Structural Rationale Distillation via Reasoning Space Compression

• URL: http://arxiv.org/abs/2605.07139v1
• Date: Fri, 08 May 2026 02:15:52 GMT
• Title: Structural Rationale Distillation via Reasoning Space Compression
• Abstract summary: Reasoning Path Compression constrains the teacher to follow a compact, dynamically maintained bank of reusable high-level reasoning paths.<n>For each training question, D-RPC retrieves the most relevant path and conditions the teacher to follow it, producing rationales consistent across similar problems yet diverse enough to cover different problem types.
• Score: 34.91106623292321
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: When distilling reasoning from large language models (LLMs) into smaller ones, teacher rationales for similar problems often vary wildly in structure and strategy. Like a chef who makes the same dish differently each time, this inconsistency burdens the student with noisy supervision that is hard to internalize. We propose Distillation through Reasoning Path Compression (D-RPC), which constrains the teacher to follow a compact, dynamically maintained bank of reusable high-level reasoning paths. For each training question, D-RPC retrieves the most relevant path and conditions the teacher to follow it, producing rationales that are consistent across similar problems yet diverse enough to cover different problem types. A PAC-Bayes analysis formalizes the resulting trade-off between bank size and coverage: smaller banks reduce supervision entropy but risk coverage gaps, and the generalization bound identifies an optimal intermediate size confirmed by our ablations. Across five math and commonsense reasoning benchmarks with two student models, D-RPC consistently outperforms chain-of-thought distillation, freeform rationale generation, direct distillation, and structured-supervision baselines, while using fewer tokens than template-heavy alternatives.

Related papers

• WhisperRec: Latent Reasoning for Efficient Foundation Recommendation Models [51.88075626243057]
  We propose WhisperRec, an efficient latent reasoning framework for foundation recommendation models (FRMs)<n>WhisperRec compresses teacher-generated Chain-of-Thought (CoT) into learnable latent reasoning tokens.<n>We show that WhisperRec consistently outperforms explicit-CoT methods and conventional baselines.
  arXiv  Detail & Related papers  (2026-07-29T08:48:35Z)
• When Compression Helps and When It Hurts: Condition-Aware Analysis of Chain-of-Thought Distillation [22.684181578779132]
  Chain-of-Thought (CoT) distillation transfers multi-step reasoning from large reasoning models to smaller students.<n>Existing CoT compression methods fall into two families, selective pruning and generative rewriting.<n>We recast CoT compression along three dimensions: importance criterion, restructuring level, and compression budget.
  arXiv  Detail & Related papers  (2026-06-19T19:31:37Z)
• Reasoning Compression with Mixed-Policy Distillation [20.7258653384411]
  Reasoning-centric large language models often incur excessive token usage and high inference-time decoding cost.<n>We propose Mixed-Policy Distillation (MPD), a reasoning compression framework that transfers concise reasoning behavior from a larger-sized teacher to a smaller student.<n>MPD reduces token usage by up to 27.1% while improving performance across multiple reasoning benchmarks.
  arXiv  Detail & Related papers  (2026-05-09T08:04:47Z)
• Distilling Long-CoT Reasoning through Collaborative Step-wise Multi-Teacher Decoding [25.81162875653095]
  We introduce CoRD, a collaborative multi-teacher decoding framework that performs step-wise reasoning synthesis guided by predictive perplexity-based scoring and beam search.<n>Experiments show that CoRD produces higher-quality reasoning data and achieves near teacher-level student performance with fewer, structured supervision signals.
  arXiv  Detail & Related papers  (2026-05-04T07:26:41Z)
• One Refiner to Unlock Them All: Inference-Time Reasoning Elicitation via Reinforcement Query Refinement [37.27419953581617]
  Large Language Models (LLMs) often fail to utilize their latent reasoning capabilities.<n>We propose ReQueR, a modular framework that treats reasoning elicitation as an inference-time alignment task.
  arXiv  Detail & Related papers  (2026-04-28T09:52:21Z)
• 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)
• "The Whole Is Greater Than the Sum of Its Parts": A Compatibility-Aware Multi-Teacher CoT Distillation Framework [16.96094045628127]
  Chain-of-Thought (CoT) reasoning empowers Large Language Models (LLMs) with remarkable capabilities but typically requires prohibitive parameter scales.<n>CoT distillation has emerged as a promising paradigm to transfer reasoning prowess into compact Student Models (SLMs)<n>We introduce COMPACT, a framework that adaptively fuses supervisions from different teachers by dynamically weighting teacher gradients.
  arXiv  Detail & Related papers  (2026-01-20T14:05:19Z)
• Consistency Is Not Always Correct: Towards Understanding the Role of Exploration in Post-Training Reasoning [75.79451512757844]
  Foundation models exhibit broad knowledge but limited task-specific reasoning.<n> RLVR and inference scaling motivate post-training strategies such as RLVR and inference scaling.<n>We show that RLVR induces a squeezing effect, reducing reasoning entropy and forgetting some correct paths.
  arXiv  Detail & Related papers  (2025-11-10T18:25:26Z)
• Distilling the Implicit Multi-Branch Structure in LLMs' Reasoning via Reinforcement Learning [63.888013006686364]
  Distilling reasoning paths from teacher to student models via supervised fine-tuning (SFT) provides a shortcut for improving the reasoning ability of Large Language Models (LLMs)<n>We propose RLKD, a reinforcement learning-based distillation framework guided by a novel Generative Structure Reward Model (GSRM)<n>Our GSRM converts reasoning paths into multiple meta-reasoning-solving steps and computes rewards to measure structural alignment between student and teacher reasoning.
  arXiv  Detail & Related papers  (2025-05-22T02:36:36Z)
• Structured Agent Distillation for Large Language Model [56.38279355868093]
  We propose Structured Agent Distillation, a framework that compresses large LLM-based agents into smaller student models.<n>Our method segments trajectories into [REASON] and [ACT] spans, applying segment-specific losses to align each component with the teacher's behavior.<n>Experiments on ALFWorld, HotPotQA-ReAct, and WebShop show that our approach consistently outperforms token-level and imitation learning baselines.
  arXiv  Detail & Related papers  (2025-05-20T02:01:55Z)

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.