Are Larger Pretrained Language Models Uniformly Better? Comparing Performance at the Instance Level

• URL: http://arxiv.org/abs/2105.06020v1
• Date: Thu, 13 May 2021 01:10:51 GMT
• Title: Are Larger Pretrained Language Models Uniformly Better? Comparing Performance at the Instance Level
• Authors: Ruiqi Zhong, Dhruba Ghosh, Dan Klein, Jacob Steinhardt
• Abstract summary: We find that BERT-Large is worse than BERT-Mini on at least 1-4% of instances across MNLI, SST-2, and QQP. Finetuning noise increases with model size and that instance-level accuracy has momentum. Our findings suggest that instance-level predictions provide a rich source of information.
• Score: 38.64433236359172
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Larger language models have higher accuracy on average, but are they better on every single instance (datapoint)? Some work suggests larger models have higher out-of-distribution robustness, while other work suggests they have lower accuracy on rare subgroups. To understand these differences, we investigate these models at the level of individual instances. However, one major challenge is that individual predictions are highly sensitive to noise in the randomness in training. We develop statistically rigorous methods to address this, and after accounting for pretraining and finetuning noise, we find that our BERT-Large is worse than BERT-Mini on at least 1-4% of instances across MNLI, SST-2, and QQP, compared to the overall accuracy improvement of 2-10%. We also find that finetuning noise increases with model size and that instance-level accuracy has momentum: improvement from BERT-Mini to BERT-Medium correlates with improvement from BERT-Medium to BERT-Large. Our findings suggest that instance-level predictions provide a rich source of information; we therefore, recommend that researchers supplement model weights with model predictions.

Related papers

• Compressed Models are NOT Trust-equivalent to Their Large Counterparts [0.8124699127636158]
  Large Deep Learning models are often compressed before being deployed in a resource-constrained environment.<n>Can we trust the prediction of compressed models just as we trust the prediction of the original large model?<n>We propose a two-dimensional framework for trust-equivalence evaluation.
  arXiv  Detail & Related papers  (2025-08-19T05:49:39Z)
• DataDecide: How to Predict Best Pretraining Data with Small Experiments [67.95896457895404]
  We release models, data, and evaluations in DataDecide -- the most extensive open suite of models over differences in data and scale. We conduct controlled pretraining experiments across 25 corpora with differing sources, deduplication, and filtering up to 100B tokens, model sizes up to 1B parameters, and 3 random seeds.
  arXiv  Detail & Related papers  (2025-04-15T17:02:15Z)
• More precise edge detections [0.0]
  Edge detection (ED) is a base task in computer vision. Current models still suffer from unsatisfactory precision rates. Model architecture for more precise predictions still needs an investigation.
  arXiv  Detail & Related papers  (2024-07-29T13:24:55Z)
• Ask Your Distribution Shift if Pre-Training is Right for You [74.18516460467019]
  In practice, fine-tuning a pre-trained model improves robustness significantly in some cases but not at all in others. We focus on two possible failure modes of models under distribution shift: poor extrapolation and biases in the training data. Our study suggests that, as a rule of thumb, pre-training can help mitigate poor extrapolation but not dataset biases.
  arXiv  Detail & Related papers  (2024-02-29T23:46:28Z)
• Uncertainty-aware Parameter-Efficient Self-training for Semi-supervised Language Understanding [38.11411155621616]
  We study self-training as one of the predominant semi-supervised learning approaches. We present UPET, a novel Uncertainty-aware self-Training framework. We show that UPET achieves a substantial improvement in terms of performance and efficiency.
  arXiv  Detail & Related papers  (2023-10-19T02:18:29Z)
• PLATON: Pruning Large Transformer Models with Upper Confidence Bound of Weight Importance [114.1541203743303]
  We propose PLATON, which captures the uncertainty of importance scores by upper confidence bound (UCB) of importance estimation. We conduct extensive experiments with several Transformer-based models on natural language understanding, question answering and image classification.
  arXiv  Detail & Related papers  (2022-06-25T05:38:39Z)
• MoEBERT: from BERT to Mixture-of-Experts via Importance-Guided Adaptation [68.30497162547768]
  We propose MoEBERT, which uses a Mixture-of-Experts structure to increase model capacity and inference speed. We validate the efficiency and effectiveness of MoEBERT on natural language understanding and question answering tasks.
  arXiv  Detail & Related papers  (2022-04-15T23:19:37Z)
• Impact of Pretraining Term Frequencies on Few-Shot Reasoning [51.990349528930125]
  We investigate how well pretrained language models reason with terms that are less frequent in the pretraining data. We measure the strength of this correlation for a number of GPT-based language models on various numerical deduction tasks. Although LMs exhibit strong performance at few-shot numerical reasoning tasks, our results raise the question of how much models actually generalize beyond pretraining data.
  arXiv  Detail & Related papers  (2022-02-15T05:43:54Z)
• Few-shot Instruction Prompts for Pretrained Language Models to Detect Social Biases [55.45617404586874]
  We propose a few-shot instruction-based method for prompting pre-trained language models (LMs) We show that large LMs can detect different types of fine-grained biases with similar and sometimes superior accuracy to fine-tuned models.
  arXiv  Detail & Related papers  (2021-12-15T04:19:52Z)
• Complementary Ensemble Learning [1.90365714903665]
  We derive a technique to improve performance of state-of-the-art deep learning models. Specifically, we train auxiliary models which are able to complement state-of-the-art model uncertainty.
  arXiv  Detail & Related papers  (2021-11-09T03:23:05Z)
• Newer is not always better: Rethinking transferability metrics, their peculiarities, stability and performance [5.650647159993238]
  Fine-tuning of large pre-trained image and language models on small customized datasets has become increasingly popular. We show that the statistical problems with covariance estimation drive the poor performance of H-score. We propose a correction and recommend measuring correlation performance against relative accuracy in such settings.
  arXiv  Detail & Related papers  (2021-10-13T17:24:12Z)
• On the Stability of Fine-tuning BERT: Misconceptions, Explanations, and Strong Baselines [31.807628937487927]
  Fine-tuning pre-trained language models such as BERT has become a common practice dominating leaderboards across various NLP benchmarks. Previous literature identified two potential reasons for the observed instability: catastrophic forgetting and small size of the fine-tuning datasets. We show that both hypotheses fail to explain the fine-tuning instability.
  arXiv  Detail & Related papers  (2020-06-08T19:06:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.