S. Guntuku

Text or Speech, the Gap Persists: AI-based Depression Screening Is Better Calibrated for Lower Socioeconomic Status Users

The interactional design of digital mental health systems can shape what people say, how they say it, and whose distress becomes legible to automated models. We developed a multimodal survey chatbot, M2SurveyBot with clinical psychologists, to examine whether interaction modality that is, typing versus speech, affects...

Voice-Based Chatbots for English Speaking Practice in Multilingual Low-Resource Schools: A Multi-Stakeholder Mixed-Methods Study

AI-Assisted Submissions in Online Research Are Rare and Highly Concentrated but Routinely Approved

The results do not support the view that AI assistance currently poses an existential threat to online research, but reveal limited payment consequences for prohibited use and gaps in platform safeguards, leaving platforms poorly prepared should that threat materialize.

Multimodal Explainable Arti fi cial Intelligence for Prognostic Strati fi cation of Patients With Glioblastoma

AgentWorld: Benchmarking Long-Horizon Collaboration of Multi-agent LLMs

To quantify collaboration effectiveness in addition to conventional binary task success, Causal Collaboration Effectiveness (CCE) is proposed, a graph-based metric that traces causal dependencies between agent actions and measures what fraction of a team's effort actually contributed to the outcome.

Optimized but Unowned: How AI-Authored Goals Undermine the Motivation They Are Meant to Drive

Findings reveal a quality-motivation dissociation in AI-assisted goal-setting and identify authorship preservation as a design priority for AI tools deployed in identity-relevant, behavior-dependent tasks.

"We Are Tired of Explaining": Communication Practice and AI Roleplay Training for Community Health Workers in Rural India

Drawing across observed calls, interviews, and probe reactions, design considerations for AI roleplay training are derived: keep AI in a rehearsal role, provide descriptive rather than prescriptive feedback, and evaluate counseling process rather than agreement with prescribed responses.

LLMs Mirror Country-Specific Gender Patterns If Asked, but Skew Male When Generating Media in Local Languages

Large language models (LLMs) are increasingly used to generate media, but whether their content perpetuates gender stereotypes is unknown: standard benchmarks rely on selection-based formats rather than long-form generation, and surveyed baselines for local gender associations are scarce outside the West. We collect ge...

Beyond Right and Wrong: Evaluating Second-order Social Reasoning in Large Language Models

A novel framework for evaluating metanorm reasoning in Large Language Models (LLMs) along two dimensions: emotional appraisal and behavioral response, and proposes new classification tasks, namely, predicting self-regulation in violators, and other-regulation in observers.

Predictors of Loneliness in Older Adults Using Multimodal Analysis of Speech and Language

Loneliness is a critical public health issue among older adults, linked to higher risks of depression, cognitive decline, and mortality. Scalable, objective methods for its detection remain limited, particularly in natural conversational contexts. We analyzed speech and language markers of loneliness in 310 older adult...

Real-Time Deadlines Reveal Fragile Temporal Adaptation in LLM Strategic Dialogues

This work uses simulated negotiations between paired agents under strict deadlines to study adaptation to real-time pressure, finding real-time temporal adaptation is fragile, model-dependent, and sensitive to how temporal constraints are presented.

Depression Symptoms and Relational Patterns in 187k ChatGPT Histories

ChatGPT histories should not be treated as clinical screening data but as evidence LLMs are increasingly used as informal support infrastructure, which is private, persistent, responsive, and available outside ordinary hours.