# Less is More: Task-aware Layer-wise Distillation for Language Model Compression

arXiv: https://arxiv.org/abs/2210.01351 · HTML: https://mlsanity.com/paper/2210.01351/

## Key facts

- Cited by 93 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 57 references that are in the map.
- First posted on arXiv 4 Oct 2022.

## Builds on (most cited first, 30 of 34)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [Neural Machine Translation of Rare Words with Subword Units](https://mlsanity.com/paper/1508.07909/) (2015)
- [A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference](https://mlsanity.com/paper/1704.05426/) (2017)
- [DeBERTa: Decoding-enhanced BERT with Disentangled Attention](https://mlsanity.com/paper/2006.03654/) (2020)
- [FitNets: Hints for Thin Deep Nets](https://mlsanity.com/paper/1412.6550/) (2014)
- [Know What You Don't Know: Unanswerable Questions for SQuAD](https://mlsanity.com/paper/1806.03822/) (2018)
- [Multitask Prompted Training Enables Zero-Shot Task Generalization](https://mlsanity.com/paper/2110.08207/) (2021)
- [MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers](https://mlsanity.com/paper/2002.10957/) (2020)
- [DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing](https://mlsanity.com/paper/2111.09543/) (2021)
- [TinyBERT: Distilling BERT for Natural Language Understanding](https://mlsanity.com/paper/1909.10351/) (2019)
- [Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Books](https://mlsanity.com/paper/1506.06724/) (2015)
- [SemEval-2017 Task 1: Semantic Textual Similarity - Multilingual and Cross-lingual Focused Evaluation](https://mlsanity.com/paper/1708.00055/) (2017)
- [The LAMBADA dataset: Word prediction requiring a broad discourse context](https://mlsanity.com/paper/1606.06031/) (2016)
- [Neural Network Acceptability Judgments](https://mlsanity.com/paper/1805.12471/) (2018)
- [Patient Knowledge Distillation for BERT Model Compression](https://mlsanity.com/paper/1908.09355/) (2019)
- [MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devices](https://mlsanity.com/paper/2004.02984/) (2020)
- [DynaBERT: Dynamic BERT with Adaptive Width and Depth](https://mlsanity.com/paper/2004.04037/) (2020)
- [MiniLMv2: Multi-Head Self-Attention Relation Distillation for Compressing Pretrained Transformers](https://mlsanity.com/paper/2012.15828/) (2020)
- [A Simple Method for Commonsense Reasoning](https://mlsanity.com/paper/1806.02847/) (2018)
- [BERT-of-Theseus: Compressing BERT by Progressive Module Replacing](https://mlsanity.com/paper/2002.02925/) (2020)
- [Analyzing Individual Neurons in Pre-trained Language Models](https://mlsanity.com/paper/2010.02695/) (2020)

