Balancing out Bias: Achieving Fairness Through Training Reweighting
- URL: http://arxiv.org/abs/2109.08253v1
- Date: Thu, 16 Sep 2021 23:40:28 GMT
- Title: Balancing out Bias: Achieving Fairness Through Training Reweighting
- Authors: Xudong Han, Timothy Baldwin, Trevor Cohn
- Abstract summary: Bias in natural language processing arises from models learning characteristics of the author such as gender and race.
Existing methods for mitigating and measuring bias do not directly account for correlations between author demographics and linguistic variables.
This paper introduces a very simple but highly effective method for countering bias using instance reweighting.
- Score: 58.201275105195485
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Bias in natural language processing arises primarily from models learning
characteristics of the author such as gender and race when modelling tasks such
as sentiment and syntactic parsing. This problem manifests as disparities in
error rates across author demographics, typically disadvantaging minority
groups. Existing methods for mitigating and measuring bias do not directly
account for correlations between author demographics and linguistic variables.
Moreover, evaluation of bias has been inconsistent in previous work, in terms
of dataset balance and evaluation methods. This paper introduces a very simple
but highly effective method for countering bias using instance reweighting,
based on the frequency of both task labels and author demographics. We extend
the method in the form of a gated model which incorporates the author
demographic as an input, and show that while it is highly vulnerable to input
data bias, it provides debiased predictions through demographic input
perturbation, and outperforms all other bias mitigation techniques when
combined with instance reweighting.
Related papers
- MABR: A Multilayer Adversarial Bias Removal Approach Without Prior Bias Knowledge [6.208151505901749]
Models trained on real-world data often mirror and exacerbate existing social biases.
We introduce a novel adversarial training strategy that operates independently of prior bias-type knowledge.
Our method effectively reduces social biases without the need for demographic annotations.
arXiv Detail & Related papers (2024-08-10T09:11:01Z) - Leveraging Prototypical Representations for Mitigating Social Bias without Demographic Information [50.29934517930506]
DAFair is a novel approach to address social bias in language models.
We leverage prototypical demographic texts and incorporate a regularization term during the fine-tuning process to mitigate bias.
arXiv Detail & Related papers (2024-03-14T15:58:36Z) - 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) - Gender Biases in Automatic Evaluation Metrics for Image Captioning [87.15170977240643]
We conduct a systematic study of gender biases in model-based evaluation metrics for image captioning tasks.
We demonstrate the negative consequences of using these biased metrics, including the inability to differentiate between biased and unbiased generations.
We present a simple and effective way to mitigate the metric bias without hurting the correlations with human judgments.
arXiv Detail & Related papers (2023-05-24T04:27:40Z) - Counter-GAP: Counterfactual Bias Evaluation through Gendered Ambiguous
Pronouns [53.62845317039185]
Bias-measuring datasets play a critical role in detecting biased behavior of language models.
We propose a novel method to collect diverse, natural, and minimally distant text pairs via counterfactual generation.
We show that four pre-trained language models are significantly more inconsistent across different gender groups than within each group.
arXiv Detail & Related papers (2023-02-11T12:11:03Z) - D-BIAS: A Causality-Based Human-in-the-Loop System for Tackling
Algorithmic Bias [57.87117733071416]
We propose D-BIAS, a visual interactive tool that embodies human-in-the-loop AI approach for auditing and mitigating social biases.
A user can detect the presence of bias against a group by identifying unfair causal relationships in the causal network.
For each interaction, say weakening/deleting a biased causal edge, the system uses a novel method to simulate a new (debiased) dataset.
arXiv Detail & Related papers (2022-08-10T03:41:48Z) - Don't Discard All the Biased Instances: Investigating a Core Assumption
in Dataset Bias Mitigation Techniques [19.252319300590656]
Existing techniques for mitigating dataset bias often leverage a biased model to identify biased instances.
The role of these biased instances is then reduced during the training of the main model to enhance its robustness to out-of-distribution data.
In this paper, we show that this assumption does not hold in general.
arXiv Detail & Related papers (2021-09-01T10:25:46Z) - Learning Debiased Representation via Disentangled Feature Augmentation [19.348340314001756]
This paper presents an empirical analysis revealing that training with "diverse" bias-conflicting samples is crucial for debiasing.
We propose a novel feature-level data augmentation technique in order to synthesize diverse bias-conflicting samples.
arXiv Detail & Related papers (2021-07-03T08:03:25Z) - Impact of Gender Debiased Word Embeddings in Language Modeling [0.0]
Gender, race and social biases have been detected as evident examples of unfairness in applications of Natural Language Processing.
Recent studies have shown that the human-generated data used in training is an apparent factor of getting biases.
Current algorithms have also been proven to amplify biases from data.
arXiv Detail & Related papers (2021-05-03T14:45:10Z) - 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)
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.