How Gender Debiasing Affects Internal Model Representations, and Why It Matters

• URL: http://arxiv.org/abs/2204.06827v1
• Date: Thu, 14 Apr 2022 08:54:15 GMT
• Title: How Gender Debiasing Affects Internal Model Representations, and Why It Matters
• Authors: Hadas Orgad, Seraphina Goldfarb-Tarrant, Yonatan Belinkov
• Abstract summary: We show that intrinsic bias is better indicator of debiasing than the standard WEAT metric. Our framework provides a comprehensive perspective on bias in NLP models, which can be applied to deploy NLP systems in a more informed manner.
• Score: 26.993273464725995
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Common studies of gender bias in NLP focus either on extrinsic bias measured by model performance on a downstream task or on intrinsic bias found in models' internal representations. However, the relationship between extrinsic and intrinsic bias is relatively unknown. In this work, we illuminate this relationship by measuring both quantities together: we debias a model during downstream fine-tuning, which reduces extrinsic bias, and measure the effect on intrinsic bias, which is operationalized as bias extractability with information-theoretic probing. Through experiments on two tasks and multiple bias metrics, we show that our intrinsic bias metric is a better indicator of debiasing than (a contextual adaptation of) the standard WEAT metric, and can also expose cases of superficial debiasing. Our framework provides a comprehensive perspective on bias in NLP models, which can be applied to deploy NLP systems in a more informed manner. Our code will be made publicly available.

