MARD: Module-Aware Reasoning Distillation for Language Models with Adaptive Supervision (2026.acl-long)
Copied to clipboard
| Challenge: | Multi-step reasoning remains challenging for language models with limited capacity . et al., 2025) demonstrate remarkable reasoning capabilities across diverse tasks . |
| Approach: | They propose a module-aware reasoning distillation framework that explicitly targets key Transformer components for effective reasoning transfer. |
| Outcome: | The proposed framework targets key components for effective reasoning transfer . it adopts an offline distillation setting, where a strong teacher model provides reasoning trajectories in advance . |
Similar Papers
Improving Reasoning Capabilities in Small Models through Mixture-of-layers Distillation with Stepwise Attention on Key Information (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods focus on transferring teacher-generated rationales to student models, but do not explore teachers’ dynamic attention towards critical information during reasoning. |
| Approach: | They propose a method that transfers the teacher’s stepwise attention on key information to the student model and a Mixture of Layers module that allows dynamic alignment between the teacher and student. |
| Outcome: | The proposed framework achieves consistent performance improvements across multiple mathematical and commonsense reasoning datasets. |
MoDE-CoTD: Chain-of-Thought Distillation for Complex Reasoning Tasks with Mixture of Decoupled LoRA-Experts (2024.lrec-main)
Copied to clipboard
| Challenge: | Current Chain-of-thought Distillation methods hinder CoT reasoning performance . student models are separately distilled from specific reasoning tasks . parameter update of student models severely harms CoT ability on unseen reasoning tasks. |
| Approach: | They propose a method which distills Chain-of-thought reasoning ability of large language models to much smaller student models. |
| Outcome: | The proposed method improves the reasoning ability of large language models on 14 datasets. |
Long-Chain Reasoning Distillation via Adaptive Prefix Alignment (2026.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have demonstrated remarkable reasoning capabilities, especially in solving complex mathematical problems. |
| Approach: | They propose a framework that exploits teacher CoTs for distillation through adaptive prefix alignment. |
| Outcome: | The proposed framework outperforms baseline models on multiple mathematical reasoning benchmarks by over 3%. |
Efficient Transformer Knowledge Distillation: A Performance Review (2023.emnlp-industry)
Copied to clipboard
| Challenge: | Pretrained transformer language models have been gaining popularity in the field of natural language processing . however, there is no study into the intersection of these two fields . |
| Approach: | They propose a method to extract knowledge from transformers to produce high-performing efficient attention models with low costs. |
| Outcome: | The proposed model compression method preserves up to 98.6% of original model performance across short-context tasks and up to 95.8% on long-concept Named Entity Recognition tasks while decreasing inference times by up to 57%. |
Enhancing Long-Chain Reasoning Distillation through Error-Aware Self-Reflection (2026.findings-acl)
Copied to clipboard
Zhuoyang Wu, Xinze Li, Zhenghao Liu, Yukun Yan, Zhiyuan Liu, Minghe Yu, Cheng Yang, Yu Gu, Ge Yu, Maosong Sun
| Challenge: | Existing studies treat SLMs as student models and use long-form Chains-of-Thought (CoTs) as supervision signals for Supervised Fine-Tuning (SFT). Existing research focuses on distilling reasoning ability from LLMs to enhance the mathematical reasoning performance of small-scale models. |
| Approach: | They propose a framework that refines teacher CoTs through an error-aware reflection process to enable the student model to construct more tailored teacher Cots. |
| Outcome: | Experiments on multiple mathematical reasoning benchmarks show that ORION improves performance by more than 2% over all baselines. |
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). |
MIND: From Passive Mimicry to Active Reasoning through Capability-Aware Multi-Perspective CoT Distillation (2026.acl-long)
Copied to clipboard
Jin Cui, Jiaqi Guo, Jiepeng Zhou, Ruixuan Yang, Jiayi Lu, Jiajun Xu, Jiangcheng Song, Boran Zhao, Pengju Ren
| Challenge: | Existing approaches restrict students to following a single golden rationale and treat different reasoning paths independently, causing suboptimal performance. |
| Approach: | They propose a capability-adaptive framework that transitions distillation from passive mimicry to active cognitive construction and employ a feedback-driven inertia calibration mechanism to align supervision with the student’s current adaptability. |
| Outcome: | Experiments show that the proposed framework achieves state-of-the-art performance on both in-distribution and out-of distribution benchmarks. |
Distilling the Essence: Efficient Reasoning Distillation via Sequence Truncation (2026.findings-acl)
Copied to clipboard
Wei-Rui Chen, Vignesh Kothapalli, Ata Fatahibaarzi, Hejian Sang, Shao Tang, Qingquan Song, Zhipeng Wang, Muhammad Abdul-Mageed
| Challenge: | a large reasoning model (LRM) training on large amounts of reasoning data is computationally expensive. |
| Approach: | They propose a method to quantify computation-quality tradeoffs as a function of sequence length. |
| Outcome: | The proposed method reduces training time, memory and FLOPs by 50% on long training sequences while retaining the full-sequence performance. |
Capture the Key in Reasoning to Enhance CoT Distillation Generalization (2025.acl-long)
Copied to clipboard
| Challenge: | Existing distillation methods for Large Language Models (LLMs) focus on fine-tuning student SLMs on correct data, resulting in students struggling to learn the key instead of analyzing mistakes according to correct solutions. |
| Approach: | They propose a method that exposes key reasoning steps rather than simple fine-tuning students' CoTs data by using a set of prompts with similar reasoning paths but divergent conclusions. |
| Outcome: | The proposed method improves student SLMs' ability to learn key reasoning steps rather than fine-tuning them on teacher data. |
Evaluating distillation methods for data-efficient syntax learning (2025.findings-emnlp)
Copied to clipboard
| Challenge: | knowledge distillation (KD) targeting attention should selectively accelerate syntax acquisition, a study finds . logit-based KD dramatically improves data-efficiency, attention-based one provides minimal benefit even for syntactic tasks. |
| Approach: | a study predicts that knowledge distillation targeting attention should selectively accelerate syntax acquisition . a systolic analysis of student models compared to logit-based knowledge distillations . |
| Outcome: | a new study shows that knowledge distillation (KD) targeting attention accelerates syntax acquisition . the hypothesis is tested on syntactic benchmarks and perplexity. |