English
Related papers

Related papers: Distilling the Essence: Efficient Reasoning Distil…

200 papers

Chain-of-thought reasoning, while powerful, can produce unnecessarily verbose output for simpler problems. We present a framework for difficulty-aware reasoning that teaches models to dynamically adjust reasoning depth based on problem…

Computation and Language · Computer Science 2025-09-08 Abdul Waheed , Chancharik Mitra , Laurie Z. Wang , Deva Ramanan , Bhiksha Raj

The scalability of large language models for long-context reasoning is severely constrained by the linear growth of their Transformer key-value cache, which incurs significant memory and computational costs. We posit that as a model…

Computation and Language · Computer Science 2025-12-30 Giovanni Monea , Yair Feldman , Shankar Padmanabhan , Kianté Brantley , Yoav Artzi

Chain-of-thought (CoT) prompting enhances reasoning in large language models (LLMs) but often leads to verbose and redundant outputs, thus increasing inference cost. We hypothesize that many reasoning steps are unnecessary for producing…

Computation and Language · Computer Science 2025-09-30 Xin Liu , Lu Wang

Distilling reasoning paths from teacher to student models via supervised fine-tuning (SFT) provides a shortcut for improving the reasoning ability of smaller Large Language Models (LLMs). However, the reasoning paths generated by teacher…

Computation and Language · Computer Science 2026-02-03 Shicheng Xu , Liang Pang , Yunchang Zhu , Jia Gu , Zihao Wei , Jingcheng Deng , Feiyang Pan , Huawei Shen , Xueqi Cheng

Large language models (LLMs) excel at complex reasoning tasks but remain computationally expensive, limiting their practical deployment. To address this, recent works have focused on distilling reasoning capabilities into smaller language…

Computation and Language · Computer Science 2025-11-06 Minki Kang , Jongwon Jeong , Seanie Lee , Jaewoong Cho , Sung Ju Hwang

Distilling the thinking traces of a Large Language Model (LLM) with reasoning capabilities into a smaller model has been proven effective. Yet, there is a scarcity of work done on how model performances scale with the quantity of…

Computation and Language · Computer Science 2025-10-08 Muyu He , Muhammad Ali Shafique , Anand Kumar , Tsach Mackey , Nazneen Rajani

Knowledge Distillation (KD) is one proposed solution to large model sizes and slow inference speed in semantic segmentation. In our research we identify 25 proposed distillation loss terms from 14 publications in the last 4 years.…

Computer Vision and Pattern Recognition · Computer Science 2023-09-08 Onno Niemann , Christopher Vox , Thorben Werner

Knowledge Distillation (KD), which transfers the knowledge of a well-trained large model (teacher) to a small model (student), has become an important area of research for practical deployment of recommender systems. Recently, Relaxed…

Information Retrieval · Computer Science 2024-05-16 Youngjune Lee , Kee-Eung Kim

The prevailing approach to distilling reasoning from Large Language Models (LLMs)-behavioral cloning from textual rationales-is fundamentally limited. It teaches Small Language Models (SLMs) to mimic surface-level patterns rather than the…

Artificial Intelligence · Computer Science 2025-10-02 Xiangyu Wen , Junhua Huang , Zeju Li , Min Li , Jianyuan Zhong , Zhijian Xu , Mingxuan Yuan , Yongxiang Huang , Qiang Xu

Reviewing plays an important role when learning knowledge. The knowledge acquisition at a certain time point may be strongly inspired with the help of previous experience. Thus the knowledge growing procedure should show strong relationship…

Computer Vision and Pattern Recognition · Computer Science 2025-05-13 Dongwei Wang , Zhi Han , Yanmei Wang , Xiai Chen , Baichen Liu , Yandong Tang

Knowledge distillation (KD) is widely used for training a compact model with the supervision of another large model, which could effectively improve the performance. Previous methods mainly focus on two aspects: 1) training the student to…

Computer Vision and Pattern Recognition · Computer Science 2020-07-27 Tiancheng Wen , Shenqi Lai , Xueming Qian

With the increasing size of datasets used for training neural networks, data pruning becomes an attractive field of research. However, most current data pruning algorithms are limited in their ability to preserve accuracy compared to models…

Computer Vision and Pattern Recognition · Computer Science 2024-08-15 Emanuel Ben-Baruch , Adam Botach , Igor Kviatkovsky , Manoj Aggarwal , Gérard Medioni

Efficient reasoning distillation for long chain-of-thought (CoT) models is increasingly constrained by the assumption of a single oracle teacher, despite the practical availability of multiple candidate teachers and growing CoT corpora. We…

Machine Learning · Computer Science 2025-10-17 Zhanming Shen , Zeyu Qin , Zenan Huang , Hao Chen , Jiaqi Hu , Yihong Zhuang , Guoshan Lu , Gang Chen , Junbo Zhao

Reasoning LLMs often spend substantial tokens on long intermediate reasoning traces (e.g., chain-of-thought) when solving new problems. We propose to summarize and store reusable reasoning skills distilled from extensive deliberation and…

Artificial Intelligence · Computer Science 2026-04-28 Guangxiang Zhao , Qilong Shi , Xusen Xiao , Xiangzheng Zhang , Tong Yang , Lin Sun

Knowledge distillation is normally used to compress a big network, or teacher, onto a smaller one, the student, by training it to match its outputs. Recently, some works have shown that robustness against adversarial attacks can also be…

Machine Learning · Computer Science 2022-03-15 Javier Maroto , Guillermo Ortiz-Jiménez , Pascal Frossard

Pre-trained language models (PLMs) have emerged as powerful tools for code understanding. However, deploying these PLMs in large-scale applications faces practical challenges due to their computational intensity and inference latency.…

Software Engineering · Computer Science 2025-08-22 Ruiqi Wang , Zezhou Yang , Cuiyun Gao , Xin Xia , Qing Liao

In this paper, we investigate how model distillation impacts the development of reasoning features in large language models (LLMs). To explore this, we train a crosscoder on Qwen-series models and their fine-tuned variants. Our results…

Machine Learning · Computer Science 2025-03-26 David D. Baek , Max Tegmark

Knowledge distillation can be a cost-effective technique to distill knowledge in Large Language Models, if the teacher output logits can be pre-computed and cached. However, successfully applying this to pre-training remains largely…

Machine Learning · Computer Science 2025-07-25 Anshumann , Mohd Abbas Zaidi , Akhil Kedia , Jinwoo Ahn , Taehwak Kwon , Kangwook Lee , Haejun Lee , Joohyung Lee

Knowledge distillation (KD) is a common approach to compress a teacher model to reduce its inference cost and memory footprint, by training a smaller student model. However, in the context of autoregressive language models (LMs), we…

Computation and Language · Computer Science 2024-06-18 Qihuang Zhong , Liang Ding , Li Shen , Juhua Liu , Bo Du , Dacheng Tao

Knowledge distillation (KD) is a core component in the training and deployment of modern generative models, particularly large language models (LLMs). While its empirical benefits are well documented -- enabling smaller student models to…

Machine Learning · Computer Science 2026-01-16 Sungmin Cha , Kyunghyun Cho