Elucidating Mechanisms of Demographic Bias in LLMs for Healthcare

• URL: http://arxiv.org/abs/2502.13319v1
• Date: Tue, 18 Feb 2025 22:40:40 GMT
• Title: Elucidating Mechanisms of Demographic Bias in LLMs for Healthcare
• Authors: Hiba Ahsan, Arnab Sen Sharma, Silvio Amir, David Bau, Byron C. Wallace,
• Abstract summary: We find that gender information is highly localized in middle layers and can be reliably manipulated at inference time via patching.<n>We find that representation of patient race is somewhat more distributed, but can also be intervened upon, to a degree.
• Score: 38.0169924254127
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We know from prior work that LLMs encode social biases, and that this manifests in clinical tasks. In this work we adopt tools from mechanistic interpretability to unveil sociodemographic representations and biases within LLMs in the context of healthcare. Specifically, we ask: Can we identify activations within LLMs that encode sociodemographic information (e.g., gender, race)? We find that gender information is highly localized in middle MLP layers and can be reliably manipulated at inference time via patching. Such interventions can surgically alter generated clinical vignettes for specific conditions, and also influence downstream clinical predictions which correlate with gender, e.g., patient risk of depression. We find that representation of patient race is somewhat more distributed, but can also be intervened upon, to a degree. To our knowledge, this is the first application of mechanistic interpretability methods to LLMs for healthcare.

Related papers

• Gender Bias in Large Language Models for Healthcare: Assignment Consistency and Clinical Implications [16.066280458640676]
  The integration of large language models into healthcare holds promise to enhance clinical decision-making.<n>Gender has long influenced physician behaviors and patient outcomes.<n>Some models even displayed a systematic female-male disparity in their interpretation of patient gender.
  arXiv  Detail & Related papers  (2025-10-08T01:11:06Z)
• The MedPerturb Dataset: What Non-Content Perturbations Reveal About Human and Clinical LLM Decision Making [13.734312822024947]
  We introduce MedPerturb, a dataset designed to evaluate medical Large Language Models (LLMs) under controlled perturbations of clinical input.<n>With MedPerturb, we release a dataset of 800 clinical contexts grounded in realistic input variability.<n>We use MedPerturb in two case studies to reveal how shifts in gender identity cues, language style, or format reflect diverging treatment selections between humans and LLMs.
  arXiv  Detail & Related papers  (2025-06-20T17:09:27Z)
• Investigating LLMs in Clinical Triage: Promising Capabilities, Persistent Intersectional Biases [6.135648377533492]
  Large Language Models (LLMs) have shown promise in clinical decision support, yet their application to triage remains underexplored. We systematically investigate the capabilities of LLMs in emergency department triage through two key dimensions. We assess multiple LLM-based approaches, ranging from continued pre-training to in-context learning, as well as machine learning approaches.
  arXiv  Detail & Related papers  (2025-04-22T21:11:47Z)
• Explainable Depression Detection in Clinical Interviews with Personalized Retrieval-Augmented Generation [32.163466666512996]
  Depression is a widespread mental health disorder, and clinical interviews are the gold standard for assessment. Current systems mainly employ black-box neural networks, which lack interpretability. We propose RED, a Retrieval-augmented generation framework for Explainable depression Detection.
  arXiv  Detail & Related papers  (2025-03-03T08:59:34Z)
• Fact or Guesswork? Evaluating Large Language Model's Medical Knowledge with Structured One-Hop Judgment [108.55277188617035]
  Large language models (LLMs) have been widely adopted in various downstream task domains, but their ability to directly recall and apply factual medical knowledge remains under-explored. Most existing medical QA benchmarks assess complex reasoning or multi-hop inference, making it difficult to isolate LLMs' inherent medical knowledge from their reasoning capabilities. We introduce the Medical Knowledge Judgment, a dataset specifically designed to measure LLMs' one-hop factual medical knowledge.
  arXiv  Detail & Related papers  (2025-02-20T05:27:51Z)
• Enhancing Patient-Centric Communication: Leveraging LLMs to Simulate Patient Perspectives [19.462374723301792]
  Large Language Models (LLMs) have demonstrated impressive capabilities in role-playing scenarios.<n>By mimicking human behavior, LLMs can anticipate responses based on concrete demographic or professional profiles.<n>We evaluate the effectiveness of LLMs in simulating individuals with diverse backgrounds and analyze the consistency of these simulated behaviors.
  arXiv  Detail & Related papers  (2025-01-12T22:49:32Z)
• 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)
• Mitigating Hallucinations of Large Language Models in Medical Information Extraction via Contrastive Decoding [92.32881381717594]
  We introduce ALternate Contrastive Decoding (ALCD) to solve hallucination issues in medical information extraction tasks. ALCD demonstrates significant improvements in resolving hallucination issues compared to conventional decoding methods.
  arXiv  Detail & Related papers  (2024-10-21T07:19:19Z)
• Dr-LLaVA: Visual Instruction Tuning with Symbolic Clinical Grounding [53.629132242389716]
  Vision-Language Models (VLM) can support clinicians by analyzing medical images and engaging in natural language interactions. VLMs often exhibit "hallucinogenic" behavior, generating textual outputs not grounded in contextual multimodal information. We propose a new alignment algorithm that uses symbolic representations of clinical reasoning to ground VLMs in medical knowledge.
  arXiv  Detail & Related papers  (2024-05-29T23:19:28Z)
• Can AI Relate: Testing Large Language Model Response for Mental Health Support [23.97212082563385]
  Large language models (LLMs) are already being piloted for clinical use in hospital systems like NYU Langone, Dana-Farber and the NHS. We develop an evaluation framework for determining whether LLM response is a viable and ethical path forward for the automation of mental health treatment.
  arXiv  Detail & Related papers  (2024-05-20T13:42:27Z)
• Tokenization Matters: Navigating Data-Scarce Tokenization for Gender Inclusive Language Technologies [75.85462924188076]
  Gender-inclusive NLP research has documented the harmful limitations of gender binary-centric large language models (LLM) We find that misgendering is significantly influenced by Byte-Pair (BPE) tokenization. We propose two techniques: (1) pronoun tokenization parity, a method to enforce consistent tokenization across gendered pronouns, and (2) utilizing pre-existing LLM pronoun knowledge to improve neopronoun proficiency.
  arXiv  Detail & Related papers  (2023-12-19T01:28:46Z)
• A Survey of Large Language Models in Medicine: Progress, Application, and Challenge [85.09998659355038]
  Large language models (LLMs) have received substantial attention due to their capabilities for understanding and generating human language. This review aims to provide a detailed overview of the development and deployment of LLMs in medicine.
  arXiv  Detail & Related papers  (2023-11-09T02:55:58Z)
• Redefining Digital Health Interfaces with Large Language Models [69.02059202720073]
  Large Language Models (LLMs) have emerged as general-purpose models with the ability to process complex information. We show how LLMs can provide a novel interface between clinicians and digital technologies. We develop a new prognostic tool using automated machine learning.
  arXiv  Detail & Related papers  (2023-10-05T14:18:40Z)
• Don't Ignore Dual Logic Ability of LLMs while Privatizing: A Data-Intensive Analysis in Medical Domain [19.46334739319516]
  We study how the dual logic ability of LLMs is affected during the privatization process in the medical domain. Our results indicate that incorporating general domain dual logic data into LLMs not only enhances LLMs' dual logic ability but also improves their accuracy.
  arXiv  Detail & Related papers  (2023-09-08T08:20:46Z)
• Self-Verification Improves Few-Shot Clinical Information Extraction [73.6905567014859]
  Large language models (LLMs) have shown the potential to accelerate clinical curation via few-shot in-context learning. They still struggle with issues regarding accuracy and interpretability, especially in mission-critical domains such as health. Here, we explore a general mitigation framework using self-verification, which leverages the LLM to provide provenance for its own extraction and check its own outputs.
  arXiv  Detail & Related papers  (2023-05-30T22:05:11Z)

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.