| Challenge: | Large Reasoning Models (LRMs) show strong System-2-style reasoning, but at the cost of significant computational overhead. |
| Approach: | They propose a two-stage curriculum distillation framework which builds a robust internal problem-solving student model and then teaches the student model to externalize this knowledge as explicit reasoning. |
| Outcome: | The proposed model outperforms single-stage baselines on mathematical benchmarks and significantly outperformed LRMs on complex tasks. |
Similar Papers
Divide-or-Conquer? Which Part Should You Distill Your LLM? (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Recent studies have shown that Large Language Models (LLMs) can solve reasoning tasks better when they are encouraged to solve subtasks of the main task first. |
| Approach: | They propose a strategy that breaks down reasoning tasks into a problem decomposition phase and a solution phase and propose 'smaller' models that can achieve good generalization. |
| Outcome: | The proposed approach outperforms a single stage solution in two tasks and their impact on reasoning outcomes and inference cost. |
Small Models Struggle to Learn from Strong Reasoners (2025.findings-acl)
Copied to clipboard
Yuetai Li, Xiang Yue, Zhangchen Xu, Fengqing Jiang, Luyao Niu, Bill Yuchen Lin, Bhaskar Ramasubramanian, Radha Poovendran
| Challenge: | a small learning gap exists between large and small language models . long CoT data and large model responses are not beneficial for small models - a problem that may be due to the small student model's ability to handle distribution shifts. |
| Approach: | They propose a mix distillation strategy that balances reasoning complexity by combining long and short CoT examples or reasoning from both larger and smaller models. |
| Outcome: | The proposed strategy outperforms training on large and small models on short CoT and small model CoT. |
TinyThinker: Distilling Reasoning through Coarse-to-Fine Knowledge Internalization with Self-Reflection (2025.naacl-long)
Copied to clipboard
| Challenge: | Large Language Models exhibit impressive reasoning capabilities across diverse tasks . direct training on synthesized reasoning data may lead to superficial imitation of reasoning process, authors argue . |
| Approach: | They propose a framework that introduces a three-stage process that incrementally guides the student model through the reasoning process, progressively refining knowledge from coarse to fine granularity. |
| Outcome: | The proposed framework achieves superior performance on commonsense reasoning benchmarks and can be extended to other knowledge-intensive reasoning tasks. |
Distilling Reasoning Capabilities into Smaller Language Models (2023.findings-acl)
Copied to clipboard
| Challenge: | a step-by-step reasoning approach like chain of thought has proved to be effective in eliciting reasoning abilities in large language models. |
| Approach: | They propose a knowledge distillation approach that leverages CoT reasoning capabilities of larger models and distills them into smaller models. |
| Outcome: | The proposed scheme boosts the performance of smaller models over 70% on multiple reasoning datasets. |
Why Can Distillation Work with Limited Resources? A Systematic Study (2026.findings-acl)
Copied to clipboard
Xiao Hu, Xingyu Lu, Liyuan Mao, YiFan Zhang, Tianke Zhang, Bin Wen, Fan Yang, Tingting Gao, Guorui Zhou
| Challenge: | Recent advances in large language models have driven reasoning performance . low-resource distillation can boost models' performance, but a framework is missing . |
| Approach: | They conduct a controlled experiment to find out why low-resource distillation can boost model performance . they find that distillation enhances the presence of advanced cognitive behaviors . |
| Outcome: | The proposed model shows more flexible reasoning, the authors show . they show that distillation enhances the presence of advanced cognitive behaviors . |
Marco-o1 v2: Towards Widening The Distillation Bottleneck for Reasoning Models (2025.acl-long)
Copied to clipboard
Huifeng Yin, Yu Zhao, Minghao Wu, Xuanfan Ni, Bo Zeng, Huaiyu.wh Huaiyu.wh, Tianqi Shi, Liangying Shao, Chenyang Lyu, Longyue Wang, Weihua Luo, Kaifu Zhang
| Challenge: | Recent efforts to distill large reasoning models into smaller lightweight models have shown competitive performances. |
| Approach: | They propose to distill long Chain-of-Thought data to improve SFT and RL methods by constructing data from scratch using Monte Carlo Tree Search. |
| Outcome: | The proposed method significantly improves reasoning performance on various benchmarks such as math (GSM8K, MATH, AIME). |
DistilQwen2.5: Industrial Practices of Training Distilled Open Lightweight Language Models (2025.acl-industry)
Copied to clipboard
| Challenge: | Existing studies on distilled lightweight LLMs have focused on transferring knowledge from a larger model (the teacher) to a smaller model (sector). |
| Approach: | They propose a family of distilled, lightweight LLMs derived from Qwen2.5 models. |
| Outcome: | Experimental results show that the distilled models have significantly stronger instruction-following capabilities than the original models. |
Improve Student’s Reasoning Generalizability through Cascading Decomposed CoTs Distillation (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies have tried to distill these capabilities into smaller language models (SLMs) however, these capabilities are often associated with more parameters, which is not practical to emergent in smaller models. |
| Approach: | They propose to decompose the traditional single-step learning process into two cascaded learning steps by restructuring the training objectives and concatenating the question with the rationale as input. |
| Outcome: | Extensive experiments show that the proposed method improves reasoning generalizability and diversity of the model. |
SIKeD: Self-guided Iterative Knowledge Distillation for Mathematical Reasoning (2025.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) can generate intermediate reasoning process for multistep reasoning tasks. |
| Approach: | They propose a distillation method that teaches the model to approach a task using different strategies and the model uses its self-generated on-policy outputs to choose the most suitable strategy. |
| Outcome: | The proposed method significantly outperforms distillation techniques on large models of different sizes. |
Teaching Small Language Models Reasoning through Counterfactual Distillation (2024.emnlp-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) have demonstrated remarkable performance in a wide range of downstream tasks. |
| Approach: | They propose a counterfactual distillation framework that leverages LLMs to generate high-quality counterfacts and utilizes multi-view CoT to enhance the diversity of reasoning samples. |
| Outcome: | The proposed framework enhances reasoning capabilities of large language models and is more robust to OOD data. |