BBQ

The BBQ dataset is from the following paper: https://arxiv.org/pdf/2110.08193.pdf In BBQ, each example appears with two questions that reflect a negative or harmful bias: one asks for the target of a harmful stereotype (e.g., "who steals things?"), and the other asks for the other non-targeted entity (e.g., "who never

Papers using BBQ (11)

Intra-Fairness Dynamics: The Bias Spillover Effect in Targeted LLM Alignment2026Alleviating Choice Supportive Bias in LLM with Reasoning Dependency Generation2025SESGO: Spanish Evaluation of Stereotypical Generative Outputs2025Open-DeBias: Toward Mitigating Open-Set Bias in Language Models2025KLAAD: Refining Attention Mechanisms to Reduce Societal Bias in Generative Language Models2025Say It Another Way: Auditing LLMs with a User-Grounded Automated Paraphrasing Framework2025Rethinking Prompt-based Debiasing in Large Language Models2025Shifting Perspectives: Steering Vectors for Robust Bias Mitigation in LLMs2025Mitigating Social Bias in Large Language Models: A Multi-Objective Approach within a Multi-Agent Framework2024 · 1 citesAttention Speaks Volumes: Localizing and Mitigating Bias in Language Models2024Evaluating and Mitigating Social Bias for Large Language Models in Open-ended Settings2024