Challenge: Existing knowledge distillation models are not optimized for dealing with pairs (or tuples) of texts.
Approach: They propose a framework for distilling fast and accurate models on text pair tasks using a scalable end-to-end training strategy.
Outcome: Empirical studies on academic and real-world e-commerce benchmarks show the proposed framework can achieve speedups of over 350x and minimal quality drop relative to the cross-attention teacher BERT model.

Similar Papers

Generation-Distillation for Efficient Natural Language Understanding in Low-Data Settings (D19-61)

Copied to clipboard

Challenge: Recent research points to knowledge distillation as a potential solution for NLU tasks.
Approach: They propose a training approach that distills large finetuned LMs into a small network using unlabeled training examples.
Outcome: The proposed approach outperforms BERT training approaches while using 300 times fewer parameters.
Multi-stage Distillation Framework for Cross-Lingual Semantic Similarity Matching (2022.findings-naacl)

Copied to clipboard

Challenge: Existing studies have shown that cross-lingual knowledge distillation can improve the performance of pre-trained models for cross-linguistic similarity matching tasks.
Approach: They propose a multi-stage distillation framework for constructing a small-size but high-performance cross-lingual model using contrastive learning, bottleneck, and parameter recurrent strategies.
Outcome: The proposed model can compress the size of XLM-R and MiniLM by more than 50% while the performance is only reduced by about 1%.
Distillation of encoder-decoder transformers for sequence labelling (2023.findings-eacl)

Copied to clipboard

Challenge: despite the strong trend in NLP to explore the use of large language models, there is still limited work evaluating prompting and decoding mechanisms for SL tasks.
Approach: They propose a hallucination-free framework for sequence tagging that is especially suited for distillation.
Outcome: The proposed framework performs well across multiple sequence labelling datasets and in a few-shot learning scenario.
FASTMATCH: Accelerating the Inference of BERT-based Text Matching (2020.coling-main)

Copied to clipboard

Challenge: Recent pre-trained language models have shown state-of-the-art accuracies in text matching.
Approach: They propose a BERT-based text matching model where representations and interactions are decoupled . they propose generating final matching scores using a lightweight attention network .
Outcome: Experiments show that the proposed model can achieve up to 100X speed-up to BERT and RoBERTa while keeping more up to 98.7% of the performance.
XtremeDistil: Multi-stage Distillation for Massive Multilingual Models (2020.acl-main)

Copied to clipboard

Challenge: Existing work on pre-trained language models focuses on reducing the size of these models into shallow ones.
Approach: They propose a knowledge distillation technique that leverages teacher internal representations to reduce the size of pre-trained language models.
Outcome: The proposed method outperforms previous methods in multilingual Named Entity Recognition (NER) it reduces the size of teacher models by 35x while retaining 95% of its F1 score.
Sparse Distillation: Speeding Up Text Classification by Using Bigger Student Models (2022.naacl-main)

Copied to clipboard

Challenge: Existing methods to reduce inference cost by distilling transformer models into lightweight student models are limited for high-volume use cases.
Approach: They propose to distill state-of-the-art transformer models into lightweight student models to reduce computation cost at inference time.
Outcome: The proposed pipeline achieves up to 600x speed-up on GPUs and CPUs on six single-sentence text classification tasks and in domain generalization settings.
EMO: Embedding Model Distillation via Intra-Model Relation and Optimal Transport Alignments (2025.emnlp-main)

Copied to clipboard

Challenge: Existing methods for knowledge distillation focus on direct output alignment, neglecting this crucial structural information.
Approach: They propose a framework for knowledge distillation that maps tokens one-to-one and aligns attention matrix patterns using Centered Kernel Alignment.
Outcome: The proposed framework significantly outperforms existing CTKD baselines.
PairDistill: Pairwise Relevance Distillation for Dense Retrieval (2024.emnlp-main)

Copied to clipboard

Challenge: Recent advances in dense retrieval have demonstrated remarkable efficacy compared to traditional sparse retrieval methods.
Approach: They propose to use pairwise relevance distillation to leverage pairwise reranking to enrich the training of dense retrieval models.
Outcome: The proposed method outperforms existing methods and achieves state-of-the-art results on multiple benchmarks.
Patient Knowledge Distillation for BERT Model Compression (D19-1)

Copied to clipboard

Challenge: Pre-trained language models such as BERT have proven to be highly effective for natural language processing tasks, but the high demand for computing resources hinders their application in practice.
Approach: They propose to compress an original large model (teacher) into an equally-effective lightweight shallow network (student) Empirically, this translates into improved results on multiple NLP tasks with a significant gain in training efficiency, without sacrificing model accuracy.
Outcome: The proposed model reduces the computational cost of training models using the teacher model into a lightweight shallow network.
Flipping Knowledge Distillation: Leveraging Small Models’ Expertise to Enhance LLMs in Text Matching (2025.acl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) have demonstrated remarkable capabilities in acquiring diverse knowledge, making them highly effective across a wide range of tasks.
Approach: They propose a flipped knowledge distillation paradigm where LLM learns from SLM . they propose to reinterpret LLMs as encoder-decoder models using LoRA .
Outcome: The proposed model has been deployed in an online application environment and validated on financial and healthcare benchmarks and real-world applications.

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