Stubborn Lexical Bias in Data and Models

• URL: http://arxiv.org/abs/2306.02190v1
• Date: Sat, 3 Jun 2023 20:12:27 GMT
• Title: Stubborn Lexical Bias in Data and Models
• Authors: Sofia Serrano, Jesse Dodge, Noah A. Smith
• Abstract summary: 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.
• Score: 50.79738900885665
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In NLP, recent work has seen increased focus on spurious correlations between various features and labels in training data, and how these influence model behavior. However, the presence and effect of such correlations are typically examined feature by feature. We investigate the cumulative impact on a model of many such intersecting features. Using a new statistical method, we examine whether such spurious patterns in data appear in models trained on the data. We select two tasks -- natural language inference and duplicate-question detection -- for which any unigram feature on its own should ideally be uninformative, which gives us a large pool of automatically extracted features with which to experiment. The large size of this pool allows us to investigate the intersection of features spuriously associated with (potentially different) labels. We then apply an optimization approach to *reweight* the training data, reducing thousands of spurious correlations, and examine how doing so affects models trained on the reweighted data. 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, including worsened bias for slightly more complex features (bigrams). We close with discussion about the implications of our results on what it means to "debias" training data, and how issues of data quality can affect model bias.

Related papers

• Measuring and Improving Attentiveness to Partial Inputs with Counterfactuals [91.59906995214209]
  We propose a new evaluation method, Counterfactual Attentiveness Test (CAT) CAT uses counterfactuals by replacing part of the input with its counterpart from a different example, expecting an attentive model to change its prediction. We show that GPT3 becomes less attentive with an increased number of demonstrations, while its accuracy on the test data improves.
  arXiv  Detail & Related papers  (2023-11-16T06:27:35Z)
• Even Small Correlation and Diversity Shifts Pose Dataset-Bias Issues [19.4921353136871]
  We study two types of distribution shifts: diversity shifts, which occur when test samples exhibit patterns unseen during training, and correlation shifts, which occur when test data present a different correlation between seen invariant and spurious features. We propose an integrated protocol to analyze both types of shifts using datasets where they co-exist in a controllable manner.
  arXiv  Detail & Related papers  (2023-05-09T23:40:23Z)
• 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)
• Decorrelate Irrelevant, Purify Relevant: Overcome Textual Spurious Correlations from a Feature Perspective [47.10907370311025]
  Natural language understanding (NLU) models tend to rely on spurious correlations (emphi.e., dataset bias) to achieve high performance on in-distribution datasets but poor performance on out-of-distribution ones. Most of the existing debiasing methods often identify and weaken these samples with biased features. Down-weighting these samples obstructs the model in learning from the non-biased parts of these samples. We propose to eliminate spurious correlations in a fine-grained manner from a feature space perspective.
  arXiv  Detail & Related papers  (2022-02-16T13:23:14Z)
• Learning from others' mistakes: Avoiding dataset biases without modeling them [111.17078939377313]
  State-of-the-art natural language processing (NLP) models often learn to model dataset biases and surface form correlations instead of features that target the intended task. Previous work has demonstrated effective methods to circumvent these issues when knowledge of the bias is available. We show a method for training models that learn to ignore these problematic correlations.
  arXiv  Detail & Related papers  (2020-12-02T16:10:54Z)
• Learning to Model and Ignore Dataset Bias with Mixed Capacity Ensembles [66.15398165275926]
  We propose a method that can automatically detect and ignore dataset-specific patterns, which we call dataset biases. Our method trains a lower capacity model in an ensemble with a higher capacity model. We show improvement in all settings, including a 10 point gain on the visual question answering dataset.
  arXiv  Detail & Related papers  (2020-11-07T22:20:03Z)
• Debiasing Skin Lesion Datasets and Models? Not So Fast [17.668005682385175]
  Models learned from data risk learning biases from that same data. When models learn spurious correlations not found in real-world situations, their deployment for critical tasks, such as medical decisions, can be catastrophic. We find out that, despite interesting results that point to promising future research, current debiasing methods are not ready to solve the bias issue for skin-lesion models.
  arXiv  Detail & Related papers  (2020-04-23T21:07:49Z)

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.