paper-with-me

홈 › Papers

YODA: Teacher-Student Progressive Learning for Language Models

2024-01-28 · Jianqiao Lu, Wanjun Zhong, YuFei Wang, Zhijiang Guo, Qi Zhu, Wenyong Huang, Yanlin Wang, Fei Mi, Baojun Wang, Yasheng Wang, Lifeng Shang, Xin Jiang, Qun Liu

Although large language models (LLMs) have demonstrated adeptness in a range of tasks, they still lag behind human learning efficiency. This disparity is often linked to the inherent human capacity to learn from basic examples, gradually generalize and handle more complex problems, and refine their skills with continuous feedback. Inspired by this, this paper introduces YODA, a novel teacher-student progressive learning framework that emulates the teacher-student education process to improve the efficacy of model fine-tuning. The framework operates on an interactive \textit{basic-generalized-harder} loop. The teacher agent provides tailored feedback on the student's answers, and systematically organizes the education process. This process unfolds by teaching the student basic examples, reinforcing understanding through generalized questions, and then enhancing learning by posing questions with progressively enhanced complexity. With the teacher's guidance, the student learns to iteratively refine its answer with feedback, and forms a robust and comprehensive understanding of the posed questions. The systematic procedural data, which reflects the progressive learning process of humans, is then utilized for model training. Taking math reasoning as a testbed, experiments show that training LLaMA2 with data from YODA improves SFT with significant performance gain (+17.01\% on GSM8K and +9.98\% on MATH). In addition, we find that training with curriculum learning further improves learning robustness.

📄 PDF Abstract BibTeX arXiv:2401.15670

Code (0)

등록된 구현이 없습니다.

Tasks

GSM8KMath

Methods 이 논문이 사용한 방법론

SFT Shrink and Fine-Tune, or SFT, is a type of distillation that avoids explicit distillation by copying parameters to a student student model and then fine-tuning.…

Similar Papers 제목 키워드 기반

PROD: Progressive Distillation for Dense Retrieval

2022-09-27 · Zhenghao Lin, Yeyun Gong, Xiao Liu, Hang Zhang 외

Knowledge distillation is an effective way to transfer knowledge from a strong teacher to an efficient student model. Ideally, we expect the better the teacher is, the better the student. However, this expectation does n…

Knowledge DistillationNatural QuestionsRetrieval

Masking Teacher and Reinforcing Student for Distilling Vision-Language Models

2025-12-23 · Byung-Kwan Lee, Yu-Chiang Frank Wang, Ryo Hachiuma arxiv

Large-scale vision-language models (VLMs) have recently achieved remarkable multimodal understanding, but their massive size makes them impractical for deployment on mobile or edge devices. This raises the need for compa…

Reinforcement LearningOffline RL

Progressive Distillation Based on Masked Generation Feature Method for Knowledge Graph Completion

2024-01-19 · Cunhang Fan, Yujie Chen, Jun Xue, Yonghui Kong 외

In recent years, knowledge graph completion (KGC) models based on pre-trained language model (PLM) have shown promising results. However, the large number of parameters and high computational cost of PLM models pose chal…

Knowledge Graph CompletionLanguage ModellingTransfer Learning

Progressive Teacher-Student Learning for Early Action Prediction

2019-06-01 · CVPR 2019 6 · Xionghui Wang, Jian-Fang Hu, Jian-Huang Lai, Jianguo Zhang 외

The goal of early action prediction is to recognize actions from partially observed videos with incomplete action executions, which is quite different from action recognition. Predicting early actions is very challenging…

Action RecognitionEarly Action PredictionPredictionTemporal Action Localization

Curriculum Learning-Guided Progressive Distillation in Large Language Models

2026-05-11 · Jincheng Cao, Fanzhi Zeng, Leqi Liu, Aryan Mokhtari arxiv

Knowledge distillation is a key technique for transferring the capabilities of large language models (LLMs) into smaller, more efficient student models. Existing distillation approaches often overlook two critical factor…

Knowledge Distillation