social-bias

Official datasets and pytorch implementation repository of SQuARe and KoSBi (ACL 2023)

A library that implements fairness-aware machine learning algorithms

Must-read Papers on Gender Bias.

Official code and dataset repository of KoBBQ (TACL 2024)

Bias Benchmark for Natural Language Inference. Code repo for the Findings of NAACL 2022 paper "On Measuring Social Biases in Prompt-Based Multi-Task Learning".

[ICLR 2026] BiasFreeBench: a Benchmark for Mitigating Bias in Large Language Model Responses

A paper list for social bias in LLMs and VLMs.

This is the official repository containing all codes used to generate the results reported in the paper titled "Social Bias in Large Language Models For Bangla: An Empirical Study on Gender and Religious Bias"

[ICLR 2025] Revealing and Reducing Gender Biases in Vision and Language Assistants (VLAs)

Bias detection Toolkit: Chrome Extension, Python Package, SOTA research paper docs.

[ICLR 2026] Official codebase of "Person-Centric Annotations of LAION-400M: Auditing Bias and Its Transfer to Models"

Repository for "RoleConflictBench: A Benchmark of Role Conflict Scenarios for Evaluating LLMs' Contextual Sensitivity" (Findings of ACL 2026)

Systematic Review of the Demographic Representativeness of LLMs

[NeurIPS 2026] MultiBBQ: A Fairness Benchmark for Multimodal LLMs. 🏆 Best Paper Award in the ACL'26 TrustNLP Workshop.

Official EMNLP 2026 implementation of GGSS: inference-time demographic debiasing for generative VLMs/MLLMs via norm-preserving, token-level geodesic activation steering. No retraining.

Serverless API for token-level social-bias detection (generalisations, unfair language, stereotypes) with GUS-Net BERT. int8 ONNX on AWS Lambda (Graviton), API-key auth, Terraform, GitHub Actions with OIDC, and a Next.js site on CloudFront.

A sentiment analysis project using Twitter tweet data aimed at analysing the sentiment towards Ukrainian and Syrian refugees.

SSA is a counterfactual explanation approach to assess social bias in hate speech classifiers by stereotypes and counter-stereotypes

A sentiment analysis project using Twitter tweet data. Project aimed to analyse and compare sentiment attached to perceived weight stigma.

Code for the article "From hype to evidence: exploring large language models for inter-group bias classification in higher education"