Towards WinoQueer: Developing a Benchmark for Anti-Queer Bias in Large Language Models

2022-06-23 · Virginia K. Felkner, Ho-Chun Herbert Chang, Eugene Jang, Jonathan May

This paper presents exploratory work on whether and to what extent biases against queer and trans people are encoded in large language models (LLMs) such as BERT. We also propose a method for reducing these biases in downstream tasks: finetuning the models on data written by and/or about queer people. To measure anti-queer bias, we introduce a new benchmark dataset, WinoQueer, modeled after other bias-detection benchmarks but addressing homophobic and transphobic biases. We found that BERT shows significant homophobic bias, but this bias can be mostly mitigated by finetuning BERT on a natural language corpus written by members of the LGBTQ+ community.

📄 PDF Abstract BibTeX arXiv:2206.11484

Code (0)

등록된 구현이 없습니다.

Tasks

Bias Detection

Methods 이 논문이 사용한 방법론

Attention 설명 없음

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Weight Decay 설명 없음

Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.

Residual Connection 설명 없음

Adam 설명 없음

Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…

WinoQueer: A Community-in-the-Loop Benchmark for Anti-LGBTQ+ Bias in Large Language Models

2023-06-26 · Virginia K. Felkner, Ho-Chun Herbert Chang, Eugene Jang, Jonathan May

We present WinoQueer: a benchmark specifically designed to measure whether large language models (LLMs) encode biases that are harmful to the LGBTQ+ community. The benchmark is community-sourced, via application of a nov…

PRIDE -- Parameter-Efficient Reduction of Identity Discrimination for Equality in LLMs

2025-07-18 · Maluna Menke, Thilo Hagendorff arxiv

Large Language Models (LLMs) frequently reproduce the gender- and sexual-identity prejudices embedded in their training corpora, leading to outputs that marginalize LGBTQIA+ users. Hence, reducing such biases is of great…

parameter-efficient fine-tuning

Filipino Benchmarks for Measuring Sexist and Homophobic Bias in Multilingual Language Models from Southeast Asia

2024-12-10 · Lance Calvin Lim Gamboa, Mark Lee

Bias studies on multilingual models confirm the presence of gender-related stereotypes in masked models processing languages with high NLP resources. We expand on this line of research by introducing Filipino CrowS-Pairs…

Detecting Stereotypes and Anti-stereotypes the Correct Way Using Social Psychological Underpinnings

2025-04-04 · Kaustubh Shivshankar Shejole, Pushpak Bhattacharyya

Stereotypes are known to be highly pernicious, making their detection critically important. However, current research predominantly focuses on detecting and evaluating stereotypical biases in LLMs, leaving the study of s…

Benchmarking

SLAyiNG: A Diverse and Community-validated Dataset of Queer Slang

2025-09-22 · Leonor Veloso, Lea Hirlimann, Philipp Wicke, Hinrich Schütze arxiv

Queer vernacular is rarely studied in NLP, despite advancements in resources and evaluation for other sociolects and informal language. Because of this, NLP systems often process queer language incorrectly, e.g., they mi…