Reliable Chain-of-Thought via Prefix Consistency

• URL: http://arxiv.org/abs/2605.07654v1
• Date: Fri, 08 May 2026 12:28:05 GMT
• Title: Reliable Chain-of-Thought via Prefix Consistency
• Abstract summary: We observe that traces with correct answers reproduce their original answer more often than traces with wrong answers.<n>We use this difference as a reliability signal, prefix consistency, that weights each candidate answer by how often it reappears under regeneration.
• Score: 6.053609157192373
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large Language Models often improve accuracy on reasoning tasks by sampling multiple Chain-of-Thought (CoT) traces and aggregating them with majority voting (MV), a test-time technique called self-consistency. When we truncate a CoT partway through and regenerate the remainder, we observe that traces with correct answers reproduce their original answer more often than traces with wrong answers. We use this difference as a reliability signal, prefix consistency, that weights each candidate answer by how often it reappears under regeneration. It requires no access to token log-probabilities or self-rating prompts. Across five reasoning models and four math and science benchmarks, prefix consistency is the best correctness predictor in most settings, and reweighting votes by it reaches Standard MV plateau accuracy at up to 21x fewer tokens (median 4.6x). Our code is available at https://github.com/naoto-iwase/prefix-consistency.

Related papers

• Does Verbose Chain-of-Thought Really Help? In-Distribution Evidence that Content, Not Length, Matters [10.230437172157474]
  Chain-of-thought prompting improves LLM reasoning, but the source is contested.<n>We repeatedly sample each model on the same question and pair a shorter with a longer of its own natural generations that follow the same reasoning plan.<n>We find that the extra tokens leave accuracy essentially unchanged for every independently-trained reasoner.<n>We ask whether two traces expressing the same semantic content produce different outcomes when one is more verbose.
  arXiv  Detail & Related papers  (2026-06-29T11:06:46Z)
• FineVerify: Scaling Test-Time Compute with Fine-Grained Self-Verification for Agentic Search [88.16262636915975]
  FineVerify is a fine-grained self-verification framework for agentic search.<n>It decomposes each question into checkable sub-questions, verifies sampled candidates, and selects the candidate with the highest aggregated score.<n>FineVerify consistently outperforms standard scaling baselines.
  arXiv  Detail & Related papers  (2026-05-30T10:21:20Z)
• Self-Verified Distillation: Your Language Model Is Secretly Its Own Synthetic Data Pipeline [56.53954182896384]
  We propose Self-Verified Distillation, a simple post-training refinement algorithm for large language models.<n>Self-Verified Distillation generates candidate solutions to unlabeled seed questions.<n>It filters them using prompt-based self-verification, and trains on the resulting self-curated dataset.<n>We find that sampling more candidate generations and using a larger verification budget during training data construction produces higher-quality self-curated data.
  arXiv  Detail & Related papers  (2026-05-20T17:26:10Z)
• Same Question, Different Answers: Evaluating LLM Reliability Beyond Accuracy [41.17236645999555]
  We study how model answers change under meaning-preserving paraphrases across factual question answering and mathematical reasoning tasks.<n>Across four benchmarks and 13 models, we find that model outputs frequently depend on the exact wording of the prompt.<n>For many questions, models alternate between correct and incorrect answers depending on phrasing, with mismatch rates reaching more than 23%.
  arXiv  Detail & Related papers  (2026-05-18T16:45:13Z)
• Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models [17.588873255093596]
  Large Reasoning Models (LRMs) achieve strong performance by generating long chains of thought (CoT)<n>LRMs often overthink, continuing to reason after a solution has already stabilized and thereby wasting tokens and increasing latency.<n>We propose PUMA, a plug-and-play framework that combines a lightweight Redundancy Detector with answer-level verification.
  arXiv  Detail & Related papers  (2026-05-17T22:04:11Z)
• The Last Word Often Wins: A Format Confound in Chain-of-Thought Corruption Studies [0.0]
  Corruption studies infer which steps are computationally important'' from accuracy loss when steps are corrupted.<n>We show that when benchmark chains end with an explicit terminal answer line, these tests largely measure emphanswer placement rather than where intermediate computation is carried out.
  arXiv  Detail & Related papers  (2026-05-11T16:26:50Z)
• Test-Time Scaling with Diffusion Language Models via Reward-Guided Stitching [66.39914384073145]
