Structural Process Supervision for Latent Chain-of-Thought Reasoning

• URL: http://arxiv.org/abs/2609.09928v1
• Date: Wed, 09 Sep 2026 09:17:46 GMT
• Title: Structural Process Supervision for Latent Chain-of-Thought Reasoning
• Abstract summary: Prototype-Mediated Process Supervision (PMPS) projects latent embeddings and explicit chain-of-thought embeddings into a shared prototype space.<n>PMPS compresses output token length to under 50% of explicit CoT on GSM8K-Aug.<n>On larger models and a more challenging task, PMPS consistently attains the highest accuracy among all latent reasoning methods with comparable output length.
• Score: 45.1922274576773
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Latent reasoning approaches enhance token-level efficiency and robustness by replacing verbose, explicit chain-of-thought (CoT) tokens with compact continuous-space embeddings. However, existing methods lack direct process supervision over these latent embeddings, which often leads to representation collapse and uneven information distribution. To address this, we propose Prototype-Mediated Process Supervision (PMPS), which introduces learnable reasoning prototypes as semantic anchors to provide structural process-level supervision for latent reasoning. PMPS projects latent embeddings and explicit CoT embeddings into a shared prototype space, achieving many-to-many soft alignment between unequal-length representations through prototype assignment. Meanwhile, we introduce a Progressive Sequential Alignment (PSA) module to further guide training: positional priors initially encourage sequential alignment structure, then gradually relax to permit adaptive matching. Experimental results show that PMPS compresses output token length to under 50% of explicit CoT on GSM8K-Aug. Compared to leading baseline SIM-CoT, our method achieves average accuracy gains of 2.08% across different model families. On GPT-2, PMPS even surpasses CoT-SFT. On larger models and a more challenging task, PMPS consistently attains the highest accuracy among all latent reasoning methods with comparable output length.

Related papers

• Training Continuous Chain of Thought Models: A Tale of Two Regimes [39.805252492017715]
  Continuous Chain-of-Thought methods replace verbose reasoning traces with a short sequence of dense latent representations.<n>We introduce C-MTP, a simpler, faster direct supervision approach that models each latent as an average of the embeddings in the CoT traces to be compressed.<n>We extend the evaluation of Continuous CoT methods to complex tasks with longer reasoning traces.
  arXiv  Detail & Related papers  (2026-07-18T21:32:06Z)
• RuPLaR : Efficient Latent Compression of LLM Reasoning Chains with Rule-Based Priors From Multi-Step to One-Step [7.647393987025467]
  We introduce One-Model One-Step, a novel compression framework for Latent Reasoning with Rule-Based Priors.<n>Our method trains an LLM to autonomously generate latent reasoning tokens in a single training stage.<n>Experiments show that our framework improves accuracy by 11.1% over existing latent CoT methods.
  arXiv  Detail & Related papers  (2026-05-10T05:55:07Z)
• Alignment Imprint: Zero-Shot AI-Generated Text Detection via Provable Preference Discrepancy [51.887915969023965]
  We show that modern Large Language Models (LLMs) undergo alignment, leaving a measurable distributional imprint.<n>To mitigate the instability in high-entropy regions, we introduce Log-likelihood Alignment Preference Discrepancy (LAPD)<n>LAPD is a standardized information-weighted statistic based on alignment imprint.
  arXiv  Detail & Related papers  (2026-04-18T09:12:24Z)
• PLUME: Latent Reasoning Based Universal Multimodal Embedding [52.35354073629127]
  Universal multimodal embedding (UME) maps heterogeneous inputs into a shared retrieval space with a single model.<n>Recent approaches improve UME by generating explicit chain-of-thought (CoT) rationales before extracting embeddings.<n>We propose PLUME, a latent reasoning framework that advances UME by replacing verbalized CoT with a short autoregressive rollout of continuous latent states.
  arXiv  Detail & Related papers  (2026-04-02T14:04:53Z)
• EntroCoT: Enhancing Chain-of-Thought via Adaptive Entropy-Guided Segmentation [18.606842425858]
  Chain-of-Thought (CoT) prompting has significantly enhanced the mathematical reasoning capabilities of Large Language Models.<n>Existing fine-tuning datasets frequently suffer from the "answer right but reasoning wrong" probelm.<n>This paper proposes EntroCoT, a unified framework for automatically identifying and refining low-quality CoT supervision traces.
  arXiv  Detail & Related papers  (2026-01-07T10:02:27Z)
• Decoupling the Effect of Chain-of-Thought Reasoning: A Human Label Variation Perspective [60.45433515408158]
  We show that long Chain-of-Thought (CoT) serves as a decisive decision-maker for the top option but fails to function as a granular distribution calibrator for ambiguous tasks.<n>We observe a distinct "decoupled mechanism": while CoT improves distributional alignment, final accuracy is dictated by CoT content.
  arXiv  Detail & Related papers  (2026-01-06T16:26:40Z)
• SIM-CoT: Supervised Implicit Chain-of-Thought [108.30049193668083]
  Implicit Chain-of-Thought (CoT) methods offer a token-efficient alternative to explicit CoT reasoning in Large Language Models.<n>We identify a core latent instability issue when scaling the computational budget of implicit CoT.<n>We propose SIM-CoT, a plug-and-play training module that introduces step-level supervision to stabilize and enrich the latent reasoning space.
  arXiv  Detail & Related papers  (2025-09-24T17:01:32Z)
• Expediting and Elevating Large Language Model Reasoning via Hidden Chain-of-Thought Decoding [14.175444025026508]
  Large language models (LLMs) have demonstrated remarkable capabilities in tasks requiring chain-of-thought (CoT) prompting. generating the full CoT process results in significantly longer output sequences, leading to increased computational costs and latency during inference. We propose a novel approach to compress the CoT process through semantic alignment, enabling more efficient decoding while preserving the benefits of CoT reasoning.
  arXiv  Detail & Related papers  (2024-09-13T06:29:20Z)
• Fine-Tuning on Diverse Reasoning Chains Drives Within-Inference CoT Refinement in LLMs [63.36637269634553]
  We introduce a novel approach where LLMs are fine-tuned to generate a sequence of Diverse Chains of Thought (DCoT) within a single inference step.<n>We show that fine-tuning on DCoT improves performance over the CoT baseline across model families and scales.<n>Our work is also significant because both quantitative analyses and manual evaluations reveal the observed gains stem from the models' ability to refine an initial reasoning chain.
  arXiv  Detail & Related papers  (2024-07-03T15:01:18Z)

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.