Analysis Of Linguistic Stereotypes in Single and Multi-Agent Generative AI Architectures
On the map: LLM agents and tool use → Social simulation and multi-agent debate
Abstract (arXiv)
Many works in the literature show that LLM outputs exhibit discriminatory behaviour, triggering stereotype-based inferences based on the dialect in which the inputs are written. This bias has been shown to be particularly pronounced when the same inputs are provided to LLMs in Standard American English (SAE) and African-American English (AAE). In this paper, we replicate existing analyses of dialect-sensitive stereotype generation in LLM outputs and investigate the effects of mitigation strategies, including prompt engineering (role-based and Chain-Of-Thought prompting) and multi-agent architectures composed of generate-critique-revise models. We define eight prompt templates to analyse different ways in which dialect bias can manifest, such as suggested names, jobs, and adjectives for SAE or AAE speakers. We use an LLM-as-judge approach to evaluate the bias in the results. Our results show that stereotype-bearing differences emerge between SAE- and AAE-related outputs across all template categories, with the strongest effects observed in adjective and job attribution. Baseline disparities vary substantially by model, with the largest SAE-AAE differential observed in Claude Haiku and the smallest in Phi-4 Mini. Chain-Of-Thought prompting proved to be an effective mitigation strategy for Claude Haiku, whereas the use of a multi-agent architecture ensured consistent mitigation across all the models. These findings suggest that for intersectionality-informed software engineering, fairness evaluation should include model-specific validation of mitigation strategies, and workflow-level controls (e.g., agentic architectures involving critique models) in high-impact LLM deployments. The current results are exploratory in nature and limited in scope, but can lead to extensions and replications by increasing the dataset size and applying the procedure to different languages or dialects.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Social simulation and multi-agent debate, one of 16 directions in LLM agents and tool use. Builds on 8 of its 20 references that are in the map. First posted on arXiv 19 Mar 2026.
Builds on
8 of 20 references.
References · 8
- 2020Language (Technology) is Power: A Critical Survey of "Bias" in NLPcited by 951
- 2016Semantics derived automatically from language corpora contain human-like biasescited by 894
- 2023Marked Personas: Using Natural Language Prompts to Measure Stereotypes in Language Modelscited by 204
- 2024Investigating Bias in LLM-Based Bias Detection: Disparities between LLMs and Human Perceptioncited by 55
- 2024Linguistic Bias in ChatGPT: Language Models Reinforce Dialect Discriminationcited by 55
- 2024Decoding Biases: Automated Methods and LLM Judges for Gender Bias Detection in Language Modelscited by 33
- 2024A Multi-LLM Debiasing Frameworkcited by 9
- 2025No LLM is Free From Bias: A Comprehensive Study of Bias Evaluation in Large Language Modelscited by 3
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025Assessing Agentic Large Language Models in Multilingual National Bias
- 2026Dialect vs Demographics: Quantifying LLM Bias from Implicit Linguistic Signals vs. Explicit User Profiles
- 2025MALIBU Benchmark: Multi-Agent LLM Implicit Bias Uncovered
- 2025Disparities in LLM Reasoning Accuracy and Explanations: A Case Study on African American English
- 2025Your AI Bosses Are Still Prejudiced: The Emergence of Stereotypes in LLM-Based Multi-Agent Systems
- 2025Actions Speak Louder than Words: Agent Decisions Reveal Implicit Biases in Language Models
- 2024Mitigating Bias in Queer Representation within Large Language Models: A Collaborative Agent Approach
- 2024Towards Implicit Bias Detection and Mitigation in Multi-Agent LLM Interactions