Calibrated Progressive Distillation: Co-Designing Curriculum and Target Mixing for Knowledge Distillation of Large Language Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for knowledge distillation address the teacher–student capacity gap by mixing teacher and student distributions in the distillation target or using curriculum learning to sequence training from easy to hard examples. |
| Approach: | They propose a white-box KD framework that co-designs curriculum scheduling and target mixing through a unified difficulty-aware principle. |
| Outcome: | The proposed framework outperforms existing methods while reducing training runtime by over 10%. |
Similar Papers
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 . |
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. |
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. |
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. |
Distillation Traps and Guards: A Calibration Knob for LLM Distillability (2026.acl-long)
Copied to clipboard
| Challenge: | Knowledge distillation (KD) transfers capabilities from large language models (LLMs) to smaller students, yet it can fail unpredictably and also underpins model leakage risks. |
| Approach: | They propose a method that allows teachers to control their distillability via reinforcement fine-tuning (RFT) they propose to use tail noise, off-policy instability, and the teacher–student gap to improve KD. |
| Outcome: | The proposed method outperforms SFT and KD baselines and can be used to protect teachers and students from bottlenecks. |
Performance-Guided LLM Knowledge Distillation for Efficient Text Classification at Scale (2024.emnlp-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) face high computational demands at inference time due to high computational costs. |
| Approach: | They propose a cost-effective and high-throughput solution for large language models . PGKD distills the knowledge of LLMs into smaller, task-specific models based on teacher-student knowledge distillation . |
| Outcome: | PGKD outperforms BERT-based models and other knowledge distillation methods on multi-class classification datasets. |
A Systematic Study of Knowledge Distillation for Natural Language Generation with Pseudo-Target Training (2023.acl-long)
Copied to clipboard
| Challenge: | Modern Natural Language Generation models come with massive computational and storage requirements. |
| Approach: | They propose a method that applies word-level knowledge distillation to multiple PTs generated by both teacher and student. |
| Outcome: | The proposed techniques can be used to compress natural language models while preserving their performance. |
Beyond Logits: Aligning Feature Dynamics for Effective Knowledge Distillation (2025.acl-long)
Copied to clipboard
Guoqiang Gong, Jiaxing Wang, Jin Xu, Deping Xiang, Zicheng Zhang, Leqi Shen, Yifeng Zhang, JunhuaShu JunhuaShu, ZhaolongXing ZhaolongXing, Zhen Chen, Pengzhang Liu, Ke Zhang
| Challenge: | Knowledge distillation (KD) compresses large language models into lightweight versions called student models. |
| Approach: | They propose to align the entire feature dynamics between teacher and student models by using two additional loss terms to achieve this. |
| Outcome: | The proposed method matches the entire feature dynamics between teacher and student models rather than just the final states. |
Cost-effective Distillation of Large Language Models (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing knowledge distillation methods require pretraining of the teacher on task-specific datasets, which can be costly for large and unstable for small datasets. |
| Approach: | They propose an approach to improve knowledge distillation by a loss-agnostic approach to task and model architecture. |
| Outcome: | The proposed method achieves competitive results across a range of tasks, especially for tasks with smaller datasets. |
Co-training and Co-distillation for Quality Improvement and Compression of Language Models (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Knowledge Distillation (KD) compresses expensive pre-trained language models . however, most smaller models fail to surpass performance of larger model . |
| Approach: | They propose a framework that co-trains two models while mutually distilling knowledge to improve performance and inference speed together. |
| Outcome: | The proposed framework outperforms the original larger model by 1.66 on the GLUE benchmark. |