Challenge: Despite the promising evaluation results by knowledge distillation (KD) in natural language understanding (NLU) and sequence-to-sequence (seq2sequ) tasks, KD for causal language modeling (LM) remains a challenge.
Approach: They propose to use external logits to improve a student's kNN-LM by leveraging teacher's knowledge at test time.
Outcome: The proposed method improves a student's kNN-LM in multiple language modeling datasets and improves perplexity.

Similar Papers

Revisiting Knowledge Distillation for Autoregressive Language Models (2024.acl-long)

Copied to clipboard

Challenge: Autoregressive language models (LMs) are expensive and memory intensive, preventing the development of industrial applications.
Approach: They propose an adaptive teaching approach to improve the KD of autoregressive language models by distilling knowledge into a small student model.
Outcome: The proposed method can achieve consistent and significant performance gains across all model types and sizes.
Dual-Space Knowledge Distillation for Large Language Models (2024.emnlp-main)

Copied to clipboard

Challenge: Existing large language models (LLMs) have strong generalization abilities due to their huge model capacities.
Approach: They propose a dual-space knowledge distillation framework that unifies the output spaces of the two models for KD.
Outcome: The proposed framework outperforms existing white-box KD frameworks on task-agnostic instruction-following benchmarks and can automatically align representations of two models with different vocabularies.
ReAugKD: Retrieval-Augmented Knowledge Distillation For Pre-trained Language Models (2023.acl-short)

Copied to clipboard

Challenge: Knowledge distillation (KD) is an effective compression technique to derive a smaller student model from a larger teacher model by transferring the knowledge embedded in the teacher's network.
Approach: They propose a framework and loss function that preserves the semantic similarities of teacher and student training examples to enable the student to retrieve from the knowledge base effectively.
Outcome: The proposed framework preserves the semantic similarities of teacher and student training examples to achieve state-of-the-art performance on the GLUE benchmark.
Knowledge Distillation for Language Models (2025.naacl-tutorial)

Copied to clipboard

Challenge: Knowledge distillation (KD) aims to transfer knowledge from a teacher to a student . this tutorial will cover topics ranging from LLM sequence compression to LLM self-distillation .
Approach: They propose to introduce intermediate-layer matching and prediction matching . they will then present advanced techniques such as reinforcement learning-based KD and multi-teacher distillation .
Outcome: This tutorial aims to provide participants with a comprehensive understanding of the techniques and applications of knowledge distillation for language models.
On the Generalization vs Fidelity Paradox in Knowledge Distillation (2025.findings-acl)

Copied to clipboard

Challenge: Knowledge distillation (KD) is a key technique for compressing large language models into smaller ones while preserving performance.
Approach: They propose to use knowledge distillation to compress large language models into smaller ones while preserving performance.
Outcome: The proposed technique improves the performance of smaller models by 10% while providing only marginal benefits for larger models.
AD-KD: Attribution-Driven Knowledge Distillation for Language Model Compression (2023.acl-long)

Copied to clipboard

Challenge: Existing knowledge distillation methods focus on the transfer of model-specific knowledge but overlook data-specific information.
Approach: They propose an attribution-driven knowledge distillation approach which explores the token-level rationale behind the teacher model and transfers attribution knowledge to the student model.
Outcome: The proposed method outperforms state-of-the-art methods on the GLUE benchmark and shows that it is more efficient than existing methods.
Staged Knowledge Distillation Through Least-to-Most Prompting: Optimizing Teacher Guidance via Difficulty-Aware Training (2025.findings-emnlp)

Copied to clipboard

Challenge: Knowledge distillation (KD) enables the compression of large language models (LLMs) conventional methods suffer from training-inference mismatches and suboptimal performance due to expensive student-generated outputs.
Approach: They propose a method that combines a CL strategy and adaptive loss design to reduce training mismatches and suboptimal performance.
Outcome: L2M-KD outperforms existing white-box KD methods on instruction-following tasks . it outperformed existing methods, achieving superior student model performance with reduced overhead .
Why Skip If You Can Combine: A Simple Knowledge Distillation Technique for Intermediate Layers (2020.emnlp-main)

Copied to clipboard

Challenge: Existing knowledge distillation techniques are not suitable for deep learning tasks due to memory constraints.
Approach: They propose to combine knowledge from a large teacher network into a student network (S) they propose to use a combinatorial mechanism to inject layer-level supervision from T to S .
Outcome: The proposed model outperforms existing models in PortugueseEnglish, TurkishEnglish and EnglishGerman directions and students trained using it have 50% fewer parameters and can deliver comparable results to 12-layer teachers.
Pre-training Distillation for Large Language Models: A Design Space Exploration (2025.acl-long)

Copied to clipboard

Challenge: Knowledge distillation (KD) aims to transfer knowledge from a large teacher model to a smaller student model for model compression.
Approach: They extend knowledge distillation to the pre-training phase of large language models . they first conduct an experiment using a teacher LLM to distill a 1.9B student LLM .
Outcome: The proposed model can be used to distill a 1.9B student model using a teacher LLM.
Towards Zero-Shot Knowledge Distillation for Natural Language Processing (2021.emnlp-main)

Copied to clipboard

Challenge: Knowledge distillation (KD) is a common knowledge transfer algorithm used for model compression across a variety of deep learning based natural language processing (NLP) solutions.
Approach: They propose to use teacher training data for model compression . they investigate six tasks and find they can achieve between 75% and 92% of the teacher’s classification score while compressing the model 30 times.
Outcome: The proposed solution achieves between 75% and 92% of the teacher’s classification score while compressing the model 30 times.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations