English
Related papers

Related papers: Self-Filtered Distillation with LLMs-generated Tru…

200 papers

Large language models (LLMs) have demonstrated significant improvements in contextual understanding. However, their ability to attend to truly critical information during long-context reasoning and generation still falls behind the pace.…

Computation and Language · Computer Science 2025-10-27 Yiju Guo , Wenkai Yang , Zexu Sun , Ning Ding , Zhiyuan Liu , Yankai Lin

A recent trend in Natural Language Processing is the exponential growth in Language Model (LM) size, which prevents research groups without a necessary hardware infrastructure from participating in the development process. This study…

Computation and Language · Computer Science 2023-01-31 Jan Philip Wahle

Reinforcement learning (RL) has been widely used to train LLM agents for multi-turn interactive tasks, but its sample efficiency is severely limited by sparse rewards and long horizons. On-policy self-distillation (OPSD) alleviates this by…

Machine Learning · Computer Science 2026-04-14 Hao Wang , Guozhi Wang , Han Xiao , Yufeng Zhou , Yue Pan , Jichao Wang , Ke Xu , Yafei Wen , Xiaohu Ruan , Xiaoxin Chen , Honggang Qi

Score distillation sampling (SDS) demonstrates a powerful capability for text-conditioned 2D image and 3D object generation by distilling the knowledge from learned score functions. However, SDS often suffers from blurriness caused by noisy…

Computer Vision and Pattern Recognition · Computer Science 2025-03-26 SeonHwa Kim , Jiwon Kim , Soobin Park , Donghoon Ahn , Jiwon Kang , Seungryong Kim , Kyong Hwan Jin , Eunju Cha

Large reasoning models such as DeepSeek-R1 and their distilled variants achieve strong performance on complex reasoning tasks. Yet, distilling these models often demands large-scale data for supervised fine-tuning (SFT), motivating the…

Computation and Language · Computer Science 2026-01-16 Lechen Zhang , Yunxiang Zhang , Wei Hu , Lu Wang

Large Language Models (LLMs) have demonstrated exceptional proficiency in mathematical reasoning tasks due to their extensive parameter counts and training on vast datasets. Despite these capabilities, deploying LLMs is hindered by their…

Computation and Language · Computer Science 2024-10-11 Xunyu Zhu , Jian Li , Can Ma , Weiping Wang

Large Language models (LLMs) are achieving state-of-the-art performance in many different downstream tasks. However, the increasing urgency of data privacy puts pressure on practitioners to train LLMs with Differential Privacy (DP) on…

Machine Learning · Computer Science 2025-12-17 James Flemings , Murali Annavaram

Distilling multi-step reasoning abilities from large language models (LLMs) into compact student models remains challenging due to noisy rationales, hallucinated supervision, and static teacher-student interactions. Existing reasoning…

Computation and Language · Computer Science 2026-05-14 Kasidit Sermsri , Teerapong Panboonyuen

Large language models (LLMs) are challenging to deploy for domain-specific tasks due to their massive scale. While distilling a fine-tuned LLM into a smaller student model is a promising alternative, the capacity gap between teacher and…

Artificial Intelligence · Computer Science 2026-01-16 Cheng Feng , Chaoliang Zhong , Jun Sun , Yusuke Oishi

Discrete diffusion models excel at visual synthesis but rely on slow, iterative decoding. Existing single-step distillation methods attempt to bypass this bottleneck, either by training auxiliary score networks that effectively double…

Computer Vision and Pattern Recognition · Computer Science 2026-05-21 Chaoyang Wang , Yunhai Tong

In real-world applications, Federated Learning (FL) meets two challenges: (1) scalability, especially when applied to massive IoT networks; and (2) how to be robust against an environment with heterogeneous data. Realizing the first…

Machine Learning · Computer Science 2022-10-03 Minh-Duong Nguyen , Quoc-Viet Pham , Dinh Thai Hoang , Long Tran-Thanh , Diep N. Nguyen , Won-Joo Hwang

On-policy self-distillation trains a reasoning model on its own rollouts while a teacher, often the same model conditioned on privileged context, provides dense token-level supervision. Existing objectives typically weight the teacher's…

Artificial Intelligence · Computer Science 2026-05-14 Junlong Ke , Zichen Wen , Weijia Li , Conghui He , Linfeng Zhang

Aligning small language models (SLMs) with human values typically involves distilling preference knowledge from large language models (LLMs). However, existing distillation methods model preference knowledge in teacher LLMs by comparing…

Computation and Language · Computer Science 2025-02-21 Yanggan Gu , Junzhuo Li , Sirui Huang , Xin Zou , Zhenghua Li , Xuming Hu

Large language models (LLMs) have showcased remarkable capabilities in complex reasoning through chain of thought (CoT) prompting. Recently, there has been a growing interest in transferring these reasoning abilities from LLMs to smaller…

Computation and Language · Computer Science 2023-12-21 Hongzhan Chen , Siyue Wu , Xiaojun Quan , Rui Wang , Ming Yan , Ji Zhang

While reasoning capabilities typically emerge in large language models (LLMs) with tens of billions of parameters, recent research focuses on improving smaller open-source models through knowledge distillation (KD) from commercial LLMs.…

Computation and Language · Computer Science 2025-05-21 Zhuochun Li , Yuelyu Ji , Rui Meng , Daqing He

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

Reasoning-oriented language models achieve strong performance by generating long chain-of-thought traces at inference time. However, this capability comes with substantial and often excessive computational cost, which can materialize in…

Machine Learning · Computer Science 2026-03-17 Gianluigi Silvestri , Edoardo Cetin

Data-free knowledge distillation (DFKD) conducts knowledge distillation via eliminating the dependence of original training data, and has recently achieved impressive results in accelerating pre-trained language models. At the heart of DFKD…

Computation and Language · Computer Science 2022-05-17 Xinyin Ma , Xinchao Wang , Gongfan Fang , Yongliang Shen , Weiming Lu

Knowledge distillation is a model compression technique in which a compact "student" network is trained to replicate the predictive behavior of a larger "teacher" network. In logit-based knowledge distillation, it has become the de facto…

Machine Learning · Computer Science 2026-05-12 Ejafa Bassam , Dawei Zhu , Kaigui Bian

Classifying patents by their relevance to the UN Sustainable Development Goals (SDGs) is crucial for tracking how innovation addresses global challenges. However, the absence of a large, labeled dataset limits the use of supervised…

Computation and Language · Computer Science 2025-09-12 Grazia Sveva Ascione , Nicolò Tamagnone