AdapterDistillation: Non-Destructive Task Composition with Knowledge Distillation (2023.emnlp-industry)
Copied to clipboard
| Challenge: | Recent work on learning from multiple tasks has shown that adding an extra fusion layer to implement knowledge composition is non-scalable for some applications. |
| Approach: | They propose a two-stage knowledge distillation algorithm to extract task specific knowledge by using local data to train a student adapter. |
| Outcome: | Experiments on frequently asked question retrieval in task-oriented dialog systems validate the efficiency of AdapterDistillation. |
Similar Papers
AdapterFusion: Non-Destructive Task Composition for Transfer Learning (2021.eacl-main)
Copied to clipboard
| Challenge: | Existing methods for incorporating knowledge from multiple tasks suffer from catastrophic forgetting and difficulties in dataset balancing. |
| Approach: | They propose an algorithm that extracts and combine adapters in a knowledge composition step. |
| Outcome: | The proposed class outperforms traditional methods such as full fine-tuning and multi-task learning on 16 diverse NLU tasks. |
Efficient Transformer Knowledge Distillation: A Performance Review (2023.emnlp-industry)
Copied to clipboard
| Challenge: | Pretrained transformer language models have been gaining popularity in the field of natural language processing . however, there is no study into the intersection of these two fields . |
| Approach: | They propose a method to extract knowledge from transformers to produce high-performing efficient attention models with low costs. |
| Outcome: | The proposed model compression method preserves up to 98.6% of original model performance across short-context tasks and up to 95.8% on long-concept Named Entity Recognition tasks while decreasing inference times by up to 57%. |
Eliciting and Understanding Cross-task Skills with Task-level Mixture-of-Experts (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Pre-trained transformer models are capable of multitasking on diverse NLP tasks, but little is known about how multitaskability and cross-task generalization is achieved. |
| Approach: | They propose to use a transformer-based mixture-of-expert model with a router component to choose among experts dynamically and flexibly. |
| Outcome: | The proposed models improve the average performance gain (ARG) metric by 2.6% when adapting to unseen tasks, and by 5.6% in zero-shot generalization settings. |
StepER: Step-wise Knowledge Distillation for Enhancing Reasoning Ability in Multi-Step Retrieval-Augmented Language Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing knowledge distillation methods overlook the need for different reasoning abilities at different steps, hindering transfer in multi-step retrieval-augmented frameworks. |
| Approach: | They propose a method that uses step-wise supervision to align with evolving information and reasoning demands across stages. |
| Outcome: | The proposed method outperforms previous methods on multi-hop QA benchmarks with an 8B model achieving performance comparable to a 70B teacher model. |
Iterative Structured Knowledge Distillation: Optimizing Language Models Through Layer-by-Layer Distillation (2025.coling-main)
Copied to clipboard
| Challenge: | Structured pruning and knowledge distillation are often not efficient and require a fixed architecture, limiting flexibility. |
| Approach: | They propose a method which integrates knowledge distillation and structured pruning by replacing transformer blocks with smaller, efficient versions during training. |
| Outcome: | The proposed method outperforms L1 pruning and maintains four-fifths of performance on language modeling and commonsense reasoning tasks. |
K-Adapter: Infusing Knowledge into Pre-Trained Models with Adapters (2021.findings-acl)
Copied to clipboard
Ruize Wang, Duyu Tang, Nan Duan, Zhongyu Wei, Xuanjing Huang, Jianshu Ji, Guihong Cao, Daxin Jiang, Ming Zhou
| Challenge: | Existing methods for injecting knowledge into pre-trained models are inconsistent and can flush out knowledge when multiple kinds of knowledge are injected. |
| Approach: | They propose a framework that retains the original parameters of pre-trained models fixed and supports the development of versatile knowledge-infused models. |
| Outcome: | The proposed framework retains the original parameters of the pre-trained model fixed and supports the development of versatile knowledge-infused models. |
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. |
Distilling Multilingual Transformers into CNNs for Scalable Intent Classification (2022.emnlp-industry)
Copied to clipboard
| Challenge: | Existing multilingual models for voice assistants are limited by their prohibitive inference time and limited performance. |
| Approach: | They propose to distill and deploy multilingual Transformer models for voice assistants using a teacher-student framework that uses teacher-trained models to supervise student model training. |
| Outcome: | The proposed model outperforms a teacher model trained on unlabelled data and achieves equivalent performance. |
A Comparative Analysis of Task-Agnostic Distillation Methods for Compressing Transformer Language Models (2023.emnlp-industry)
Copied to clipboard
| Challenge: | Large language models are often inefficient for real-world deployment due to expensive inference costs. |
| Approach: | They propose to use knowledge distillation to transfer the knowledge of the original model to a smaller, more efficient student model. |
| Outcome: | The proposed method is the best for multi-lingual and multilingual student architectures. |
BAM! Born-Again Multi-Task Networks for Natural Language Understanding (P19-1)
Copied to clipboard
| Challenge: | Existing methods to train multi-task neural networks outperform or even match their single-task counterparts are difficult to implement. |
| Approach: | They propose a method that uses knowledge distillation to train multi-task neural networks that outperform or even match their single-task counterparts. |
| Outcome: | The proposed method outperforms or matches single-task neural networks on the GLUE benchmark. |