Challenge: Large pre-trained transformer language models are notoriously expensive to train . prior work has developed smaller, more compact models to reduce training costs .
Approach: They propose to develop smaller, more compact transformer language models which can be calibrated in-domain . they show that smaller models can achieve competitive calibration compared to larger models .
Outcome: The proposed models achieve competitive calibration and better calibration than larger models on a wide range of tasks.

Similar Papers

Calibration of Pre-trained Transformers (2020.emnlp-main)

Copied to clipboard

Challenge: Pre-trained Transformers dominate benchmark tasks but use a large number of self-attention heads across many layers in a way that is difficult to unpack.
Approach: They analyze pre-trained Transformer models' posterior probabilities to determine whether they are calibrated for three tasks: natural language inference, paraphrase detection, and commonsense reasoning.
Outcome: The models are calibrated in-domain and out-of-domain, and their calibration error out-domain can be as much as 3.5x lower.
Compressing Large-Scale Transformer-Based Models: A Case Study on BERT (2021.tacl-1)

Copied to clipboard

Challenge: Popular pre-trained Transformers have improved performance for various NLP tasks by sizable margins, but are too resource-hungry and computation-intensive to suit low-capacity devices or applications with strict latency requirements.
Approach: They present a literature review of the compression of Transformers, focusing on the popular BERT model, which has attracted considerable research attention.
Outcome: The proposed models improve Sentiment analysis, paraphrase detection, machine reading comprehension, question answering, text summarization, and other tasks by sizable margins.
The Trade-offs of Domain Adaptation for Neural Language Models (2022.acl-long)

Copied to clipboard

Challenge: Neural Language Models (LMs) trained on large generic training sets have been shown to be effective at adapting to smaller, specific target domains for language modeling and other downstream tasks.
Approach: They propose a framework for a Neural Language Models (LM) to be presented in a common framework.
Outcome: The proposed framework highlights similarities and subtle differences between adaptation techniques and the framework.
On the Way to Lossless Compression of Language Transformers: Exploring Cross-Domain Properties of Quantization (2024.lrec-main)

Copied to clipboard

Challenge: Modern Natural Language Processing models have a huge capacity, but this makes it difficult to employ.
Approach: They propose a method to quantize at least 95% of Transformer weights without access to task-specific data so the drop in performance does not exceed 0.02%.
Outcome: The proposed method quantizes 95% of Transformer weights and corresponding activations to INT8 without access to task-specific data so the drop in performance does not exceed 0.02%.
Domain Pre-training Impact on Representations (2025.findings-emnlp)

Copied to clipboard

Challenge: a small, specialized corpus can produce effective representations, but the quality of pre-training is not affected by the choice of corpus.
Approach: They focus on the representation quality achieved through pre-training alone .
Outcome: The results show that pre-training on a small, specialized corpus produces effective representations.
Bag of Tricks for In-Distribution Calibration of Pretrained Transformers (2023.findings-eacl)

Copied to clipboard

Challenge: Recent studies show that pre-trained language models (PLMs) often predict over-confidently.
Approach: They propose to use ensemble learning and data augmentation to improve confidence calibration for PLMs by combining calibration techniques with a trade-off between accuracy and classification.
Outcome: The proposed calibration method improves classification accuracy and confidence in pre-trained language models by combining several calibration techniques.
Optimizing Deeper Transformers on Small Datasets (2021.acl-long)

Copied to clipboard

Challenge: a common belief that training deep transformers from scratch requires large datasets is wrong . however, with proper initialization and optimization, the benefits of very deep transformer can carry over to challenging tasks with small datasets.
Approach: They train 48 layers of transformers from pre-trained RoBERTa and 24 relation-aware layers from scratch.
Outcome: The proposed scheme achieves state-of-the-art performance on a text-to-sql parsing benchmark . it uses 24 fine-tuned layers from pre-trained RoBERTa and 24 relation-aware layers from scratch .
Identifying the limits of transformers when performing model-checking with natural language (2023.eacl-main)

Copied to clipboard

Challenge: Recent studies have focused on transformer models’ ability to perform reasoning on text, but the above question has not been adequately answered.
Approach: They investigated the problem of model-checking with natural language to determine whether transformers can comprehend logical semantics in natural language.
Outcome: The proposed model-checking problem is suited to address this issue but is untouched in natural language inference research.
The Diminishing Returns of Masked Language Models to Science (2023.findings-acl)

Copied to clipboard

Challenge: Existing studies have shown that masked language models can improve downstream tasks by pretraining larger models for longer on more data.
Approach: They empirically evaluate the extent to which these results extend to tasks in science by using 14 domain-specific transformer-based masked language models.
Outcome: The proposed model can improve on 12 scientific tasks, but not all.
When High Accuracy Hides Poor Calibration: Rethinking Confidence Evaluation in Transformer-Based Text Classification with Balanced Brier Score (2026.acl-long)

Copied to clipboard

Challenge: Existing evidence for TC under fine-tuning is limited.
Approach: They propose a calibration method that balances the contribution of correct and incorrect predictions within confidence bins.
Outcome: The proposed calibration measures show that the models are overconfident even when miscalibrated . the proposed calibration methods challenge calibration assessment practices and provide a more reliable alternative for evaluating confidence quality in Transformer-based TC.

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