← Back to papers
2024 EMNLP EMNLP 2024

Intermediate Layer Distillation with the Reused Teacher Classifier: A Study on the Importance of the Classifier of Attention-based Models

Authors

Hang Zhang , Seyyed Hasan Mozafari , James J. Clark , Brett H. Meyer , Warren J. Gross
Download PDF

Related papers

EmbodiedBERT: Cognitively Informed Metaphor Detection Incorporating Sensorimotor Information 2024
Mitigating Matthew Effect: Multi-Hypergraph Boosted Multi-Interest Self-Supervised Learning for Conversational Recommendation 2024
Learning to Extract Structured Entities Using Language Models 2024
Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis 2024
CSSL: Contrastive Self-Supervised Learning for Dependency Parsing on Relatively Free Word Ordered and Morphologically Rich Low Resource Languages 2024