# Toward Efficient Language Model Pretraining and Downstream Adaptation via Self-Evolution: A Case Study on SuperGLUE

arXiv: https://arxiv.org/abs/2212.01853 · HTML: https://mlsanity.com/paper/2212.01853/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 48 references that are in the map.
- First posted on arXiv 4 Dec 2022.

## Builds on (most cited first, 30 of 36)

- [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)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions](https://mlsanity.com/paper/1905.10044/) (2019)
- [DeBERTa: Decoding-enhanced BERT with Disentangled Attention](https://mlsanity.com/paper/2006.03654/) (2020)
- [SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems](https://mlsanity.com/paper/1905.00537/) (2019)
- [Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Books](https://mlsanity.com/paper/1506.06724/) (2015)
- [Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning](https://mlsanity.com/paper/1704.03976/) (2017)
- [SpanBERT: Improving Pre-training by Representing and Predicting Spans](https://mlsanity.com/paper/1907.10529/) (2019)
- [ST-MoE: Designing Stable and Transferable Sparse Expert Models](https://mlsanity.com/paper/2202.08906/) (2022)
- [WiC: the Word-in-Context Dataset for Evaluating Context-Sensitive Meaning Representations](https://mlsanity.com/paper/1808.09121/) (2018)
- [ERNIE: Enhanced Representation through Knowledge Integration](https://mlsanity.com/paper/1904.09223/) (2019)
- [ERNIE 3.0: Large-scale Knowledge Enhanced Pre-training for Language Understanding and Generation](https://mlsanity.com/paper/2107.02137/) (2021)
- [SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized Optimization](https://mlsanity.com/paper/1911.03437/) (2019)
- [SPoT: Better Frozen Model Adaptation through Soft Prompt Transfer](https://mlsanity.com/paper/2110.07904/) (2021)
- [A Simple Method for Commonsense Reasoning](https://mlsanity.com/paper/1806.02847/) (2018)
- [ReCoRD: Bridging the Gap between Human and Machine Commonsense Reading Comprehension](https://mlsanity.com/paper/1810.12885/) (2018)
- [SparseAdapter: An Easy Approach for Improving the Parameter-Efficiency of Adapters](https://mlsanity.com/paper/2210.04284/) (2022)
- [Parameter-Efficient and Student-Friendly Knowledge Distillation](https://mlsanity.com/paper/2205.15308/) (2022)
- [Improving Sharpness-Aware Minimization with Fisher Mask for Better Generalization on Language Models](https://mlsanity.com/paper/2210.05497/) (2022)
- [PANDA: Prompt Transfer Meets Knowledge Distillation for Efficient Model Adaptation](https://mlsanity.com/paper/2208.10160/) (2022)
- [METRO: Efficient Denoising Pretraining of Large Scale Autoencoding Language Models with Model Generated Signals](https://mlsanity.com/paper/2204.06644/) (2022)
- [E2S2: Encoding-Enhanced Sequence-to-Sequence Pretraining for Language Understanding and Generation](https://mlsanity.com/paper/2205.14912/) (2022)
- [InforMask: Unsupervised Informative Masking for Language Model Pretraining](https://mlsanity.com/paper/2210.11771/) (2022)