  We propose a self-consistency framework that turns cheap diffusion-sampled reasoning into a reusable pool of step-level candidates.<n>We find that step-level recombination is most beneficial on harder problems.<n>Our training-free framework improves average accuracy by up to 2 across six math and coding tasks.
  arXiv  Detail & Related papers  (2026-02-26T11:08:39Z)
• Probing the Trajectories of Reasoning Traces in Large Language Models [4.599673637363014]
  We propose a protocol to probe the trajectories of reasoning traces in large language models.<n>We find that accuracy and decision commitment consistently increase as the percentage of provided reasoning tokens grows.<n>We show that trajectory probing provides diagnostics for efficient and safer deployment of reasoning models.
  arXiv  Detail & Related papers  (2026-01-30T16:45:16Z)
• Multiplex Thinking: Reasoning via Token-wise Branch-and-Merge [87.51901436392427]
  Large language models often solve complex reasoning tasks more effectively with Chain-of-Thought (CoT)<n>Humans, by contrast, often reason softly by maintaining a tractable probability distribution over plausible next steps.<n>We propose Multiplex Thinking, a soft reasoning mechanism that samples K candidate tokens and aggregates their embeddings into a single continuous multiplex token.<n>Multiplex Thinking is self-adaptive: when the model is confident, the multiplex token is nearly discrete and behaves like standard CoT.
  arXiv  Detail & Related papers  (2026-01-13T18:48:00Z)
• Think-at-Hard: Selective Latent Iterations to Improve Reasoning Language Models [22.525318796588568]
  Think-at-Hard (TaH) is a dynamic latent thinking method that iterates deeper only at hard tokens.<n>TaH boosts reasoning performance across five challenging benchmarks.
  arXiv  Detail & Related papers  (2025-11-11T18:57:02Z)
• Mind the Gap: A Closer Look at Tokenization for Multiple-Choice Question Answering with LLMs [16.357595595062946]
  There is no consensus on how to tokenize the space following the colon, often overlooked as a trivial choice.<n>Surprisingly, we are able to recommend one specific strategy -- tokenizing the space together with the answer letter.<n>Our findings underscore the importance of careful evaluation design and highlight the need for standardized, transparent evaluation protocols.
  arXiv  Detail & Related papers  (2025-09-18T14:47:58Z)
• Latent Self-Consistency for Reliable Majority-Set Selection in Short- and Long-Answer Reasoning [17.045726739741813]
  We introduce Latent Self-Consistency, which selects the most semantically consistent response using learnable token embeddings.<n>A lightweight forward generation of summary tokens increases inference time by less than 1% and requires no changes to the model architecture.
  arXiv  Detail & Related papers  (2025-08-25T18:36:28Z)
• Beyond the Last Answer: Your Reasoning Trace Uncovers More than You Think [51.0691253204425]
  We analyze intermediate reasoning steps, termed subthoughts, to answer two questions: Does the final answer reliably represent the model's optimal conclusion?<n>Our approach involves segmenting a reasoning trace into sequential subthoughts based on linguistic cues.<n>We find that aggregating these answers by selecting the most frequent one (the mode) often yields significantly higher accuracy compared to relying solely on the answer derived from the original complete trace.
  arXiv  Detail & Related papers  (2025-04-29T12:39:07Z)
• GRACE: Discriminator-Guided Chain-of-Thought Reasoning [75.35436025709049]
  We propose Guiding chain-of-thought ReAsoning with a CorrectnEss Discriminator (GRACE) to steer the decoding process towards producing correct reasoning steps. GRACE employs a discriminator trained with a contrastive loss over correct and incorrect steps, which is used during decoding to score next-step candidates.
  arXiv  Detail & Related papers  (2023-05-24T09:16:51Z)
• Faithful Chain-of-Thought Reasoning [51.21714389639417]
  Chain-of-Thought (CoT) prompting boosts Language Models' (LM) performance on a gamut of reasoning tasks. We propose Faithful CoT, a reasoning framework involving two stages: Translation and Problem Solving. This guarantees that the reasoning chain provides a faithful explanation of the final answer.
  arXiv  Detail & Related papers  (2023-01-31T03:04:26Z)
• Self-Consistency Improves Chain of Thought Reasoning in Language Models [53.45015291520658]
  We explore a simple ensemble strategy, self-consistency, that significantly improves the reasoning accuracy of large language models. For arithmetic and commonsense reasoning benchmarks we find that self-consistency yields significant accuracy improvements.
  arXiv  Detail & Related papers  (2022-03-21T17:48:52Z)

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.