Vasudha Varadarajan
  • Bio
  • Publications
  • Awards
  • Experience
  • Talks
  • Media
  • Teaching and Mentoring
  • Publications
    • Explaining GPTs' schema of depression: A machine behavior analysis.
    • CCBENCH: Assessing LLM Cultural Competence via Implicitly Signaled Norms using Health Queries
    • Evaluating Document-Tuned Transformer Representations for Person-level Mental Health Assessment
    • Examining the Utility of Self-disclosure Types for Modeling Annotators of Social Norms
    • Explaining GPTs’ schema of depression: A machine behavior analysis.
    • From Word Sequences to Behavioral Sequences: Adapting Modeling and Evaluation Paradigms for Longitudinal NLP
    • Lost in Delusion: Examining LLM Safety Under User Delusions and Distress
    • McMasters of Change: Predicting Well-Being States and Transitions from Longitudinal Language
    • Measuring resilience using language modeling: A computational approach to observing resilience
    • Proceedings of the 10th Workshop on Computational Linguistics and Clinical Psychology (CLPsych 2026)
    • SOTOPIA-TOM: Evaluating Information Management in Multi-Agent Interaction with Theory of Mind
    • When Should AI Read the Room? Public Perceptions of Social Intelligence in AI Agents
    • Capturing Human Cognitive Styles with Language: Towards an Experimental Evaluation Paradigm
    • Critical or Compliant? The Double-Edged Sword of Reasoning in Chain-of-Thought Explanations
    • ISCA: A Framework for Interview-Style Conversational Agents
    • Linking Language-based Distortion Detection to Mental Health Outcomes
    • MAQuA: Adaptive Question-Asking for Multidimensional Mental Health Screening using Item Response Theory
    • Systematic Evaluation of Auto-Encoding and Large Language Model Representations for Capturing Author States and Traits
    • The Consistent Lack of Variance of Psychological Factors Expressed by LLMs and Spambots
    • Towards Truer Scores of Mental States: Computational Linguistics for Psychological Measurement
    • Unifying the Extremes: Developing a Unified Model for Detecting and Predicting Extremist Traits and Radicalization
    • Who We Are, Where We Are: Mental Health at the Intersection of Person, Situation, and Large Language Models
    • ALBA: Adaptive Language-Based Assessments for Mental Health
    • Archetypes and Entropy: Theory-Driven Extraction of Evidence for Suicide Risk
    • From Text to Context: Contextualizing Language with Humans, Groups, and Communities for Socially Aware NLP
    • \" I Slept Like a Baby\": Using Human Traits To Characterize Deceptive ChatGPT and Human Text.
    • ALBA: Adaptive Language-Based Assessments for Mental Health
    • Discourse-level representations can improve prediction of degree of anxiety
    • Transfer and active learning for dissonance detection: Addressing the rare-class challenge
    • Detecting dissonant stance in social media: The role of topic exposure
    • Discourse Relation Embeddings: Representing the Relations between Discourse Segments in Social Media
    • WWBP-SQT-lite: Multi-level models and difference embeddings for moments of change identification in mental health forums
    • Discourse relation embeddings: Representing the relations between discourse segments in social media
    • V-formation via model predictive control
  • Media
    • National High School Journal of Science (NHSJS) on Authorship and Originality in the Age of AI
    • AI Innovation Institute covers our work on AI vs human-generated text.
    • Stony Brook Medicine covers our Study on Distinguishing between Human and AI-Generated Content
  • Blog
    • High School Research Mentorship
    • Research Mentorship
    • Reviewing for NLP and CSS conferences.
    • Scientist-in-Residence Program (SiR) with New York Academy of Sciences
    • 1000 Girls, 1000 Futures
  • Recent & Upcoming Talks
    • Talk @ CRA Grad Cohort, Denver 2025 on Capturing Human Cognitive Styles with Language
    • Invited Talk @ The Alan Turing Institute on Adaptive Language-Based Assessments
    • Tutorial @ NAACL 2024: From Text to Context:Contextualizing Language with Humans, Groups, and Communities for Socially Aware NLP
    • Talk @ ACL 2023 Best Paper Awards on transfer and active learning for dissonance detection
    • Talk @ DARPA Forward, Fort Collins 2022 on detecting dissonance on social media
  • Projects
    • Projects
    • Pandas
    • PyTorch
    • scikit-learn
  • Awards
  • Experience
  • Teaching
    • Learn JavaScript
    • Learn Python

CCBENCH: Assessing LLM Cultural Competence via Implicitly Signaled Norms using Health Queries

Jan 1, 2026·
Vasudha Varadarajan
,
Akhila Yerukola
,
Mona T Diab
,
Maarten Sap
· 0 min read
Cite URL
Type
Journal article
Publication
COLM
Last updated on Jan 1, 2026
← Explaining GPTs' schema of depression: A machine behavior analysis. Aug 1, 2026
Evaluating Document-Tuned Transformer Representations for Person-level Mental Health Assessment Jan 1, 2026 →

© 2026 Vasudha Varadarajan. This work is licensed under CC BY NC ND 4.0

Published with Hugo Blox Builder — the free, open source website builder that empowers creators.