English
Related papers

Related papers: OPSDL: On-Policy Self-Distillation for Long-Contex…

200 papers

The rapid advancement of large language models (LLMs) has significantly advanced the capabilities of artificial intelligence across various domains. However, their massive scale and high computational costs render them unsuitable for direct…

Computer Vision and Pattern Recognition · Computer Science 2025-10-01 Miao Rang , Zhenni Bi , Hang Zhou , Hanting Chen , An Xiao , Tianyu Guo , Kai Han , Xinghao Chen , Yunhe Wang

On-policy distillation (OPD) trains a student model on its own rollouts using dense feedback from a stronger teacher. Prior literature suggests that, provided teacher feedback is available, supervising the full sequence of response tokens…

Computation and Language · Computer Science 2026-05-26 Kaiyuan Liu , Ziyuan Zhuang , Yang Bai , Bing Wang , Rongxiang Weng , Jieping Ye

Training-time privileged information (PI) can enable language models to succeed on tasks they would otherwise fail, making it a powerful tool for reinforcement learning in hard, long-horizon settings. However, transferring capabilities…

Machine Learning · Computer Science 2026-02-17 Emiliano Penaloza , Dheeraj Vattikonda , Nicolas Gontier , Alexandre Lacoste , Laurent Charlin , Massimo Caccia

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

On-policy self-distillation (OPSD) trains a student on its own rollouts using a privileged teacher, but its standard objective weights all generated tokens equally, implicitly treating the privileged teacher target as equally reliable at…

Machine Learning · Computer Science 2026-05-22 Xiaogeng Liu , Xinyan Wang , Yingzi Ma , Yechao Zhang , Chaowei Xiao

Large language models (LLMs) increasingly operate in settings that require reliable long-context understanding, such as retrieval-augmented generation and multi-document reasoning. A common strategy is to fine-tune pretrained short-context…

Computation and Language · Computer Science 2026-04-17 Zichong Li , Chen Liang , Liliang Ren , Tuo Zhao , Yelong Shen , Weizhu Chen

On-policy distillation (OPD), which samples trajectories from the student model and supervises them with a teacher at the token level, avoids relying solely on verifiable terminal rewards and can yield better generalization than off-policy…

Large language models (LLMs) have gained extended context windows through scaling positional encodings and lightweight continual pre-training. However, this often leads to degraded performance on short-text tasks, while the reasons for this…

Computation and Language · Computer Science 2025-05-29 Zican Dong , Junyi Li , Jinhao Jiang , Mingyu Xu , Wayne Xin Zhao , Bingning Wang , Weipeng Chen

On-policy distillation (OPD) is an increasingly important paradigm for post-training language models. However, we identify a pervasive Scaling Law of Miscalibration: while OPD effectively improves task accuracy, it systematically traps…

Machine Learning · Computer Science 2026-04-21 Jiaxin Zhang , Xiangyu Peng , Qinglin Chen , Qinyuan Ye , Caiming Xiong , Chien-Sheng Wu

Large language models (LLMs) have achieved substantial progress in processing long contexts but still struggle with long-context reasoning. Existing approaches typically involve fine-tuning LLMs with synthetic data, which depends on…

Computation and Language · Computer Science 2024-11-14 Siheng Li , Cheng Yang , Zesen Cheng , Lemao Liu , Mo Yu , Yujiu Yang , Wai Lam

Language models significantly benefit from context tokens, such as prompts or scratchpads. They perform better when prompted with informative instructions, and they acquire new reasoning capabilities by generating a scratch-pad before…

Computation and Language · Computer Science 2022-10-03 Charlie Snell , Dan Klein , Ruiqi Zhong

On-policy self-distillation has become a strong recipe for LLM reasoning, where a privileged teacher supervises the student's own rollouts while conditioning on the reference solution. A design choice shared by nearly all such methods,…

Artificial Intelligence · Computer Science 2026-05-28 Zihao Han , Tiangang Zhang , Huaibin Wang , Yilun Sun

Diffusion Language Models (DLMs) have recently achieved strong results in text generation. However, their multi-step sampling leads to slow inference, limiting practical use. To address this, we extend Inverse Distillation, a technique…

Machine Learning · Computer Science 2026-02-24 David Li , Nikita Gushchin , Dmitry Abulkhanov , Eric Moulines , Ivan Oseledets , Maxim Panov , Alexander Korotin

We introduce a novel approach to large language model (LLM) distillation by formulating it as a constrained reinforcement learning problem. While recent work has begun exploring the integration of task-specific rewards into distillation…

Machine Learning · Computer Science 2025-09-30 Matthieu Zimmer , Xiaotong Ji , Tu Nguyen , Haitham Bou Ammar

Self-distillation (SD) offers a promising path for adapting large language models (LLMs) without relying on stronger external teachers. However, SD in autoregressive LLMs remains challenging because self-generated trajectories are…

Computation and Language · Computer Science 2026-05-22 Yiqiao Jin , Yiyang Wang , Lucheng Fu , Yijia Xiao , Yinyi Luo , Haoxin Liu , B. Aditya Prakash , Josiah Hester , Jindong Wang , Srijan Kumar

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

Distilling large language models (LLMs) typically involves transferring the teacher model's responses through supervised fine-tuning (SFT). However, this approach neglects the potential to distill both data (output content) and reward…

Computation and Language · Computer Science 2025-02-28 Yudi Zhang , Lu Wang , Meng Fang , Yali Du , Chenghua Huang , Jun Wang , Qingwei Lin , Mykola Pechenizkiy , Dongmei Zhang , Saravan Rajmohan , Qi Zhang

On-policy distillation (OPD) trains student models under their own induced distribution while leveraging supervision from stronger teachers. We identify a failure mode of OPD: as training progresses, on-policy rollouts can undergo abrupt…

Computation and Language · Computer Science 2026-04-10 Feng Luo , Yu-Neng Chuang , Guanchu Wang , Zicheng Xu , Xiaotian Han , Tianyi Zhang , Vladimir Braverman

Large language models (LLMs) have achieved remarkable advancements in natural language processing. However, the massive scale and computational demands of these models present formidable challenges when considering their practical…

Computation and Language · Computer Science 2024-04-09 Weize Liu , Guocong Li , Kai Zhang , Bang Du , Qiyuan Chen , Xuming Hu , Hongxia Xu , Jintai Chen , Jian Wu

Long context reasoning in large language models (LLMs) has demonstrated enhancement of their cognitive capabilities via chain-of-thought (CoT) inference. Training such models is usually done via reinforcement learning with verifiable…

Computation and Language · Computer Science 2025-12-05 Purbesh Mitra , Sennur Ulukus