# ROBBIE: Robust Bias Evaluation of Large Generative Language Models

arXiv: https://arxiv.org/abs/2311.18140 · HTML: https://mlsanity.com/paper/2311.18140/

## Key facts

- Cited by 53 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Nov 2023.

## Built on by (most cited first, 30 of 53)

- [A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment](https://mlsanity.com/paper/2504.15585/) (2025)
- [Representation Noising: A Defence Mechanism Against Harmful Finetuning](https://mlsanity.com/paper/2405.14577/) (2024)
- [Bias in Large Language Models: Origin, Evaluation, and Mitigation](https://mlsanity.com/paper/2411.10915/) (2024)
- [Embodied AI Agents: Modeling the World](https://mlsanity.com/paper/2506.22355/) (2025)
- [Fairness in Large Language Models: A Taxonomic Survey](https://mlsanity.com/paper/2404.01349/) (2024)
- [Beyond prompt brittleness: Evaluating the reliability and consistency of political worldviews in LLMs](https://mlsanity.com/paper/2402.17649/) (2024)
- [Gender, Race, and Intersectional Bias in Resume Screening via Language Model Retrieval](https://mlsanity.com/paper/2407.20371/) (2024)
- [Immunization against harmful fine-tuning attacks](https://mlsanity.com/paper/2402.16382/) (2024)
- [MBBQ: A Dataset for Cross-Lingual Comparison of Stereotypes in Generative LLMs](https://mlsanity.com/paper/2406.07243/) (2024)
- [Beyond Perplexity: Multi-dimensional Safety Evaluation of LLM Compression](https://mlsanity.com/paper/2407.04965/) (2024)
- [Toward Generalizable Evaluation in the LLM Era: A Survey Beyond Benchmarks](https://mlsanity.com/paper/2504.18838/) (2025)
- [Holistic Automated Red Teaming for Large Language Models through Top-Down Test Case Generation and Multi-turn Interaction](https://mlsanity.com/paper/2409.16783/) (2024)
- [Fairness and Bias in Multimodal AI: A Survey](https://mlsanity.com/paper/2406.19097/) (2024)
- [Fairness through Difference Awareness: Measuring Desired Group Discrimination in LLMs](https://mlsanity.com/paper/2502.01926/) (2025)
- [Look, Listen, and Answer: Overcoming Biases for Audio-Visual Question Answering](https://mlsanity.com/paper/2404.12020/) (2024)
- [Position: Towards Bidirectional Human-AI Alignment](https://mlsanity.com/paper/2406.09264/) (2024)
- [Raising the Bar: Investigating the Values of Large Language Models via Generative Evolving Testing](https://mlsanity.com/paper/2406.14230/) (2024)
- [Social Bias Benchmark for Generation: A Comparison of Generation and QA-Based Evaluations](https://mlsanity.com/paper/2503.06987/) (2025)
- [LLM Whisperer: An Inconspicuous Attack to Bias LLM Responses](https://mlsanity.com/paper/2406.04755/) (2024)
- [Ask LLMs Directly, "What shapes your bias?": Measuring Social Bias in Large Language Models](https://mlsanity.com/paper/2406.04064/) (2024)
- [BiasDora: Exploring Hidden Biased Associations in Vision-Language Models](https://mlsanity.com/paper/2407.02066/) (2024)
- [Subtle Biases Need Subtler Measures: Dual Metrics for Evaluating Representative and Affinity Bias in Large Language Models](https://mlsanity.com/paper/2405.14555/) (2024)
- [How Are LLMs Mitigating Stereotyping Harms? Learning from Search Engine Studies](https://mlsanity.com/paper/2407.11733/) (2024)
- [Evaluating and Mitigating Social Bias for Large Language Models in Open-ended Settings](https://mlsanity.com/paper/2412.06134/) (2024)
- [On Fairness of Low-Rank Adaptation of Large Models](https://mlsanity.com/paper/2405.17512/) (2024)
- [Are Large Language Models Really Bias-Free? Jailbreak Prompts for Assessing Adversarial Robustness to Bias Elicitation](https://mlsanity.com/paper/2407.08441/) (2024)
- [CatRAG: Functor-Guided Structural Debiasing with Retrieval Augmentation for Fair LLMs](https://mlsanity.com/paper/2603.21524/) (2026)
- [Unintended Harms of Value-Aligned LLMs: Psychological and Empirical Insights](https://mlsanity.com/paper/2506.06404/) (2025)
- [Underneath the Numbers: Quantitative and Qualitative Gender Fairness in LLMs for Depression Prediction](https://mlsanity.com/paper/2406.08183/) (2024)
- [B-score: Detecting biases in large language models using response history](https://mlsanity.com/paper/2505.18545/) (2025)

## Abstract (arXiv)

As generative large language models (LLMs) grow more performant and prevalent, we must develop comprehensive enough tools to measure and improve their fairness. Different prompt-based datasets can be used to measure social bias across multiple text domains and demographic axes, meaning that testing LLMs on more datasets can potentially help us characterize their biases more fully, and better ensure equal and equitable treatment of marginalized demographic groups. In this work, our focus is two-fold: (1) Benchmarking: a comparison of 6 different prompt-based bias and toxicity metrics across 12 demographic axes and 5 families of generative LLMs. Out of those 6 metrics, AdvPromptSet and HolisticBiasR are novel datasets proposed in the paper. The comparison of those benchmarks gives us insights about the bias and toxicity of the compared models. Therefore, we explore the frequency of demographic terms in common LLM pre-training corpora and how this may relate to model biases. (2) Mitigation: we conduct a comprehensive study of how well 3 bias/toxicity mitigation techniques perform across our suite of measurements. ROBBIE aims to provide insights for practitioners while deploying a model, emphasizing the need to not only measure potential harms, but also understand how they arise by characterizing the data, mitigate harms once found, and balance any trade-offs. We open-source our analysis code in hopes of encouraging broader measurements of bias in future LLMs.