a process-causal framework for interpreting long-form reasoning from a single on-policy rollout.<n>DRTC detects pivot decision points using uncertainty and distribution-shift signals.<n>It measures whether each intervention redirects the direction of the model's log-probability trajectory.
  arXiv  Detail & Related papers  (2026-02-17T03:38:16Z)
• Verifying Large Language Models' Reasoning Paths via Correlation Matrix Rank [71.09032766271493]
  Large language models (LLMs) are prone to errors and hallucinations.<n>How to check their outputs effectively and efficiently has become a critical problem in their applications.
  arXiv  Detail & Related papers  (2025-10-28T11:01:10Z)
• Is Chain-of-Thought Reasoning of LLMs a Mirage? A Data Distribution Lens [23.326813303795692]
  Chain-of-Thought (CoT) prompting has been shown to improve Large Language Model (LLM) performance on various tasks.<n>However, some initial findings suggest that CoT reasoning may be more superficial than it appears.
  arXiv  Detail & Related papers  (2025-08-02T04:37:28Z)
• Fractured Chain-of-Thought Reasoning [61.647243580650446]
  We introduce Fractured Sampling, a unified inference-time strategy that interpolates between full CoT and solution-only sampling.<n>We show that Fractured Sampling consistently achieves superior accuracy-cost trade-offs, yielding steep log-linear scaling gains in Pass@k versus token budget.
  arXiv  Detail & Related papers  (2025-05-19T11:30:41Z)
• Quantifying Logical Consistency in Transformers via Query-Key Alignment [20.636818928993684]
  We propose a novel, lightweight evaluation strategy for logical reasoning.<n>By computing a single forward pass and extracting a "QK-score" from carefully chosen heads, our method reveals latent representations that reliably separate valid from invalid inferences.
  arXiv  Detail & Related papers  (2025-02-24T10:02:50Z)
• Model-free Methods for Event History Analysis and Efficient Adjustment (PhD Thesis) [55.2480439325792]
  This thesis is a series of independent contributions to statistics unified by a model-free perspective.<n>The first chapter elaborates on how a model-free perspective can be used to formulate flexible methods that leverage prediction techniques from machine learning.<n>The second chapter studies the concept of local independence, which describes whether the evolution of one process is directly influenced by another.
  arXiv  Detail & Related papers  (2025-02-11T19:24:09Z)
• 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)
• Understanding Reasoning Ability of Language Models From the Perspective of Reasoning Paths Aggregation [110.71955853831707]
  We view LMs as deriving new conclusions by aggregating indirect reasoning paths seen at pre-training time. We formalize the reasoning paths as random walk paths on the knowledge/reasoning graphs. Experiments and analysis on multiple KG and CoT datasets reveal the effect of training on random walk paths.
  arXiv  Detail & Related papers  (2024-02-05T18:25:51Z)
• DCR: Divide-and-Conquer Reasoning for Multi-choice Question Answering with LLMs [9.561022942046279]
  We propose Divide and Conquer Reasoning (DCR) to enhance the reasoning capability of large language models (LLMs) We first categorize questions into two subsets based on confidence score ($mathcalCS$), which is estimated by statistical frequency of generated answers. In particular, we first categorize questions into two subsets based on confidence score ($mathcalCS$), which is estimated by statistical frequency of generated answers.
  arXiv  Detail & Related papers  (2024-01-10T14:38:46Z)
• Self-Evaluation Guided Beam Search for Reasoning [61.523627290397556]
  We introduce a stepwise self-evaluation mechanism to guide and calibrate the reasoning process of Large Language Model (LLM) We propose a decoding algorithm integrating the self-evaluation guidance via beam search. Our approach surpasses the corresponding Codex-backboned baselines in few-shot accuracy by $6.34%$, $9.56%$, and $5.46%$ on the GSM8K, AQuA, and StrategyQA.
  arXiv  Detail & Related papers  (2023-05-01T02:37:59Z)

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.