Challenge: Recent work has proposed methods for minimizing regressions caused by model updates . focus is on spoken language understanding models, which are unexplored .
Approach: They propose a focal distillation technique to reduce regressions in goal-oriented dialog systems . they also evaluate its effectiveness for key language understanding tasks .
Outcome: The proposed technique outperforms naive supervised training in mislabeled data and label expansion settings.

Similar Papers

Hard Gate Knowledge Distillation - Leverage Calibration for Robust and Reliable Language Model (2022.emnlp-main)

Copied to clipboard

Challenge: Existing knowledge distillation schemes focus on a teacher as a source of knowledge and a gauge to detect miscalibration of a student.
Approach: They propose a method that uses a teacher model as a source of knowledge and a model as an error detector to detect miscalibration of a student.
Outcome: The proposed scheme improves model generalization and significantly lowers calibration error.
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.
Distilling Instruction-following Abilities of Large Language Models with Task-aware Curriculum Planning (2024.findings-emnlp)

Copied to clipboard

Challenge: Instruction tuning aims to align large language models (LLMs) with open-domain instructions and human-preferred responses.
Approach: They propose a multi-round distillation framework that uses an oracle LLM to select instructions that are difficult for a student LLM.
Outcome: The proposed framework outperforms large language models and user-tuned models on several widely recognized benchmarks and multiple student LLMs.
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.
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.
POINTS-Reader: Distillation-Free Adaptation of Vision-Language Models for Document Conversion (2025.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to training document conversion models with manual annotation are costly and time-consuming, and training student models by distilling outputs from teacher models can significantly limit their performance in real-world applications.
Approach: They propose a fully automated framework for constructing high-quality document extraction datasets and models capable of handling diverse document formats and layouts.
Outcome: The proposed model outperforms existing models and improves on annotated documents.
Causal Distillation for Language Models (2022.naacl-main)

Copied to clipboard

Challenge: Distillation efforts have led to language models that are more compact and efficient without serious drops in performance.
Approach: They propose to augment distillation with a third objective that encourages the student model to imitate the causal dynamics of the teacher through a distillation interchange intervention training objective (DIITO).
Outcome: The proposed method lowers perplexity on the WikiText-103M corpus and improves on the GLUE benchmark, SQuAD, and CoNLL-2003.
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.
Prompt-Level Distillation: A Non-Parametric Alternative to Model Fine-Tuning for Efficient Reasoning (2026.acl-industry)

Copied to clipboard

Challenge: Advanced reasoning typically requires Chain-of-Thought prompting, which is accurate but incurs prohibitive latency and substantial test-time inference costs.
Approach: They propose to extract explicit reasoning patterns from a Teacher model and organize them into a structured list of expressive instructions for the Student model’s System Prompt.
Outcome: Evaluated using Gemma-3 4B, the proposed model improves Macro F1 scores on StereoSet and Contract-NLI while increasing LogiQA accuracy to 70%.
uDistil-Whisper: Label-Free Data Filtering for Knowledge Distillation in Low-Data Regimes (2025.naacl-long)

Copied to clipboard

Challenge: Recent work on distilling Whisper’s knowledge into small models using pseudo-labels shows promising performance while reducing the size by up to 50%.
Approach: They propose a framework that distills Whisper’s knowledge into small models using pseudo-labels and reduces the size by up to 50%.
Outcome: The proposed model outperforms the teacher model by 5-7 WER points and is 25-50% more efficient when scaling the data.

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