English
Related papers

Related papers: ORPO-Distill: Mixed-Policy Preference Optimization…

200 papers

Distilling reasoning traces from strong large language models into smaller ones is a promising route to improve intelligence in resource-constrained settings. Existing approaches face a fundamental trade-off: offline distillation from…

Computation and Language · Computer Science 2026-05-15 Yumeng Zhang , Zhengbang Yang , Yevin Nikhel Goonatilake , Zhuangdi Zhu

Knowledge distillation (KD) is a technique that compresses large teacher models by training smaller student models to mimic them. The success of KD in auto-regressive language models mainly relies on Reverse KL for mode-seeking and…

Computation and Language · Computer Science 2024-09-23 Jun Rao , Xuebo Liu , Zepeng Lin , Liang Ding , Jing Li , Dacheng Tao , Min Zhang

Multi-task learning (MTL) has been widely used in recommender systems, wherein predicting each type of user feedback on items (e.g, click, purchase) are treated as individual tasks and jointly trained with a unified model. Our key…

Information Retrieval · Computer Science 2022-03-29 Chenxiao Yang , Junwei Pan , Xiaofeng Gao , Tingyu Jiang , Dapeng Liu , Guihai Chen

Knowledge distillation has proven to be an effective technique in improving the performance a student model using predictions from a teacher model. However, recent work has shown that gains in average efficiency are not uniform across…

Machine Learning · Computer Science 2022-06-15 Serena Wang , Harikrishna Narasimhan , Yichen Zhou , Sara Hooker , Michal Lukasik , Aditya Krishna Menon

Preference optimization techniques, such as Direct Preference Optimization (DPO), are frequently employed to enhance the reasoning capabilities of large language models (LLMs) in domains like mathematical reasoning and coding, typically…

Computation and Language · Computer Science 2025-02-17 Fangkai Jiao , Geyang Guo , Xingxing Zhang , Nancy F. Chen , Shafiq Joty , Furu Wei

On-policy distillation (OPD) trains a student on its own trajectories under token-level teacher supervision, but existing methods are capped by a single-teacher capability ceiling: when the teacher errs, the student inherits the error. OPD…

Computation and Language · Computer Science 2026-05-05 Jianze Wang , Ying Liu , Jinlong Chen , Xuchun Hu , Qilong Zhang , Yu Cao , Jun Wang , Hua Yang , Yong Xie , Qianglong Chen

News recommendation plays a critical role in online news platforms by helping users discover relevant content. Cross-domain news recommendation further requires inferring user's underlying information needs from heterogeneous signals that…

Computation and Language · Computer Science 2026-02-17 Mengdan Zhu , Yufan Zhao , Tao Di , Yulan Yan , Liang Zhao

Current long chain-of-thought (long-CoT) models excel at mathematical reasoning but rely on slow and error-prone natural language traces. Tool-augmented agents address arithmetic via code execution, but often falter on complex logical…

Computation and Language · Computer Science 2025-09-03 Weihua Du , Pranjal Aggarwal , Sean Welleck , Yiming Yang

We present a novel framework of knowledge distillation that is capable of learning powerful and efficient student models from ensemble teacher networks. Our approach addresses the inherent model capacity issue between teacher and student…

Machine Learning · Computer Science 2019-12-02 Minsoo Kang , Jonghwan Mun , Bohyung Han

Distillation transfers knowledge from a large model trained on broad data to a smaller, more efficient model suitable for deployment. In structured prediction settings, prior knowledge about the task can guide the choice of a target…

Machine Learning · Computer Science 2026-05-20 Thien Le , Melanie Weber

In the realm of large language model (LLM), as the size of large models increases, it also brings higher training costs. There is a urgent need to minimize the data size in LLM training. Compared with data selection method, the data…

Computation and Language · Computer Science 2025-04-25 Rong Yao , Hailin Hu , Yifei Fu , Hanting Chen , Wenyi Fang , Fanyi Du , Kai Han , Yunhe Wang

On-policy self-distillation, where a student is pulled toward a copy of itself conditioned on privileged context (e.g., a verified solution or feedback), offers a promising direction for advancing reasoning capability without a stronger…

Machine Learning · Computer Science 2026-05-13 Guobin Shen , Xiang Cheng , Chenxiao Zhao , Lei Huang , Jindong Li , Dongcheng Zhao , Xing Yu

Moving beyond simple scalar rewards toward richer world feedback is a natural path to more scalable RL post-training. On-policy self-distillation (OPSD) is a promising recent approach that uses arbitrary feedback as learning signal, yet its…

Machine Learning · Computer Science 2026-05-29 Tommy He , Jerome Sieber , Matteo Saponati

Black-box knowledge distillation for large language models presents a strict trade-off. Simple off-policy methods (e.g., sequence-level knowledge distillation) struggle to correct the student's inherent errors. Fully on-policy methods…

Machine Learning · Computer Science 2026-04-24 Xiwen Chen , Jingjing Wang , Wenhui Zhu , Peijie Qiu , Xuanzhao Dong , Hejian Sang , Zhipeng Wang , Alborz Geramifard , Feng Luo

On-Policy Distillation (OPD) has emerged as a dominant post-training paradigm for large language models, especially for reasoning domains. However, OPD remains unstable in practice due to the high gradient variance of its single-sample…

Machine Learning · Computer Science 2026-05-11 Minjae Oh , Sangjun Song , Gyubin Choi , Yunho Choi , Yohan Jo

Direct Preference Optimization (DPO) is an effective framework for aligning large language models with human preferences, but it struggles with complex reasoning tasks. DPO optimizes for the likelihood of generating preferred over…

Artificial Intelligence · Computer Science 2026-04-23 Darsh Kachroo , Adriana Caraeni , Arjun Prasaath Anbazhagan , Brennan Lagasse , Kevin Zhu

Knowledge Distillation (KD) is a promising technique for reducing the high computational demand of large language models (LLMs). However, previous KD methods are primarily applied to white-box classification models or training small models…

Computation and Language · Computer Science 2026-02-03 Yuxian Gu , Li Dong , Furu Wei , Minlie Huang

Learning from human preference data has emerged as the dominant paradigm for fine-tuning large language models (LLMs). The two most common families of techniques -- online reinforcement learning (RL) such as Proximal Policy Optimization…

Machine Learning · Computer Science 2024-07-17 Yuda Song , Gokul Swamy , Aarti Singh , J. Andrew Bagnell , Wen Sun

Distillation-based learning boosts the performance of the miniaturized neural network based on the hypothesis that the representation of a teacher model can be used as structured and relatively weak supervision, and thus would be easily…

Machine Learning · Computer Science 2019-04-22 Xiao Jin , Baoyun Peng , Yichao Wu , Yu Liu , Jiaheng Liu , Ding Liang , Junjie Yan , Xiaolin Hu

Scaling on-policy distillation (OPD) for large language models (LLMs) confronts a fundamental tension: asynchronous execution is necessary for system efficiency, but structurally deviates from the ideal on-policy objective. To address this…

Machine Learning · Computer Science 2026-05-19 Xianwei Chen , Shimin Zhang , Jibin Wu