Structural Rationale Distillation via Reasoning Space Compression
cs.CL, cs.AI, cs.LG
Submitted: 2026-05-08
Updated: 2026-11-04
Terminology
Sources
- Chain-of-Thought Reasoning In The Wild Is Not Always Faithful
- Thought Anchors: Which LLM Reasoning Steps Matter?
- Language Models are Few-Shot Learners
- MCC-KD: Multi-CoT Consistent Knowledge Distillation
- Skip-Thinking: Chunk-wise Chain-of-Thought Distillation Enable Smaller Language Models to Reason Better and Faster
- Unveiling the Key Factors for Distilling Chain-of-Thought Reasoning
- Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
- Training Verifiers to Solve Math Word Problems
- Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoning
- MIND: From Passive Mimicry to Active Reasoning through Capability-Aware Multi-Perspective CoT Distillation
- LoRA: Low-Rank Adaptation of Large Language Models
- Learning from Diverse Reasoning Paths with Routing and Collaboration
- Symbolic Chain-of-Thought Distillation: Small Models Can Also "Think" Step-by-Step
- Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problems
- Teaching Small Language Models to Reason
- ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory
- Explain Yourself! Leveraging Language Models for Commonsense Reasoning
- Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks
- Questions Are All You Need to Train a Dense Passage Retriever
- Distilling Reasoning Capabilities into Smaller Language Models
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data