Unsupervised Discovery of Implicit Gender Bias (2020.emnlp-main)

Copied to clipboard

Challenge: Social biases are difficult to identify because human judgements in this domain can be unreliable.
Approach: They propose an unsupervised approach to detecting implicit gender bias in text . their main challenge is forcing the model to focus on signs of implicit bias .
Outcome: The proposed model reduces the influence of confounds by focusing on signs of implicit bias rather than other artifacts in the data.

Similar Papers

Uncovering Implicit Gender Bias in Narratives through Commonsense Inference (2021.findings-emnlp)

Copied to clipboard

Challenge: Pre-trained language models learn harmful biases from their training corpora and may repeat these biase if used for generation.
Approach: They focus on gender biases associated with the protagonist in model-generated stories and use a commonsense reasoning engine to uncover them.
Outcome: The proposed model-generated stories are based on a commonsense reasoning engine and are able to uncover gender biases in the protagonist's motivations, attributes, mental states, and implications on others.
Multi-Dimensional Gender Bias Classification (2020.emnlp-main)

Copied to clipboard

Challenge: a novel framework decomposes gender bias in text along several pragmatic and semantic dimensions . language is a primary means by which people communicate, express identities and categorize themselves . unwanted gender biases can affect downstream applications, leading to poor user experiences .
Approach: They propose a framework that decomposes gender bias in text along several dimensions . they annotate eight large scale datasets with gender information and collect a benchmark .
Outcome: The proposed framework decomposes gender bias in text along several pragmatic and semantic dimensions.
Mitigating Gender Bias in Natural Language Processing: Literature Review (P19-1)

Copied to clipboard

Challenge: NLP models propagate and may even amplify gender bias found in text corpora . methods to mitigate gender bias in NLP are relatively nascent .
Approach: They propose to analyze gender bias based on four forms of representation bias and discuss the advantages and drawbacks of existing gender debiasing methods.
Outcome: The proposed methods are based on four forms of representation bias and have advantages and drawbacks.
Comparing Intrinsic Gender Bias Evaluation Measures without using Human Annotated Examples (2023.eacl-main)

Copied to clipboard

Challenge: Existing methods to evaluate gender biases in pre-trained language models have been limited by the cost and difficulties of recruiting human annotators.
Approach: They propose a method to compare intrinsic gender bias evaluation measures without relying on human annotated examples.
Outcome: The proposed method compares gender-based gender bias evaluation measures without human annotators without human input.
Blind Men and the Elephant: Diverse Perspectives on Gender Stereotypes in Benchmark Datasets (2025.emnlp-main)

Copied to clipboard

Challenge: Existing benchmarks for measuring gender stereotypical bias in language models are inconsistencies . lack of explicit standards in data gathering can have detrimental effects on results .
Approach: They propose that currently available benchmarks capture only partial facets of gender stereotypes . they apply a framework from social psychology to balance data across components of gender stereotypes based on stereotypical benchmarks.
Outcome: The proposed framework improves correlation between different benchmarks by using simple balancing techniques.
A Comparative Study of Explicit and Implicit Gender Biases in Large Language Models via Self-evaluation (2024.lrec-main)

Copied to clipboard

Challenge: Existing studies on the explicit and implicit biases in large language models (LLMs) focus on either explicit or implicit bias.
Approach: They propose a self-evaluation-based two-stage measurement of explicit and implicit biases within large language models grounded in social psychology.
Outcome: The proposed model is based on two stages of self-evaluation on state-of-the-art LLMs to measure explicit bias toward social targets, where bias is less likely to be self-recognized by the LLM.
Unsupervised Discovery of Gendered Language through Latent-Variable Modeling (P19-1)

Copied to clipboard

Challenge: a recent study has focused on the ways in which language is gendered . positive adjectives used to describe women are more often related to their bodies .
Approach: They propose a model that models adjective choice and its sentiment given the natural gender of a head noun.
Outcome: The proposed model shows that positive adjectives used to describe women are more often related to their bodies than positive adjective words used to explain men.
Identifying and Reducing Gender Bias in Word-Level Language Models (N19-3)

Copied to clipboard

Challenge: Existing discriminatory biases in training data can be amplified by models . text corpora exhibit socially problematic biase .
Approach: They propose a metric to measure gender bias and a regularization loss term to minimize embeddings onto an embeddable subspace that encodes gender.
Outcome: The proposed method reduces gender bias up to an optimal weight assigned to the loss term, and the model becomes unstable as the perplexity increases.
Pro-Woman, Anti-Man? Identifying Gender Bias in Stance Detection (2024.findings-acl)

Copied to clipboard

Challenge: Gender bias has been widely observed in NLP models, which can perpetuate harmful stereotypes and discrimination.
Approach: They construct a dataset to measure gender bias in stance detection using 36k samples . they find that all models are gender-biased and prone to classify sentences that contain male nouns as Against and those with female noun as Favor .
Outcome: The proposed dataset shows that all models are gender-biased and prone to classify sentences that contain male nouns as Against and those with female noun as Favor.
How Gender Debiasing Affects Internal Model Representations, and Why It Matters (2022.naacl-main)

Copied to clipboard

Challenge: Existing studies of gender bias in NLP focus on extrinsic or intrinsic bias, but the relationship between extrindic and intrinsic bias is relatively unknown.
Approach: They propose a framework to measure extrinsic and intrinsic bias together and propose metric to measure debiasing and intrinsic debiases.
Outcome: The proposed framework provides a comprehensive perspective on bias in NLP models, which can be applied to deploy NLP systems in a more informed manner.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations