Challenge: Knowledge distillation optimises a smaller student model to behave similarly to a larger teacher model, retaining some performance benefits.
Approach: They propose to augment the distillation with generated unlabelled examples that match the target distribution and upsamples data points among the training set that are similar to the target.
Outcome: The proposed method outperforms previous robustness solutions on the task of natural language inference (NLI) it also improves performance on OOD domains even beyond the target domain.

Similar Papers

Enhancing Task-Specific Distillation in Small Data Regimes through Language Generation (2022.coling-1)

Copied to clipboard

Challenge: Large-scale pretrained language models have led to significant improvements in Natural Language Processing, but they come at the cost of high computational and storage requirements.
Approach: They propose to distill knowledge from larger models to smaller ones through pseudo-labels on task-specific datasets.
Outcome: The proposed approach improves on the SST-2, MRPC, YELP-2, and TREC-6 datasets.
Robustness Challenges in Model Distillation and Pruning for Natural Language Understanding (2023.eacl-main)

Copied to clipboard

Challenge: Recent studies have focused on compressing pre-trained language models (PLMs) however, few studies have examined the impact of compression on generalizability and robustness of compressed models for out-of-distribution data.
Approach: They propose to use knowledge distillation and pruning to reduce model generalization and generalization on out-of-distribution data.
Outcome: The proposed compression techniques overfit on shortcut samples and generalize poorly on hard ones.
Improving the OOD Performance of Closed-Source LLMs on NLI Through Strategic Data Selection (2026.findings-eacl)

Copied to clipboard

Challenge: Existing methods to improve robustness require changing the fine-tuning process or large-scale data augmentation, which are infeasible or cost prohibitive for closed-source models.
Approach: They propose to prioritize more complex examples or replace existing training examples with LLM-generated data to improve performance on OOD NLI datasets.
Outcome: The proposed methods improve performance on difficult OOD datasets while training with synthetic data leads to substantial improvements on easier OOD data.
FIRST: Teach A Reliable Large Language Model Through Efficient Trustworthy Distillation (2024.emnlp-main)

Copied to clipboard

Challenge: Experimental results show that a well-calibrated model is more reliable than a fine-tuned model due to “tuning-induced mis-calibration”.
Approach: They propose a method which utilizes a small portion of teacher’s knowledge to obtain a reliable language model in a cost-efficient way.
Outcome: The proposed method reduces the computational burden by utilizing teacher's knowledge to obtain a reliable language model in a cost-efficient way.
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.
On the Analysis and Distillation of Emergent Outlier Properties in Pre-trained Language Models (2025.naacl-long)

Copied to clipboard

Challenge: Existing studies show that a small subset of dimensions within language Transformers’ representation spaces emerge as "outliers" during pretraining.
Approach: They propose a method that prioritizes critical outlier dimensions in distillation using a weighted MSE loss.
Outcome: The proposed method outperforms state-of-the-art distillation methods and generalizes well across Encoder-only BERT, Decoder-only GPT-2, and Encodeer-Decoder T5 architectures.
DistillCSE: Distilled Contrastive Learning for Sentence Embeddings (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing approaches to sentence embeddings are based on contrastive learning (CL) .
Approach: They propose a framework which performs contrastive learning under the self-training paradigm with knowledge distillation and propose 'Group-P shuffling strategy' and averaging logits from multiple teacher components.
Outcome: The proposed framework outperforms many strong baseline methods and yields a new state-of-the-art performance.
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.
Accurate Knowledge Distillation via n-best Reranking (2024.naacl-long)

Copied to clipboard

Challenge: Existing studies using sequencelevel knowledge distillation (KD) have adopted this approach.
Approach: They propose to utilize n-best reranking to enhance Sequence-Level Knowledge Distillation by utilizing a diverse set of models with different inductive biases, objective functions or architectures to pick the highest-quality hypotheses as labels.
Outcome: The proposed approach is validated on the WMT’21 German English and Chinese english translation tasks.
Multi-Level Knowledge Distillation for Out-of-Distribution Detection in Text (2023.acl-long)

Copied to clipboard

Challenge: Self-supervised representation learning has proved to be a valuable component for out-of-distribution (OoD) detection with only the texts of in-difference (ID) examples.
Approach: They propose a method that integrates strengths and weaknesses of both methods . they use a fine-tuned model as the teacher to teach a randomly initialized student model .
Outcome: The proposed method outperforms human evaluators in the pair-expert task on the Human ChatGPT Comparison Corpus.

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