Related papers: Crosslingual On-Policy Self-Distillation for Multi…

Transferring the reasoning capability from stronger large language models (LLMs) to smaller ones has been quite appealing, as smaller LLMs are more flexible to deploy with less expense. Among the existing solutions, knowledge distillation…

Language models rely on semantic priors to perform in-context learning, which leads to poor performance on tasks involving inductive reasoning. Instruction-tuning methods based on imitation learning can superficially enhance the in-context…

The significant computational demands of large language models have increased interest in distilling reasoning abilities into smaller models via Chain-of-Thought (CoT) distillation. Current CoT distillation methods mainly focus on…

The deployment of large language models (LLMs) faces considerable challenges concerning resource constraints and inference efficiency. Recent research has increasingly focused on smaller, task-specific models enhanced by distilling…

On-policy distillation (OPD) has become a core technique in the post-training of large language models, yet its training dynamics remain poorly understood. This paper provides a systematic investigation of OPD dynamics and mechanisms. We…

While large language models (LLMs) have been pre-trained on multilingual corpora, their performance still lags behind in most languages compared to a few resource-rich languages. One common approach to mitigate this issue is to translate…

Large-scale self-supervised pre-trained speech encoders outperform conventional approaches in speech recognition and translation tasks. Due to the high cost of developing these large models, building new encoders for new tasks and deploying…

Large language models (LLMs) excel in complex reasoning tasks, and distilling their reasoning capabilities into smaller models has shown promise. However, we uncover an interesting phenomenon, which we term the Small Model Learnability Gap:…

On-policy distillation (OPD), which aligns the student with the teacher's logit distribution on student-generated trajectories, has demonstrated strong empirical gains in improving student performance and often outperforms off-policy…

The push to compress and impart the proficiency of Large Language Models (LLMs) into more deployable and efficient Small Language Models (SLMs) has benefited from improvements in knowledge distillation (KD) techniques. These techniques…

Recent studies have demonstrated that Large Language Models (LLMs) have strong mathematical reasoning abilities but rely on hundreds of billions of parameters. To tackle the challenge of poor reasoning in Small Language Models (SLMs),…

On-policy distillation (OPD) has become a popular training paradigm in the LLM community. This paradigm selects a larger model as the teacher to provide dense, fine-grained signals for each sampled trajectory, in contrast to reinforcement…

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…

Large Language Models (LLMs) have recently made significant advances in code generation through the 'Chain-of-Thought' prompting technique. This technique empowers the model to autonomously devise "solution plans" to tackle intricate…

While large language models (LLMs) excel in various natural language processing tasks, their huge size and the inaccessibility of parameters present challenges for practical deployment. Previous studies try to distill task-specific ability…

This paper addresses the challenges of high computational cost and slow inference in deploying large language models. It proposes a distillation strategy guided by multiple teacher models. The method constructs several teacher models and…

On-policy distillation (OPD), which supervises a student on its own sampled trajectories, has emerged as a data-efficient post-training method for improving reasoning while avoiding the reward dependence of reinforcement learning and the…

On-policy self-distillation (SD) improves LLM reasoning by using teacher-side privileged information (PI) to turn sparse verifier outcomes into dense token-level supervision. Existing methods usually assume trusted PI, such as reference…

On-policy distillation is an efficient alternative to reinforcement learning, offering dense token-level training signals. However, its reliance on a stronger external teacher has driven recent work on on-policy self-distillation, where the…

Chain-of-Thought (CoT) reasoning enhances Large Language Models (LLMs) by encouraging step-by-step reasoning in natural language. However, leveraging a latent continuous space for reasoning may offer benefits in terms of both efficiency and…