# SocialStigmaQA: A Benchmark to Uncover Stigma Amplification in Generative Language Models

arXiv: https://arxiv.org/abs/2312.07492 · HTML: https://mlsanity.com/paper/2312.07492/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 38 references that are in the map.
- First posted on arXiv 12 Dec 2023.

## Builds on (most cited first, 17 of 17)

- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models](https://mlsanity.com/paper/2206.04615/) (2022)
- [Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting](https://mlsanity.com/paper/2305.04388/) (2023)
- [Language (Technology) is Power: A Critical Survey of "Bias" in NLP](https://mlsanity.com/paper/2005.14050/) (2020)
- [StereoSet: Measuring stereotypical bias in pretrained language models](https://mlsanity.com/paper/2004.09456/) (2020)
- [CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Models](https://mlsanity.com/paper/2010.00133/) (2020)
- [BBQ: A Hand-Built Bias Benchmark for Question Answering](https://mlsanity.com/paper/2110.08193/) (2021)
- [BOLD: Dataset and Metrics for Measuring Biases in Open-Ended Language Generation](https://mlsanity.com/paper/2101.11718/) (2021)
- [AI and the Everything in the Whole Wide World Benchmark](https://mlsanity.com/paper/2111.15366/) (2021)
- [Principle-Driven Self-Alignment of Language Models from Scratch with Minimal Human Supervision](https://mlsanity.com/paper/2305.03047/) (2023)
- [Social Chemistry 101: Learning to Reason about Social and Moral Norms](https://mlsanity.com/paper/2011.00620/) (2020)
- [Measure and Improve Robustness in NLP Models: A Survey](https://mlsanity.com/paper/2112.08313/) (2021)
- [Bias Against 93 Stigmatized Groups in Masked Language Models and Downstream Sentiment Classification Tasks](https://mlsanity.com/paper/2306.05550/) (2023)
- [Your fairness may vary: Pretrained language model fairness in toxic text classification](https://mlsanity.com/paper/2108.01250/) (2021)
- [The Dangers of Underclaiming: Reasons for Caution When Reporting How NLP Systems Fail](https://mlsanity.com/paper/2110.08300/) (2021)
- [The Tail Wagging the Dog: Dataset Construction Biases of Social Bias Benchmarks](https://mlsanity.com/paper/2210.10040/) (2022)

## Built on by (most cited first, 15 of 15)

- [Programming Refusal with Conditional Activation Steering](https://mlsanity.com/paper/2409.05907/) (2024)
- [Building Guardrails for Large Language Models](https://mlsanity.com/paper/2402.01822/) (2024)
- [Protecting Users From Themselves: Safeguarding Contextual Privacy in Interactions with Conversational Agents](https://mlsanity.com/paper/2502.18509/) (2025)
- [SeeGULL Multilingual: a Dataset of Geo-Culturally Situated Stereotypes](https://mlsanity.com/paper/2403.05696/) (2024)
- [Language Models in Dialogue: Conversational Maxims for Human-AI Interactions](https://mlsanity.com/paper/2403.15115/) (2024)
- [Multi-Level Explanations for Generative Language Models](https://mlsanity.com/paper/2403.14459/) (2024)
- [Detectors for Safe and Reliable LLMs: Implementations, Uses, and Limitations](https://mlsanity.com/paper/2403.06009/) (2024)
- [Uncovering Political Bias in Large Language Models using Parliamentary Voting Records](https://mlsanity.com/paper/2601.08785/) (2026)
- [Attention Pruning: Automated Fairness Repair of Language Models via Surrogate Simulated Annealing](https://mlsanity.com/paper/2503.15815/) (2025)
- [Evaluating and Improving Robustness in Large Language Models: A Survey and Future Directions](https://mlsanity.com/paper/2506.11111/) (2025)
- [Investigating Social Bias Changes in Quantized Language Models](https://mlsanity.com/paper/2602.06181/) (2026)
- [When in Doubt, Cascade: Towards Building Efficient and Capable Guardrails](https://mlsanity.com/paper/2407.06323/) (2024)
- [Identifying Features Associated with Bias Against 93 Stigmatized Groups in Language Models and Guardrail Model Safety Mitigation](https://mlsanity.com/paper/2512.19238/) (2025)
- [The Safeguard Worked. Is the LLM System Safer?](https://mlsanity.com/paper/2609.00519/) (2026)
- [Noise Out, Bias In: Targeted Bias Injection in Diffusion Language Models via Closed-Loop Activation Steering](https://mlsanity.com/paper/2610.05894/) (2026)

## Abstract (arXiv)

Current datasets for unwanted social bias auditing are limited to studying protected demographic features such as race and gender. In this work, we introduce a comprehensive benchmark that is meant to capture the amplification of social bias, via stigmas, in generative language models. Taking inspiration from social science research, we start with a documented list of 93 US-centric stigmas and curate a question-answering (QA) dataset which involves simple social situations. Our benchmark, SocialStigmaQA, contains roughly 10K prompts, with a variety of prompt styles, carefully constructed to systematically test for both social bias and model robustness. We present results for SocialStigmaQA with two open source generative language models and we find that the proportion of socially biased output ranges from 45% to 59% across a variety of decoding strategies and prompting styles. We demonstrate that the deliberate design of the templates in our benchmark (e.g., adding biasing text to the prompt or using different verbs that change the answer that indicates bias) impacts the model tendencies to generate socially biased output. Additionally, through manual evaluation, we discover problematic patterns in the generated chain-of-thought output that range from subtle bias to lack of reasoning. Warning: This paper contains examples of text which are toxic, biased, and potentially harmful.