# How Are LLMs Mitigating Stereotyping Harms? Learning from Search Engine Studies

arXiv: https://arxiv.org/abs/2407.11733 · HTML: https://mlsanity.com/paper/2407.11733/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 67 of its 113 references that are in the map.
- First posted on arXiv 16 Jul 2024.

## Builds on (most cited first, 30 of 67)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference](https://mlsanity.com/paper/1704.05426/) (2017)
- [HuggingFace's Transformers: State-of-the-art Natural Language Processing](https://mlsanity.com/paper/1910.03771/) (2019)
- [DeBERTa: Decoding-enhanced BERT with Disentangled Attention](https://mlsanity.com/paper/2006.03654/) (2020)
- [WebGPT: Browser-assisted question-answering with human feedback](https://mlsanity.com/paper/2112.09332/) (2021)
- [Multitask Prompted Training Enables Zero-Shot Task Generalization](https://mlsanity.com/paper/2110.08207/) (2021)
- [FEVER: a large-scale dataset for Fact Extraction and VERification](https://mlsanity.com/paper/1803.05355/) (2018)
- [RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models](https://mlsanity.com/paper/2009.11462/) (2020)
- [Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference](https://mlsanity.com/paper/2403.04132/) (2024)
- [A General Language Assistant as a Laboratory for Alignment](https://mlsanity.com/paper/2112.00861/) (2021)
- [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)
- [Semantics derived automatically from language corpora contain human-like biases](https://mlsanity.com/paper/1608.07187/) (2016)
- [Adversarial NLI: A New Benchmark for Natural Language Understanding](https://mlsanity.com/paper/1910.14599/) (2019)
- [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)
- [The Woman Worked as a Babysitter: On Biases in Language Generation](https://mlsanity.com/paper/1909.01326/) (2019)
- [Artificial Intelligence, Values and Alignment](https://mlsanity.com/paper/2001.09768/) (2020)
- [Asleep at the Keyboard? Assessing the Security of GitHub Copilot's Code Contributions](https://mlsanity.com/paper/2108.09293/) (2021)
- [BOLD: Dataset and Metrics for Measuring Biases in Open-Ended Language Generation](https://mlsanity.com/paper/2101.11718/) (2021)

## Built on by (most cited first, 10 of 10)

- [The Scales of Justitia: A Comprehensive Survey on Safety Evaluation of LLMs](https://mlsanity.com/paper/2506.11094/) (2025)
- [Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs)](https://mlsanity.com/paper/2505.21091/) (2025)
- [Pragmatic Inference Chain (PIC) Improving LLMs' Reasoning of Authentic Implicit Toxic Language](https://mlsanity.com/paper/2503.01539/) (2025)
- [How far can bias go? Tracing bias from pretraining data to alignment](https://mlsanity.com/paper/2411.19240/) (2024)
- [Model Misalignment and Language Change: Traces of AI-Associated Language in Unscripted Spoken English](https://mlsanity.com/paper/2508.00238/) (2025)
- [MHSafeEval: Role-Aware Interaction-Level Evaluation of Mental Health Safety in Large Language Models](https://mlsanity.com/paper/2604.17730/) (2026)
- [Evaluating Chinese Large Language Models: The Influence of Persona Assignment on Stereotypes and Safeguards](https://mlsanity.com/paper/2506.04975/) (2025)
- [Analyzing the Safety of Japanese Large Language Models in Stereotype-Triggering Prompts](https://mlsanity.com/paper/2503.01947/) (2025)
- [Measuring Stereotype and Deviation Biases in Large Language Models](https://mlsanity.com/paper/2508.06649/) (2025)
- [Personalisation or Prejudice? Addressing Geographic Bias in Hate Speech Detection using Debias Tuning in Large Language Models](https://mlsanity.com/paper/2505.02252/) (2025)

## Abstract (arXiv)

With the widespread availability of LLMs since the release of ChatGPT and increased public scrutiny, commercial model development appears to have focused their efforts on 'safety' training concerning legal liabilities at the expense of social impact evaluation. This mimics a similar trend which we could observe for search engine autocompletion some years prior. We draw on scholarship from NLP and search engine auditing and present a novel evaluation task in the style of autocompletion prompts to assess stereotyping in LLMs. We assess LLMs by using four metrics, namely refusal rates, toxicity, sentiment and regard, with and without safety system prompts. Our findings indicate an improvement to stereotyping outputs with the system prompt, but overall a lack of attention by LLMs under study to certain harms classified as toxic, particularly for prompts about peoples/ethnicities and sexual orientation. Mentions of intersectional identities trigger a disproportionate amount of stereotyping. Finally, we discuss the implications of these findings about stereotyping harms in light of the coming intermingling of LLMs and search and the choice of stereotyping mitigation policy to adopt. We address model builders, academics, NLP practitioners and policy makers, calling for accountability and awareness concerning stereotyping harms, be it for training data curation, leader board design and usage, or social impact measurement.