SWITCH: Studying with Teacher for Knowledge Distillation of Large Language Models

• URL: http://arxiv.org/abs/2410.19503v1
• Date: Fri, 25 Oct 2024 12:10:49 GMT
• Title: SWITCH: Studying with Teacher for Knowledge Distillation of Large Language Models
• Authors: Jahyun Koo, Yerin Hwang, Yongil Kim, Taegwan Kang, Hyunkyung Bae, Kyomin Jung,
• Abstract summary: SWITCH (Studying WIth TeaCHer for Knowledge Distillation) is a novel approach that strategically incorporates the teacher model during the student's sequence generation. We show that SWITCH surpasses traditional Knowledge Distillation methods, particularly excelling in the generation of long sequential data.
• Score: 16.060402139507644
• License:
• Abstract: Despite the success of Large Language Models (LLMs), they still face challenges related to high inference costs and memory requirements. To address these issues, Knowledge Distillation (KD) has emerged as a popular method for model compression, with student-generated outputs (SGOs) being particularly notable for reducing the mismatch between training and inference. However, SGOs often produce noisy and biased sequences, which can lead to misguidance from the teacher model, especially in long sequences. To mitigate these challenges, we propose SWITCH (Studying WIth TeaCHer for Knowledge Distillation), a novel approach that strategically incorporates the teacher model during the student's sequence generation. SWITCH identifies discrepancies between the token probabilities of the teacher and student models, allowing the teacher to intervene selectively, particularly in long sequences that are more prone to teacher misguidance. Extensive experimental results across three model families and five instruction-following datasets show that SWITCH surpasses traditional KD methods, particularly excelling in the generation of long sequential data.

Related papers

• CFTS-GAN: Continual Few-Shot Teacher Student for Generative Adversarial Networks [0.5024983453990064]
  Few-shot and continual learning face two well-known challenges in GANs: overfitting and catastrophic forgetting. This paper proposes a Continual Few-shot Teacher-Student technique for the generative adversarial network (CFTS-GAN) that considers both challenges together.
  arXiv  Detail & Related papers  (2024-10-17T20:49:08Z)
• Speculative Knowledge Distillation: Bridging the Teacher-Student Gap Through Interleaved Sampling [81.00825302340984]
  We introduce Speculative Knowledge Distillation (SKD) to generate high-quality training data on-the-fly. In SKD, the student proposes tokens, and the teacher replaces poorly ranked ones based on its own distribution. We evaluate SKD on various text generation tasks, including translation, summarization, math, and instruction following.
  arXiv  Detail & Related papers  (2024-10-15T06:51:25Z)
• Exploring and Enhancing the Transfer of Distribution in Knowledge Distillation for Autoregressive Language Models [62.5501109475725]
  Knowledge distillation (KD) is a technique that compresses large teacher models by training smaller student models to mimic them. This paper introduces Online Knowledge Distillation (OKD), where the teacher network integrates small online modules to concurrently train with the student model. OKD achieves or exceeds the performance of leading methods in various model architectures and sizes, reducing training time by up to fourfold.
  arXiv  Detail & Related papers  (2024-09-19T07:05:26Z)
• On the Resurgence of Recurrent Models for Long Sequences -- Survey and Research Opportunities in the Transformer Era [59.279784235147254]
  This survey is aimed at providing an overview of these trends framed under the unifying umbrella of Recurrence. It emphasizes novel research opportunities that become prominent when abandoning the idea of processing long sequences.
  arXiv  Detail & Related papers  (2024-02-12T23:55:55Z)
• Multistage Collaborative Knowledge Distillation from a Large Language Model for Semi-Supervised Sequence Generation [60.657065293413716]
  We study semi-supervised sequence generation tasks, where the few labeled examples are too scarce to finetune a model. We present the discovery that a student model distilled from a few-shot prompted large language models can commonly generalize better than its teacher.
  arXiv  Detail & Related papers  (2023-11-15T01:28:28Z)
• Comparative Knowledge Distillation [102.35425896967791]
  Traditional Knowledge Distillation (KD) assumes readily available access to teacher models for frequent inference. We propose Comparative Knowledge Distillation (CKD), which encourages student models to understand the nuanced differences in a teacher model's interpretations of samples. CKD consistently outperforms state of the art data augmentation and KD techniques.
  arXiv  Detail & Related papers  (2023-11-03T21:55:33Z)
• No Length Left Behind: Enhancing Knowledge Tracing for Modeling Sequences of Excessive or Insufficient Lengths [3.2687390531088414]
  Knowledge tracing aims to predict students' responses to practices based on their historical question-answering behaviors. As sequences get longer, computational costs will increase exponentially. We propose a model called Sequence-Flexible Knowledge Tracing (SFKT)
  arXiv  Detail & Related papers  (2023-08-07T11:30:58Z)
• On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes [44.97759066341107]
  Generalized Knowledge Distillation (GKD) trains the student on its self-generated output sequences by leveraging feedback from the teacher. We demonstrate the efficacy of GKD for distilling auto-regressive language models on summarization, translation, and arithmetic reasoning tasks.
  arXiv  Detail & Related papers  (2023-06-23T17:56:26Z)
• Learning to Teach with Student Feedback [67.41261090761834]
  Interactive Knowledge Distillation (IKD) allows the teacher to learn to teach from the feedback of the student. IKD trains the teacher model to generate specific soft target at each training step for a certain student. Joint optimization for both teacher and student is achieved by two iterative steps.
  arXiv  Detail & Related papers  (2021-09-10T03:01:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.