# Navigating the Rabbit Hole: Emergent Biases in LLM-Generated Attack Narratives Targeting Mental Health Groups

arXiv: https://arxiv.org/abs/2504.06160 · HTML: https://mlsanity.com/paper/2504.06160/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 70 references that are in the map.
- First posted on arXiv 8 Apr 2025.

## Builds on (most cited first, 25 of 25)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [A Survey on Evaluation of Large Language Models](https://mlsanity.com/paper/2307.03109/) (2023)
- [Ethical and social risks of harm from Language Models](https://mlsanity.com/paper/2112.04359/) (2021)
- [Whose Opinions Do Language Models Reflect?](https://mlsanity.com/paper/2303.17548/) (2023)
- [Bias and Fairness in Large Language Models: A Survey](https://mlsanity.com/paper/2309.00770/) (2023)
- [From Louvain to Leiden: guaranteeing well-connected communities](https://mlsanity.com/paper/1810.08473/) (2018)
- [Language Models can Solve Computer Tasks](https://mlsanity.com/paper/2303.17491/) (2023)
- [Towards Understanding and Mitigating Social Biases in Language Models](https://mlsanity.com/paper/2106.13219/) (2021)
- [Can Large Language Models Transform Computational Social Science?](https://mlsanity.com/paper/2305.03514/) (2023)
- [Cultural Bias and Cultural Alignment of Large Language Models](https://mlsanity.com/paper/2311.14096/) (2023)
- [Large language models that replace human participants can harmfully misportray and flatten identity groups](https://mlsanity.com/paper/2402.01908/) (2024)
- [Evaluating the Social Impact of Generative AI Systems in Systems and Society](https://mlsanity.com/paper/2306.05949/) (2023)
- [Picking on the Same Person: Does Algorithmic Monoculture lead to Outcome Homogenization?](https://mlsanity.com/paper/2211.13972/) (2022)
- [Human-AI Collaboration Enables More Empathic Conversations in Text-based Peer-to-Peer Mental Health Support](https://mlsanity.com/paper/2203.15144/) (2022)
- [When Large Language Models contradict humans? Large Language Models' Sycophantic Behaviour](https://mlsanity.com/paper/2311.09410/) (2023)
- [Large Language Models Reflect the Ideology of their Creators](https://mlsanity.com/paper/2410.18417/) (2024)
- [Benefits and Harms of Large Language Models in Digital Mental Health](https://mlsanity.com/paper/2311.14693/) (2023)
- [The Capability of Large Language Models to Measure Psychiatric Functioning](https://mlsanity.com/paper/2308.01834/) (2023)
- [Automated Ableism: An Exploration of Explicit Disability Biases in Sentiment and Toxicity Analysis Models](https://mlsanity.com/paper/2307.09209/) (2023)
- [Do Large Language Models Align with Core Mental Health Counseling Competencies?](https://mlsanity.com/paper/2410.22446/) (2024)
- [Lived Experience Not Found: LLMs Struggle to Align with Experts on Addressing Adverse Drug Reactions from Psychiatric Medication Use](https://mlsanity.com/paper/2410.19155/) (2024)
- [Divine LLaMAs: Bias, Stereotypes, Stigmatization, and Emotion Representation of Religion in Large Language Models](https://mlsanity.com/paper/2407.06908/) (2024)
- [Words Matter: Reducing Stigma in Online Conversations about Substance Use with Large Language Models](https://mlsanity.com/paper/2408.07873/) (2024)
- [AI incidents and 'networked trouble': The case for a research agenda](https://mlsanity.com/paper/2403.07879/) (2024)

## Abstract (arXiv)

Large Language Models (LLMs) have been shown to demonstrate imbalanced biases against certain groups. However, the study of unprovoked targeted attacks by LLMs towards at-risk populations remains underexplored. Our paper presents three novel contributions: (1) the explicit evaluation of LLM-generated attacks on highly vulnerable mental health groups; (2) a network-based framework to study the propagation of relative biases; and (3) an assessment of the relative degree of stigmatization that emerges from these attacks. Our analysis of a recently released large-scale bias audit dataset reveals that mental health entities occupy central positions within attack narrative networks, as revealed by a significantly higher mean centrality of closeness (p-value = 4.06e-10) and dense clustering (Gini coefficient = 0.7). Drawing from an established stigmatization framework, our analysis indicates increased labeling components for mental health disorder-related targets relative to initial targets in generation chains. Taken together, these insights shed light on the structural predilections of large language models to heighten harmful discourse and highlight the need for suitable approaches for mitigation.