Understanding the Interplay of Scale, Data, and Bias in Language Models: A Case Study with BERT

• URL: http://arxiv.org/abs/2407.21058v1
• Date: Thu, 25 Jul 2024 23:09:33 GMT
• Title: Understanding the Interplay of Scale, Data, and Bias in Language Models: A Case Study with BERT
• Authors: Muhammad Ali, Swetasudha Panda, Qinlan Shen, Michael Wick, Ari Kobren,
• Abstract summary: We study the influence of model scale and pre-training data on a language model's learnt social biases. Our experiments show that pre-training data substantially influences how upstream biases evolve with model scale. We shed light on the complex interplay of data and model scale, and investigate how it translates to concrete biases.
• Score: 4.807994469764776
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In the current landscape of language model research, larger models, larger datasets and more compute seems to be the only way to advance towards intelligence. While there have been extensive studies of scaling laws and models' scaling behaviors, the effect of scale on a model's social biases and stereotyping tendencies has received less attention. In this study, we explore the influence of model scale and pre-training data on its learnt social biases. We focus on BERT -- an extremely popular language model -- and investigate biases as they show up during language modeling (upstream), as well as during classification applications after fine-tuning (downstream). Our experiments on four architecture sizes of BERT demonstrate that pre-training data substantially influences how upstream biases evolve with model scale. With increasing scale, models pre-trained on large internet scrapes like Common Crawl exhibit higher toxicity, whereas models pre-trained on moderated data sources like Wikipedia show greater gender stereotypes. However, downstream biases generally decrease with increasing model scale, irrespective of the pre-training data. Our results highlight the qualitative role of pre-training data in the biased behavior of language models, an often overlooked aspect in the study of scale. Through a detailed case study of BERT, we shed light on the complex interplay of data and model scale, and investigate how it translates to concrete biases.

Related papers

• Less can be more: representational vs. stereotypical gender bias in facial expression recognition [3.9698529891342207]
  Machine learning models can inherit biases from their training data, leading to discriminatory or inaccurate predictions. This paper investigates the propagation of demographic biases from datasets into machine learning models. We focus on the gender demographic component, analyzing two types of bias: representational and stereotypical.
  arXiv  Detail & Related papers  (2024-06-25T09:26:49Z)
• Fast Model Debias with Machine Unlearning [54.32026474971696]
  Deep neural networks might behave in a biased manner in many real-world scenarios. Existing debiasing methods suffer from high costs in bias labeling or model re-training. We propose a fast model debiasing framework (FMD) which offers an efficient approach to identify, evaluate and remove biases.
  arXiv  Detail & Related papers  (2023-10-19T08:10:57Z)
• Scaling Laws Do Not Scale [54.72120385955072]
  Recent work has argued that as the size of a dataset increases, the performance of a model trained on that dataset will increase. We argue that this scaling law relationship depends on metrics used to measure performance that may not correspond with how different groups of people perceive the quality of models' output. Different communities may also have values in tension with each other, leading to difficult, potentially irreconcilable choices about metrics used for model evaluations.
  arXiv  Detail & Related papers  (2023-07-05T15:32:21Z)
• On Hate Scaling Laws For Data-Swamps [14.891493485229251]
  We show that the presence of hateful content in datasets, when measured with a Hate Content Rate (HCR) metric, increased by nearly $12%$. As scale increased, the tendency of the model to associate images of human faces with the human being' class over 7 other offensive classes reduced by half. For the Black female category, the tendency of the model to associate their faces with the criminal' class doubled, while quintupling for Black male faces.
  arXiv  Detail & Related papers  (2023-06-22T18:00:17Z)
• Exposing Bias in Online Communities through Large-Scale Language Models [3.04585143845864]
  This work uses the flaw of bias in language models to explore the biases of six different online communities. The bias of the resulting models is evaluated by prompting the models with different demographics and comparing the sentiment and toxicity values of these generations. This work not only affirms how easily bias is absorbed from training data but also presents a scalable method to identify and compare the bias of different datasets or communities.
  arXiv  Detail & Related papers  (2023-06-04T08:09:26Z)
• Stubborn Lexical Bias in Data and Models [50.79738900885665]
  We use a new statistical method to examine whether spurious patterns in data appear in models trained on the data. We apply an optimization approach to *reweight* the training data, reducing thousands of spurious correlations. Surprisingly, though this method can successfully reduce lexical biases in the training data, we still find strong evidence of corresponding bias in the trained models.
  arXiv  Detail & Related papers  (2023-06-03T20:12:27Z)
• Analyzing Bias in Diffusion-based Face Generation Models [75.80072686374564]
  Diffusion models are increasingly popular in synthetic data generation and image editing applications. We investigate the presence of bias in diffusion-based face generation models with respect to attributes such as gender, race, and age. We examine how dataset size affects the attribute composition and perceptual quality of both diffusion and Generative Adversarial Network (GAN) based face generation models.
  arXiv  Detail & Related papers  (2023-05-10T18:22:31Z)
• Variation of Gender Biases in Visual Recognition Models Before and After Finetuning [29.55318393877906]
  We introduce a framework to measure how biases change before and after fine-tuning a large scale visual recognition model for a downstream task. We find that supervised models trained on datasets such as ImageNet-21k are more likely to retain their pretraining biases. We also find that models finetuned on larger scale datasets are more likely to introduce new biased associations.
  arXiv  Detail & Related papers  (2023-03-14T03:42:47Z)
• Debiasing Vision-Language Models via Biased Prompts [79.04467131711775]
  We propose a general approach for debiasing vision-language foundation models by projecting out biased directions in the text embedding. We show that debiasing only the text embedding with a calibrated projection matrix suffices to yield robust classifiers and fair generative models.
  arXiv  Detail & Related papers  (2023-01-31T20:09:33Z)
• Training Trajectories of Language Models Across Scales [99.38721327771208]
  Scaling up language models has led to unprecedented performance gains. How do language models of different sizes learn during pre-training? Why do larger language models demonstrate more desirable behaviors?
  arXiv  Detail & Related papers  (2022-12-19T19:16:29Z)
• The Birth of Bias: A case study on the evolution of gender bias in an English language model [1.6344851071810076]
  We use a relatively small language model, using the LSTM architecture trained on an English Wikipedia corpus. We find that the representation of gender is dynamic and identify different phases during training. We show that gender information is represented increasingly locally in the input embeddings of the model.
  arXiv  Detail & Related papers  (2022-07-21T00:59:04Z)

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.