Related papers

• BiasConnect: Investigating Bias Interactions in Text-to-Image Models [73.76853483463836]
  We introduce BiasConnect, a novel tool designed to analyze and quantify bias interactions in Text-to-Image models. Our method provides empirical estimates that indicate how other bias dimensions shift toward or away from an ideal distribution when a given bias is modified. We demonstrate the utility of BiasConnect for selecting optimal bias mitigation axes, comparing different TTI models on the dependencies they learn, and understanding the amplification of intersectional societal biases in TTI models.
  arXiv  Detail & Related papers  (2025-03-12T19:01:41Z)
• Towards Resource Efficient and Interpretable Bias Mitigation in Large Language Models [1.787433808079955]
  Large language models (LLMs) have been observed to perpetuate unwanted biases in training data. In this paper, we mitigate bias by leveraging small biased and anti-biased expert models to obtain a debiasing signal. Experiments on mitigating gender, race, and religion biases show a reduction in bias on several local and global bias metrics.
  arXiv  Detail & Related papers  (2024-12-02T16:56:08Z)
• How far can bias go? -- Tracing bias from pretraining data to alignment [54.51310112013655]
  This study examines the correlation between gender-occupation bias in pre-training data and their manifestation in LLMs. Our findings reveal that biases present in pre-training data are amplified in model outputs.
  arXiv  Detail & Related papers  (2024-11-28T16:20:25Z)
• Analyzing Correlations Between Intrinsic and Extrinsic Bias Metrics of Static Word Embeddings With Their Measuring Biases Aligned [8.673018064714547]
  We examine the abilities of intrinsic bias metrics of static word embeddings to predict whether Natural Language Processing (NLP) systems exhibit biased behavior. A word embedding is one of the fundamental NLP technologies that represents the meanings of words through real vectors, and problematically, it also learns social biases such as stereotypes.
  arXiv  Detail & Related papers  (2024-09-14T02:13:56Z)
• Is There a One-Model-Fits-All Approach to Information Extraction? Revisiting Task Definition Biases [62.806300074459116]
  Definition bias is a negative phenomenon that can mislead models. We identify two types of definition bias in IE: bias among information extraction datasets and bias between information extraction datasets and instruction tuning datasets. We propose a multi-stage framework consisting of definition bias measurement, bias-aware fine-tuning, and task-specific bias mitigation.
  arXiv  Detail & Related papers  (2024-03-25T03:19:20Z)
• Improving Bias Mitigation through Bias Experts in Natural Language Understanding [10.363406065066538]
  We propose a new debiasing framework that introduces binary classifiers between the auxiliary model and the main model. Our proposed strategy improves the bias identification ability of the auxiliary model.
  arXiv  Detail & Related papers  (2023-12-06T16:15:00Z)
• Causality and Independence Enhancement for Biased Node Classification [56.38828085943763]
  We propose a novel Causality and Independence Enhancement (CIE) framework, applicable to various graph neural networks (GNNs) Our approach estimates causal and spurious features at the node representation level and mitigates the influence of spurious correlations. Our approach CIE not only significantly enhances the performance of GNNs but outperforms state-of-the-art debiased node classification methods.
  arXiv  Detail & Related papers  (2023-10-14T13:56:24Z)
• Mitigating Bias for Question Answering Models by Tracking Bias Influence [84.66462028537475]
  We propose BMBI, an approach to mitigate the bias of multiple-choice QA models. Based on the intuition that a model would lean to be more biased if it learns from a biased example, we measure the bias level of a query instance. We show that our method could be applied to multiple QA formulations across multiple bias categories.
  arXiv  Detail & Related papers  (2023-10-13T00:49:09Z)
• Echoes: Unsupervised Debiasing via Pseudo-bias Labeling in an Echo Chamber [17.034228910493056]
  This paper presents experimental analyses revealing that the existing biased models overfit to bias-conflicting samples in the training data. We propose a straightforward and effective method called Echoes, which trains a biased model and a target model with a different strategy. Our approach achieves superior debiasing results compared to the existing baselines on both synthetic and real-world datasets.
  arXiv  Detail & Related papers  (2023-05-06T13:13:18Z)
• Feature-Level Debiased Natural Language Understanding [86.8751772146264]
  Existing natural language understanding (NLU) models often rely on dataset biases to achieve high performance on specific datasets. We propose debiasing contrastive learning (DCT) to mitigate biased latent features and neglect the dynamic nature of bias. DCT outperforms state-of-the-art baselines on out-of-distribution datasets while maintaining in-distribution performance.
  arXiv  Detail & Related papers  (2022-12-11T06:16:14Z)
• The SAME score: Improved cosine based bias score for word embeddings [49.75878234192369]
  We introduce SAME, a novel bias score for semantic bias in embeddings. We show that SAME is capable of measuring semantic bias and identify potential causes for social bias in downstream tasks.
  arXiv  Detail & Related papers  (2022-03-28T09:28:13Z)
• Information-Theoretic Bias Reduction via Causal View of Spurious Correlation [71.9123886505321]
  We propose an information-theoretic bias measurement technique through a causal interpretation of spurious correlation. We present a novel debiasing framework against the algorithmic bias, which incorporates a bias regularization loss. The proposed bias measurement and debiasing approaches are validated in diverse realistic scenarios.
  arXiv  Detail & Related papers  (2022-01-10T01:19:31Z)
• Learning Debiased Models with Dynamic Gradient Alignment and Bias-conflicting Sample Mining [39.00256193731365]
  Deep neural networks notoriously suffer from dataset biases which are detrimental to model robustness, generalization and fairness. We propose a two-stage debiasing scheme to combat against the intractable unknown biases.
  arXiv  Detail & Related papers  (2021-11-25T14:50:10Z)
• Intrinsic Bias Metrics Do Not Correlate with Application Bias [12.588713044749179]
  This research examines whether easy-to-measure intrinsic metrics correlate well to real world extrinsic metrics. We measure both intrinsic and extrinsic bias across hundreds of trained models covering different tasks and experimental conditions. We advise that efforts to debias embedding spaces be always also paired with measurement of downstream model bias, and suggest that that community increase effort into making downstream measurement more feasible via creation of additional challenge sets and annotated test data.
  arXiv  Detail & Related papers  (2020-12-31T18:59:44Z)

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.