Pith. sign in

REVIEW 6 cited by

Deconstructing Long Chain-of-Thought: A Structured Reasoning Optimization Framework for Long CoT Distillation

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2503.16385 v1 pith:5PMX4ORI submitted 2025-03-20 cs.AI

classification cs.AI
keywords distillationlongreasoningmodelschain-of-thoughtdataapproachcapabilities
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Recent advancements in large language models (LLMs) have demonstrated remarkable reasoning capabilities through long chain-of-thought (CoT) reasoning. The R1 distillation scheme has emerged as a promising approach for training cost-effective models with enhanced reasoning abilities. However, the underlying mechanisms driving its effectiveness remain unclear. This study examines the universality of distillation data and identifies key components that enable the efficient transfer of long-chain reasoning capabilities in LLM distillation. Our findings reveal that the effectiveness of long CoT reasoning distillation from teacher models like Qwen-QwQ degrades significantly on nonhomologous models, challenging the assumed universality of current distillation methods. To gain deeper insights into the structure and patterns of long CoT reasoning, we propose DLCoT (Deconstructing Long Chain-of-Thought), a distillation data enhancement framework. DLCoT consists of three key steps: (1) data segmentation to decompose complex long CoT structures, (2) simplification by eliminating unsolvable and redundant solutions, and (3) optimization of intermediate error states. Our approach significantly improves model performance and token efficiency, facilitating the development of high-performance LLMs.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Is More Privileged Information Better? From Solution Traces to Problem-Solving Structure in Self-Distilled Reasoning

    cs.AI 2026-08 conditional novelty 6.0 of 10

    Structured problem-space guidance, rather than the full reference solution, yields the highest aggregate question-only accuracy in on-policy self-distillation across three math benchmarks and model scales.

  2. Reasoning Denoiser: Denoising Reasoning Traces for Hallucination Detection in Large Reasoning Models

    cs.AI 2026-07 conditional novelty 6.0 of 10

    REDE removes irrelevant and repetitive reasoning steps using final-answer attention as supervision, improving hallucination detection AUROC by up to ~19 points over unfiltered traces.

  3. Concise Reasoning, Big Gains: Pruning Long Reasoning Trace with Difficulty-Aware Prompting

    cs.AI 2025-05 conditional novelty 6.0 of 10

    Fine-tuning small models on difficulty-adapted, shortened reasoning traces (LiteCoT) yields equal or better benchmark accuracy than training on much longer traces, with far fewer tokens.

  4. Are Large Language Models Reliable AI Scientists? Assessing Reverse-Engineering of Black-Box Systems

    cs.LG 2025-05 conditional novelty 6.0 of 10

    LLMs struggle to use passive observations for reverse engineering, but active intervention improves performance, largely through the process of generating queries rather than the data obtained.

  5. Amplify Adjacent Token Differences: Enhancing Long Chain-of-Thought Reasoning with Shift-FFN

    cs.CL 2025-05 conditional novelty 6.0 of 10

    A gated Shift-FFN adapter that adds the previous token's representation to the current token's before the feedforward layer reduces repetitive looping and improves math accuracy in LoRA fine-tuned models trained on lo...

  6. Beyond Templates: Dynamic Adaptation of Reasoning Demonstrations via Feasibility-Aware Exploration

    cs.CL 2025-05 conditional novelty 4.0 of 10

    DART filters and rewrites expert reasoning demonstrations with the student model's own rollouts, then fine-tunes on those outcome-consistent adapted trajectories.

Pith tools