## Built on by (most cited first, 24 of 24)

- [Can ChatGPT Understand Too? A Comparative Study on ChatGPT and Fine-tuned BERT](https://mlsanity.com/paper/2302.10198/) (2023)
- [Towards Making the Most of ChatGPT for Machine Translation](https://mlsanity.com/paper/2303.13780/) (2023)
- [Achieving >97% on GSM8K: Deeply Understanding the Problems Makes LLMs Better Solvers for Math Word Problems](https://mlsanity.com/paper/2404.14963/) (2024)
- [Diversifying the Mixture-of-Experts Representation for Language Models with Orthogonal Optimizer](https://mlsanity.com/paper/2310.09762/) (2023)
- [Take Care of Your Prompt Bias! Investigating and Mitigating Prompt Bias in Factual Knowledge Extraction](https://mlsanity.com/paper/2403.09963/) (2024)
- [Bag of Tricks for Effective Language Model Pretraining and Downstream Adaptation: A Case Study on GLUE](https://mlsanity.com/paper/2302.09268/) (2023)
- [Revisiting Token Dropping Strategy in Efficient BERT Pretraining](https://mlsanity.com/paper/2305.15273/) (2023)
- [Divide, Conquer, and Combine: Mixture of Semantic-Independent Experts for Zero-Shot Dialogue State Tracking](https://mlsanity.com/paper/2306.00434/) (2023)
- [Self-Evolution Learning for Discriminative Language Model Pretraining](https://mlsanity.com/paper/2305.15275/) (2023)
- [Fostering the Ecosystem of Open Neural Encoders for Portuguese with Albertina PT* Family](https://mlsanity.com/paper/2403.01897/) (2024)
- [Evaluating Implicit Bias in Large Language Models by Attacking From a Psychometric Perspective](https://mlsanity.com/paper/2406.14023/) (2024)
- [CLOCR-C: Context Leveraging OCR Correction with Pre-trained Language Models](https://mlsanity.com/paper/2408.17428/) (2024)
- [Prompt-Learning for Cross-Lingual Relation Extraction](https://mlsanity.com/paper/2304.10354/) (2023)
- [Open Sentence Embeddings for Portuguese with the Serafim PT* encoders family](https://mlsanity.com/paper/2407.19527/) (2024)
- [OmniForce: On Human-Centered, Large Model Empowered and Cloud-Edge Collaborative AutoML System](https://mlsanity.com/paper/2303.00501/) (2023)
- [Zero-Shot Sharpness-Aware Quantization for Pre-trained Language Models](https://mlsanity.com/paper/2310.13315/) (2023)
- [What Are They Filtering Out? An Experimental Benchmark of Filtering Strategies for Harm Reduction in Pretraining Datasets](https://mlsanity.com/paper/2503.05721/) (2025)
- [Explaining Relation Classification Models with Semantic Extents](https://mlsanity.com/paper/2308.02193/) (2023)
- [Self-Evolution Knowledge Distillation for LLM-based Machine Translation](https://mlsanity.com/paper/2412.15303/) (2024)
- [MPipeMoE: Memory Efficient MoE for Pre-trained Models with Adaptive Pipeline Parallelism](https://mlsanity.com/paper/2506.22175/) (2025)
- [Survey of NLU Benchmarks Diagnosing Linguistic Phenomena: Why not Standardize Diagnostics Benchmarks?](https://mlsanity.com/paper/2507.20419/) (2025)
- [Open Your Model's Eyes: Video and Context-Aware Multimodal Backchannel Prediction](https://mlsanity.com/paper/2607.22729/) (2026)
- [E-CONAN (Entailment, CONtradition And Neutral) Benchmarks: Arabic Textual Entailment and Natural Inference Datasets](https://mlsanity.com/paper/2609.11334/) (2026)
- [E-CONAN (Entailment, CONtradition And Neutral) Diagnostics Dataset Investigating Linguistic Phenomena in Arabic Natural Language Understanding](https://mlsanity.com/paper/2609.33530/) (2026)

## Abstract (arXiv)

This technical report briefly describes our JDExplore d-team's Vega v2 submission on the SuperGLUE leaderboard. SuperGLUE is more challenging than the widely used general language understanding evaluation (GLUE) benchmark, containing eight difficult language understanding tasks, including question answering, natural language inference, word sense disambiguation, coreference resolution, and reasoning. [Method] Instead of arbitrarily increasing the size of a pretrained language model (PLM), our aim is to 1) fully extract knowledge from the input pretraining data given a certain parameter budget, e.g., 6B, and 2) effectively transfer this knowledge to downstream tasks. To achieve goal 1), we propose self-evolution learning for PLMs to wisely predict the informative tokens that should be masked, and supervise the masked language modeling (MLM) process with rectified smooth labels. For goal 2), we leverage the prompt transfer technique to improve the low-resource tasks by transferring the knowledge from the foundation model and related downstream tasks to the target task. [Results] According to our submission record (Oct. 2022), with our optimized pretraining and fine-tuning strategies, our 6B Vega method achieved new state-of-the-art performance on 4/8 tasks, sitting atop the SuperGLUE leaderboard on Oct. 8, 2022, with an average score of 91.3.