## Built on by (most cited first, 30 of 93)

- [A Survey on Knowledge Distillation of Large Language Models](https://mlsanity.com/paper/2402.13116/) (2024)
- [A Survey on Model Compression for Large Language Models](https://mlsanity.com/paper/2308.07633/) (2023)
- [A Survey on Efficient Inference for Large Language Models](https://mlsanity.com/paper/2404.14294/) (2024)
- [Efficient Large Language Models: A Survey](https://mlsanity.com/paper/2312.03863/) (2023)
- [LLM Inference Unveiled: Survey and Roofline Model Insights](https://mlsanity.com/paper/2402.16363/) (2024)
- [A Survey of Resource-efficient LLM and Multimodal Foundation Models](https://mlsanity.com/paper/2401.08092/) (2024)
- [Model Compression and Efficient Inference for Large Language Models: A Survey](https://mlsanity.com/paper/2402.09748/) (2024)
- [Survey on Knowledge Distillation for Large Language Models: Methods, Evaluation, and Application](https://mlsanity.com/paper/2407.01885/) (2024)
- [What is the Role of Small Models in the LLM Era: A Survey](https://mlsanity.com/paper/2409.06857/) (2024)
- [CodecLM: Aligning Language Models with Tailored Synthetic Data](https://mlsanity.com/paper/2404.05875/) (2024)
- [Students Parrot Their Teachers: Membership Inference on Model Distillation](https://mlsanity.com/paper/2303.03446/) (2023)
- [A Survey of Small Language Models](https://mlsanity.com/paper/2410.20011/) (2024)
- [Adapting Large Language Models for Content Moderation: Pitfalls in Data Engineering and Supervised Fine-tuning](https://mlsanity.com/paper/2310.03400/) (2023)
- [ApiQ: Finetuning of 2-Bit Quantized Large Language Model](https://mlsanity.com/paper/2402.05147/) (2024)
- [AD-KD: Attribution-Driven Knowledge Distillation for Language Model Compression](https://mlsanity.com/paper/2305.10010/) (2023)
- [DDK: Distilling Domain Knowledge for Efficient Large Language Models](https://mlsanity.com/paper/2407.16154/) (2024)
- [LLAVADI: What Matters For Multimodal Large Language Models Distillation](https://mlsanity.com/paper/2407.19409/) (2024)
- [PromptKD: Distilling Student-Friendly Knowledge for Generative Language Models via Prompt Tuning](https://mlsanity.com/paper/2402.12842/) (2024)
- [Align-KD: Distilling Cross-Modal Alignment Knowledge for Mobile Vision-Language Model Enhancement](https://mlsanity.com/paper/2412.01282/) (2024)
- [ABKD: Pursuing a Proper Allocation of the Probability Mass in Knowledge Distillation via α-β-Divergence](https://mlsanity.com/paper/2505.04560/) (2025)
- [Faster and Lighter LLMs: A Survey on Current Challenges and Way Forward](https://mlsanity.com/paper/2402.01799/) (2024)
- [BiLD: Bi-directional Logits Difference Loss for Large Language Model Distillation](https://mlsanity.com/paper/2406.13555/) (2024)
- [SLMRec: Distilling Large Language Models into Small for Sequential Recommendation](https://mlsanity.com/paper/2405.17890/) (2024)
- [A Comprehensive Survey of Compression Algorithms for Language Models](https://mlsanity.com/paper/2401.15347/) (2024)
- [A Token is Worth over 1,000 Tokens: Efficient Knowledge Distillation through Low-Rank Clone](https://mlsanity.com/paper/2505.12781/) (2025)
- [DREAM: Drafting with Refined Target Features and Entropy-Adaptive Cross-Attention Fusion for Multimodal Speculative Decoding](https://mlsanity.com/paper/2505.19201/) (2025)
- [Toward Adaptive Large Language Models Structured Pruning via Hybrid-grained Weight Importance Assessment](https://mlsanity.com/paper/2403.10799/) (2024)
- [Quantifying Knowledge Distillation Using Partial Information Decomposition](https://mlsanity.com/paper/2411.07483/) (2024)
- [LLM-Oriented Token-Adaptive Knowledge Distillation](https://mlsanity.com/paper/2510.11615/) (2025)
- [Module-wise Adaptive Distillation for Multimodality Foundation Models](https://mlsanity.com/paper/2310.04550/) (2023)

## Abstract (arXiv)

Layer-wise distillation is a powerful tool to compress large models (i.e. teacher models) into small ones (i.e., student models). The student distills knowledge from the teacher by mimicking the hidden representations of the teacher at every intermediate layer. However, layer-wise distillation is difficult. Since the student has a smaller model capacity than the teacher, it is often under-fitted. Furthermore, the hidden representations of the teacher contain redundant information that the student does not necessarily need for the target task's learning. To address these challenges, we propose a novel Task-aware layEr-wise Distillation (TED). TED designs task-aware filters to align the hidden representations of the student and the teacher at each layer. The filters select the knowledge that is useful for the target task from the hidden representations. As such, TED reduces the knowledge gap between the two models and helps the student to fit better on the target task. We evaluate TED in two scenarios: continual pre-training and fine-tuning. TED demonstrates significant and consistent improvements over existing distillation methods in both scenarios. Code is available at https://github.com/cliang1453/task-aware-distillation.