Analysis Of Linguistic Stereotypes in Single and Multi-Agent Generative AI Architectures
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 strategi
Record details
Published: 19 March 2026
Source: arXiv
Category: Research
Topics: Bias & fairness · Agents & autonomy · Finance, VC & PE
Retrieved: 14 July 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
QoS-Aware Token Scheduling and Private Data Valuation for Multi-Modal Agentic Networks
arXiv · 2 April 2026
Aligned Agents, Biased Swarm: Measuring Bias Amplification in Multi-Agent Systems
arXiv · 10 April 2026
Static and Dynamic Strategies for Influencing Opinions in Social Networks
arXiv · 14 May 2026
Beyond Independent Manipulation: Individual Fairness-aware Strategic Classification with Peer Imitation
arXiv · 30 May 2026
Can Induced Emotion Bias LLM Behaviors in Sequential Decision Making?
arXiv cs.AI · 14 July 2026
Artificial intelligence and augmented intelligence collaboration: regaining trust and confidence in the financial sector
OpenAlex · 25 June 2018
How to cite this record
ethics.ai (19 March 2026), “Analysis Of Linguistic Stereotypes in Single and Multi-Agent Generative AI Architectures,” evidence record 7017, https://ethics.ai/record/7017 (originally published by arXiv).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.