Intersectional Fairness in Large Language Models

arXiv:2604.20677 · cs.CL · Submitted 2026-04-22 · Read on arXiv

cs.CL

Submitted: 2026-04-22

Updated: 2026-09-12

Code: https://github.com/nyu-mll/crows-pairs

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Consistency — 52× in this paper · explained in 3 episodes
• Accuracy — 50× in this paper · explained in 1 episode
• Benchmark — 39× in this paper · explained in 2 episodes
• Machine Learning — 13× in this paper
• Alignment — 9× in this paper · explained in 1 episode
• Bias Benchmark for Question Answering — 5× in this paper
• Differential Fairness — 5× in this paper
• Abstention — 4× in this paper · explained in 1 episode
• Intersectionality — 4× in this paper · explained in 2 episodes
• Accountability — 3× in this paper · explained in 2 episodes
• Adam — 2× in this paper · explained in 2 episodes
• Adaptation — 2× in this paper · explained in 1 episode
• Ground-Truth Correctness — 2× in this paper
• Large Language Models (LLMs) — 2× in this paper · explained in 6 episodes
• Socio-Economic Status — 2× in this paper
• Sparsity — 2× in this paper · explained in 4 episodes
• Evaluation Dimensions — 1× in this paper · explained in 3 episodes
• Interpretability — 1× in this paper · explained in 15 episodes
• Most Frequent Answer Accuracy — 1× in this paper
• Multi-Agent Framework — 1× in this paper · explained in 3 episodes
• Perplexity — 1× in this paper · explained in 3 episodes
• Requirements Engineering Conference — 1× in this paper
• Robustness — 1× in this paper · explained in 5 episodes
• Statistical Parity Subgroup Fairness — 1× in this paper
• Verification — 1× in this paper · explained in 2 episodes

Sources

• Practitioner Insights on Fairness Requirements in the AI Development Life Cycle: An Interview Study
• Say It Another Way: Auditing LLMs with a User-Grounded Automated Paraphrasing Framework
• Mental Health Equity in LLMs: Leveraging Multi-Hop Question Answering to Detect Amplified and Silenced Perspectives
• Social Bias Evaluation for Large Language Models Requires Prompt Variations
• Social Bias Benchmark for Generation: A Comparison of Generation and QA-Based Evaluations
• A Survey on Fairness in Large Language Models
• Evaluating and Mitigating Social Bias for Large Language Models in Open-ended Settings
• BBQ-V: Benchmarking Visual Stereotype Bias in Large Multimodal Models
• BBQ: A Hand-Built Bias Benchmark for Question Answering
• Towards Systematic Specification and Verification of Fairness Requirements: A Position Paper
• BharatBBQ: A Multilingual Bias Benchmark for Question Answering in the Indian Context
• A Catalog of Fairness-Aware Practices in Machine Learning Engineering
• Is Your Model Fairly Certain? Uncertainty-Aware Fairness Evaluation for LLMs
• Does Reasoning Introduce Bias? A Study of Social Bias Evaluation and Mitigation in LLM Reasoning
• Rethinking Prompt-based Debiasing in Large Language Models
• Red teaming ChatGPT via Jailbreaking: Bias, Robustness, Reliability and Toxicity

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering