VITAL: A New Dataset for Benchmarking Pluralistic Alignment in Healthcare

• URL: http://arxiv.org/abs/2502.13775v2
• Date: Sat, 31 May 2025 09:13:38 GMT
• Title: VITAL: A New Dataset for Benchmarking Pluralistic Alignment in Healthcare
• Authors: Anudeex Shetty, Amin Beheshti, Mark Dras, Usman Naseem,
• Abstract summary: Existing alignment paradigms fail to account for the diversity of perspectives across cultures, demographics, and communities.<n>This is particularly critical in health-related scenarios, where plurality is essential due to the influence of culture, religion, personal values, and conflicting opinions.<n>This work highlights the limitations of current approaches and lays the groundwork for developing health-specific alignment solutions.
• Score: 9.087074203425061
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Alignment techniques have become central to ensuring that Large Language Models (LLMs) generate outputs consistent with human values. However, existing alignment paradigms often model an averaged or monolithic preference, failing to account for the diversity of perspectives across cultures, demographics, and communities. This limitation is particularly critical in health-related scenarios, where plurality is essential due to the influence of culture, religion, personal values, and conflicting opinions. Despite progress in pluralistic alignment, no prior work has focused on health, likely due to the unavailability of publicly available datasets. To address this gap, we introduce VITAL, a new benchmark dataset comprising 13.1K value-laden situations and 5.4K multiple-choice questions focused on health, designed to assess and benchmark pluralistic alignment methodologies. Through extensive evaluation of eight LLMs of varying sizes, we demonstrate that existing pluralistic alignment techniques fall short in effectively accommodating diverse healthcare beliefs, underscoring the need for tailored AI alignment in specific domains. This work highlights the limitations of current approaches and lays the groundwork for developing health-specific alignment solutions.

Related papers

• Position: General Alignment Has Hit a Ceiling; Edge Alignment Must Be Taken Seriously [51.03213216886717]
  We take the position that the dominant paradigm of General Alignment reaches a structural ceiling in settings with conflicting values.<n>We introduce Edge Alignment as a distinct approach in which systems preserve multi dimensional value structure.
  arXiv  Detail & Related papers  (2026-02-23T16:51:43Z)
• Pluralistic Alignment for Healthcare: A Role-Driven Framework [14.636276754192219]
  We propose a first lightweight, generalizable, pluralistic alignment approach, EthosAgents, to simulate diverse perspectives and values.<n>We empirically show that it advances the pluralistic alignment for all three modes across seven varying-sized open and closed models.<n>Our findings reveal that health-related pluralism demands adaptable and normatively aware approaches, offering insights into how these models can better respect diversity in other high-stakes domains.
  arXiv  Detail & Related papers  (2025-09-12T20:28:27Z)
• mFARM: Towards Multi-Faceted Fairness Assessment based on HARMs in Clinical Decision Support [10.90604216960609]
  The deployment of Large Language Models (LLMs) in high-stakes medical settings poses a critical AI alignment challenge.<n>Existing fairness evaluation methods fall short in these contexts as they typically use simplistic metrics that overlook the multi-dimensional nature of medical harms.<n>We propose a multi-metric framework - Multi-faceted Fairness Assessment based on hARMs ($mFARM$) to audit fairness for three distinct dimensions of disparity.<n>Our findings showcase that the proposed $mFARM$ metrics capture subtle biases more effectively under various settings.
  arXiv  Detail & Related papers  (2025-09-02T06:47:57Z)
• MuSACo: Multimodal Subject-Specific Selection and Adaptation for Expression Recognition with Co-Training [52.99217736494484]
  We introduce MuSACo, a multi-modal subject-specific selection and adaptation method for personalized expression recognition.<n>This makes MuSACo relevant for affective computing applications in digital health, such as patient-specific assessment for stress or pain.<n>Our experimental results on challenging multimodal ER datasets: BioVid and StressID, show that MuSACo can outperform UDA (blending) and state-of-the-art MSDA methods.
  arXiv  Detail & Related papers  (2025-08-17T23:08:21Z)
• Alignment and Safety in Large Language Models: Safety Mechanisms, Training Paradigms, and Emerging Challenges [47.14342587731284]
  This survey provides a comprehensive overview of alignment techniques, training protocols, and empirical findings in large language models (LLMs) alignment.<n>We analyze the development of alignment methods across diverse paradigms, characterizing the fundamental trade-offs between core alignment objectives.<n>We discuss state-of-the-art techniques, including Direct Preference Optimization (DPO), Constitutional AI, brain-inspired methods, and alignment uncertainty quantification (AUQ)
  arXiv  Detail & Related papers  (2025-07-25T20:52:58Z)
• Towards Domain Specification of Embedding Models in Medicine [1.0713888959520208]
  We propose a comprehensive benchmark suite of 51 tasks spanning classification, clustering, pair classification, and retrieval modeled on the Massive Text Embedding Benchmark (MTEB)<n>Our results demonstrate that this combined approach establishes a robust evaluation framework and yields embeddings that consistently outperform state of the art alternatives in different tasks.
  arXiv  Detail & Related papers  (2025-07-25T16:15:00Z)
• Differential Privacy for Deep Learning in Medicine [3.9080478252129573]
  Differential privacy (DP) is a key technique for protecting sensitive patient data in medical deep learning (DL)<n>As clinical models grow more data-dependent, balancing privacy with utility and fairness has become a critical challenge.<n>This scoping review synthesizes recent developments in applying DP to medical DL.
  arXiv  Detail & Related papers  (2025-05-31T18:03:15Z)
• Bounded Rationality for LLMs: Satisficing Alignment at Inference-Time [52.230936493691985]
  We propose SITAlign, an inference framework that addresses the multifaceted nature of alignment by maximizing a primary objective while satisfying threshold-based constraints on secondary criteria.<n>We provide theoretical insights by deriving sub-optimality bounds of our satisficing based inference alignment approach.
  arXiv  Detail & Related papers  (2025-05-29T17:56:05Z)
• LlaMADRS: Prompting Large Language Models for Interview-Based Depression Assessment [75.44934940580112]
  This study introduces LlaMADRS, a novel framework leveraging open-source Large Language Models (LLMs) to automate depression severity assessment. We employ a zero-shot prompting strategy with carefully designed cues to guide the model in interpreting and scoring transcribed clinical interviews. Our approach, tested on 236 real-world interviews, demonstrates strong correlations with clinician assessments.
  arXiv  Detail & Related papers  (2025-01-07T08:49:04Z)
• MMIE: Massive Multimodal Interleaved Comprehension Benchmark for Large Vision-Language Models [71.36392373876505]
  We introduce MMIE, a large-scale benchmark for evaluating interleaved multimodal comprehension and generation in Large Vision-Language Models (LVLMs) MMIE comprises 20K meticulously curated multimodal queries, spanning 3 categories, 12 fields, and 102 subfields, including mathematics, coding, physics, literature, health, and arts. It supports both interleaved inputs and outputs, offering a mix of multiple-choice and open-ended question formats to evaluate diverse competencies.
  arXiv  Detail & Related papers  (2024-10-14T04:15:00Z)
• GMAI-MMBench: A Comprehensive Multimodal Evaluation Benchmark Towards General Medical AI [67.09501109871351]
  Large Vision-Language Models (LVLMs) are capable of handling diverse data types such as imaging, text, and physiological signals. GMAI-MMBench is the most comprehensive general medical AI benchmark with well-categorized data structure and multi-perceptual granularity to date. It is constructed from 284 datasets across 38 medical image modalities, 18 clinical-related tasks, 18 departments, and 4 perceptual granularities in a Visual Question Answering (VQA) format.
  arXiv  Detail & Related papers  (2024-08-06T17:59:21Z)
• ABC Align: Large Language Model Alignment for Safety & Accuracy [0.0]
  We present ABC Align, a novel alignment methodology for Large Language Models (LLMs) We combine a set of data and methods that build on recent breakthroughs in synthetic data generation, preference optimisation, and post-training model quantisation. Our unified approach mitigates bias and improves accuracy, while preserving reasoning capability, as measured against standard benchmarks.
  arXiv  Detail & Related papers  (2024-08-01T06:06:25Z)
• Trustworthy and Practical AI for Healthcare: A Guided Deferral System with Large Language Models [1.2281181385434294]
  Large language models (LLMs) offer a valuable technology for various applications in healthcare. Their tendency to hallucinate and the existing reliance on proprietary systems pose challenges in environments concerning critical decision-making. This paper presents a novel HAIC guided deferral system that can simultaneously parse medical reports for disorder classification, and defer uncertain predictions with intelligent guidance to humans.
  arXiv  Detail & Related papers  (2024-06-11T12:41:54Z)
• A Toolbox for Surfacing Health Equity Harms and Biases in Large Language Models [20.11590976578911]
  Large language models (LLMs) hold promise to serve complex health information needs but also have the potential to introduce harm and exacerbate health disparities. Reliably evaluating equity-related model failures is a critical step toward developing systems that promote health equity. We present resources and methodologies for surfacing biases with potential to precipitate equity-related harms in long-form, LLM-generated answers to medical questions.
  arXiv  Detail & Related papers  (2024-03-18T17:56:37Z)
• Controllable Preference Optimization: Toward Controllable Multi-Objective Alignment [103.12563033438715]
  Alignment in artificial intelligence pursues consistency between model responses and human preferences as well as values. Existing alignment techniques are mostly unidirectional, leading to suboptimal trade-offs and poor flexibility over various objectives. We introduce controllable preference optimization (CPO), which explicitly specifies preference scores for different objectives.
  arXiv  Detail & Related papers  (2024-02-29T12:12:30Z)
• Generalization in medical AI: a perspective on developing scalable models [3.003979691986621]
  Many prestigious journals now require reporting results both on the local hidden test set as well as on external datasets. This is because of the variability encountered in intended use and specificities across hospital cultures. We establish a hierarchical three-level scale system reflecting the generalization level of a medical AI algorithm.
  arXiv  Detail & Related papers  (2023-11-09T14:54:28Z)
• Robust Stance Detection: Understanding Public Perceptions in Social Media [15.460495567765362]
  stance detection identifies precise positions relative to a well-defined topic. Traditional stance detection models often lag in performance when applied to new domains and topics. A solution we present in this paper combines counterfactual data augmentation with contrastive learning to enhance the robustness of stance detection.
  arXiv  Detail & Related papers  (2023-09-26T18:19:51Z)
• Learnable Weight Initialization for Volumetric Medical Image Segmentation [66.3030435676252]
  We propose a learnable weight-based hybrid medical image segmentation approach. Our approach is easy to integrate into any hybrid model and requires no external training data. Experiments on multi-organ and lung cancer segmentation tasks demonstrate the effectiveness of our approach.
  arXiv  Detail & Related papers  (2023-06-15T17:55:05Z)
• Med-UniC: Unifying Cross-Lingual Medical Vision-Language Pre-Training by Diminishing Bias [38.26934474189853]
  Unifying Cross-Lingual Medical Vision-Language Pre-Training (Med-UniC) designed to integrate multimodal medical data from English and Spanish. Med-UniC reaches superior performance across 5 medical image tasks and 10 datasets encompassing over 30 diseases.
  arXiv  Detail & Related papers  (2023-05-31T14:28:19Z)
• Fairness meets Cross-Domain Learning: a new perspective on Models and Metrics [80.07271410743806]
  We study the relationship between cross-domain learning (CD) and model fairness. We introduce a benchmark on face and medical images spanning several demographic groups as well as classification and localization tasks. Our study covers 14 CD approaches alongside three state-of-the-art fairness algorithms and shows how the former can outperform the latter.
  arXiv  Detail & Related papers  (2023-03-25T09:34:05Z)
• Representational Ethical Model Calibration [0.7078141380481605]
  Epistem equity is the comparative fidelity of intelligence in decision-making. No general framework for its quantification, let alone assurance, exists. We introduce a comprehensive framework for Representational Ethical Model.
  arXiv  Detail & Related papers  (2022-07-25T10:33:39Z)

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.