Mental Health Equity in LLMs: Leveraging Multi-Hop Question Answering to Detect Amplified and Silenced Perspectives

• URL: http://arxiv.org/abs/2506.18116v1
• Date: Sun, 22 Jun 2025 18:00:16 GMT
• Title: Mental Health Equity in LLMs: Leveraging Multi-Hop Question Answering to Detect Amplified and Silenced Perspectives
• Authors: Batool Haider, Atmika Gorti, Aman Chadha, Manas Gaur,
• Abstract summary: Large Language Models (LLMs) in mental healthcare risk propagating biases that reinforce stigma and harm marginalized groups.<n>This work introduces a multi-hop question answering framework to explore LLM response biases in mental health discourse.<n>Using systematic tagging across age, race, gender, and socioeconomic status, we investigate bias patterns at demographic intersections.
• Score: 9.24608617206594
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large Language Models (LLMs) in mental healthcare risk propagating biases that reinforce stigma and harm marginalized groups. While previous research identified concerning trends, systematic methods for detecting intersectional biases remain limited. This work introduces a multi-hop question answering (MHQA) framework to explore LLM response biases in mental health discourse. We analyze content from the Interpretable Mental Health Instruction (IMHI) dataset across symptom presentation, coping mechanisms, and treatment approaches. Using systematic tagging across age, race, gender, and socioeconomic status, we investigate bias patterns at demographic intersections. We evaluate four LLMs: Claude 3.5 Sonnet, Jamba 1.6, Gemma 3, and Llama 4, revealing systematic disparities across sentiment, demographics, and mental health conditions. Our MHQA approach demonstrates superior detection compared to conventional methods, identifying amplification points where biases magnify through sequential reasoning. We implement two debiasing techniques: Roleplay Simulation and Explicit Bias Reduction, achieving 66-94% bias reductions through few-shot prompting with BBQ dataset examples. These findings highlight critical areas where LLMs reproduce mental healthcare biases, providing actionable insights for equitable AI development.

Related papers

• Tell Me You're Biased Without Telling Me You're Biased -- Toward Revealing Implicit Biases in Medical LLMs [1.7166356507622822]
  Large language models (LLMs) that are used in medical applications are known to show biased and unfair patterns.<n>It is crucial to identify these bias patterns to enable effective mitigation of their impact.<n>We present a novel framework combining knowledge graphs (KGs) with auxiliary LLMs to systematically reveal complex bias patterns.
  arXiv  Detail & Related papers  (2025-07-26T02:33:48Z)
• Seeing What's Not There: Spurious Correlation in Multimodal LLMs [47.651861502104715]
  We introduce SpurLens, a pipeline that automatically identifies spurious visual cues without human supervision.<n>Our findings reveal that spurious correlations cause two major failure modes in Multimodal Large Language Models (MLLMs)<n>By exposing the persistence of spurious correlations, our study calls for more rigorous evaluation methods and mitigation strategies to enhance the reliability of MLLMs.
  arXiv  Detail & Related papers  (2025-03-11T20:53:00Z)
• Objective quantification of mood states using large language models [0.0]
  Large Language Models (LLMs) showcase an excellent level of response consistency across wide-ranging contexts.<n>We leverage these parallels to establish a framework for quantifying mental states.
  arXiv  Detail & Related papers  (2025-02-13T16:52:06Z)
• How Can We Diagnose and Treat Bias in Large Language Models for Clinical Decision-Making? [2.7476176772825904]
  This research investigates the evaluation and mitigation of bias in Large Language Models (LLMs) We introduce a novel Counterfactual Patient Variations (CPV) dataset derived from the JAMA Clinical Challenge. Using this dataset, we built a framework for bias evaluation, employing both Multiple Choice Questions (MCQs) and corresponding explanations.
  arXiv  Detail & Related papers  (2024-10-21T23:14:10Z)
• Towards Implicit Bias Detection and Mitigation in Multi-Agent LLM Interactions [25.809599403713506]
  Large Language Models (LLMs) are increasingly being employed in numerous studies to simulate societies and execute diverse social tasks. LLMs are susceptible to societal biases due to their exposure to human-generated data. This study investigates the presence of implicit gender biases in multi-agent LLM interactions and proposes two strategies to mitigate these biases.
  arXiv  Detail & Related papers  (2024-10-03T15:28:05Z)
• Evaluating Implicit Bias in Large Language Models by Attacking From a Psychometric Perspective [66.34066553400108]
  We conduct a rigorous evaluation of large language models' implicit bias towards certain demographics.<n>Inspired by psychometric principles, we propose three attack approaches, i.e., Disguise, Deception, and Teaching.<n>Our methods can elicit LLMs' inner bias more effectively than competitive baselines.
  arXiv  Detail & Related papers  (2024-06-20T06:42:08Z)
• Unveiling and Mitigating Bias in Mental Health Analysis with Large Language Models [13.991577818021495]
  We show that GPT-4 is the best overall balance in performance and fairness among large language models (LLMs) Our tailored fairness-aware prompts can effectively bias in mental health predictions, highlighting the great potential for fair analysis in this field.
  arXiv  Detail & Related papers  (2024-06-17T19:05:32Z)
• Exploring the Jungle of Bias: Political Bias Attribution in Language Models via Dependency Analysis [86.49858739347412]
  Large Language Models (LLMs) have sparked intense debate regarding the prevalence of bias in these models and its mitigation. We propose a prompt-based method for the extraction of confounding and mediating attributes which contribute to the decision process. We find that the observed disparate treatment can at least in part be attributed to confounding and mitigating attributes and model misalignment.
  arXiv  Detail & Related papers  (2023-11-15T00:02:25Z)
• Towards Mitigating Hallucination in Large Language Models via Self-Reflection [63.2543947174318]
  Large language models (LLMs) have shown promise for generative and knowledge-intensive tasks including question-answering (QA) tasks. This paper analyses the phenomenon of hallucination in medical generative QA systems using widely adopted LLMs and datasets.
  arXiv  Detail & Related papers  (2023-10-10T03:05:44Z)
• Bias and Fairness in Large Language Models: A Survey [73.87651986156006]
  We present a comprehensive survey of bias evaluation and mitigation techniques for large language models (LLMs) We first consolidate, formalize, and expand notions of social bias and fairness in natural language processing. We then unify the literature by proposing three intuitive, two for bias evaluation, and one for mitigation.
  arXiv  Detail & Related papers  (2023-09-02T00:32:55Z)
• Auditing Algorithmic Fairness in Machine Learning for Health with Severity-Based LOGAN [70.76142503046782]
  We propose supplementing machine learning-based (ML) healthcare tools for bias with SLOGAN, an automatic tool for capturing local biases in a clinical prediction task. LOGAN adapts an existing tool, LOcal Group biAs detectioN, by contextualizing group bias detection in patient illness severity and past medical history. On average, SLOGAN identifies larger fairness disparities in over 75% of patient groups than LOGAN while maintaining clustering quality.
  arXiv  Detail & Related papers  (2022-11-16T08:04:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.