24 citations · 81 across the 44 of their papers we have counts for
48 papers
AI-Assisted Submissions in Online Research Are Rare and Highly Concentrated but Routinely Approved
Neil K. R. Sehgal, Manuel Tonneau, Dunigan Folk +2
Online research platforms underpin much of what science claims about people, on the assumption that a human produced each response. Generative AI threatens that assumption by letti…
AgentWorld: Benchmarking Long-Horizon Collaboration of Multi-agent LLMs
Raphael Shu, Yusen Zhang, Young Min Cho +7
Existing multi-agent benchmarks primarily test in competitive settings, short-horizon interactions under 20 steps, or simply aggregate individual performance, failing to isolate an…
PersonaMem-v3: Toward Omni-Platform Personal Intelligence for Holistic User Understanding, Recommendation, and Agentic Tasks
Bowen Jiang, Yuan Yuan, Zhuoqun Hao +12
Personal intelligence is becoming a central frontier for user-facing AI agents. To be helpful in everyday life, agents must understand users across the digital contexts where their…
Depression Symptoms and Relational Patterns in 187k ChatGPT Histories
Neil K. R. Sehgal, Dunigan Folk, Lyle Ungar +1
Large language models are increasingly used as private, always-available conversational systems, but little is known about how people with depressive symptoms use them. Building on…
Narrative Sharpens Gender Gaps: Surveying Film Characters with LLM Agents
Vivienne Bihe Chi, Reyhan Jamalova, Lyle Ungar +1
Mainstream film is one of the richest sources of cultural content that AI systems learn from. Yet we have few tools for measuring the gender values it encodes. We present a proof-o…
What Users Cannot See: Evaluating LLM Emotional Support Beyond User Preference
Vivienne Bihe Chi, Adithya V Ganesan, Ryan L Boyd +2
People increasingly turn to LLMs for emotional support, yet common evaluations reward responses that feel helpful and may miss consequential response behaviors. We introduce a theo…
Contrastive Conceptor Activation Steering (COAST): Unlocking Vision-Language-Action Models through Hidden States
Miranda Muqing Miao, Subin Kim, Brandon Yang +1
Vision-Language-Action (VLA) models leverage powerful perceptual priors from web-scale Vision-Language Model (VLM) pre-training, yet they remain surprisingly brittle in practice, f…
Optimized but Unowned: How AI-Authored Goals Undermine the Motivation They Are Meant to Drive
Vivienne Bihe Chi, Roman Rietsche, Andreas Göldi +2
As AI tools become embedded in productivity and self-improvement contexts, a pressing question emerges: what happens when AI does the goal-setting for us? In a preregistered experi…
Conceptors for Semantic Steering
Ilias Triantafyllopoulos, Young-Min Cho, Ren Tao +6
Activation-based steering provides control of LLM behavior at inference time, but the dominant paradigm reduces each concept to a single direction whose geometry is left largely un…
Closing the Confidence-Faithfulness Gap in Large Language Models
Miranda Muqing Miao, Lyle Ungar
Large language models (LLMs) tend to verbalize confidence scores that are largely detached from their actual accuracy, yet the geometric relationship governing this behavior remain…
Voice-Based Chatbots for English Speaking Practice in Multilingual Low-Resource Indian Schools: A Multi-Stakeholder Study
Sneha Shashidhara, Vivienne Bihe Chi, Abhay P Singh +2
Spoken English proficiency is a powerful driver of economic mobility for low-income Indian youth, yet opportunities for spoken practice remain scarce in schools. We investigate the…
A Concise Agent is Less Expert: Revealing Side Effects of Using Style Features on Conversational Agents
Young-Min Cho, Yuan Yuan, Sharath Chandra Guntuku +1
Style features such as friendly, helpful, or concise are widely used in prompts to steer the behavior of Large Language Model (LLM) conversational agents, yet their unintended side…
Real-Time Deadlines Reveal Fragile Temporal Adaptation in LLM Strategic Dialogues
Neil K. R. Sehgal, Sharath Chandra Guntuku, Lyle Ungar
Large Language Models (LLMs) generate text token-by-token in discrete time, yet real-world communication, from therapy sessions to business negotiations, critically depends on cont…
PersonaMem-v2: Towards Personalized Intelligence via Learning Implicit User Personas and Agentic Memory
Bowen Jiang, Yuan Yuan, Maohao Shen +13
Personalization is one of the next milestones in advancing AI capability and alignment. We introduce PersonaMem-v2, the state-of-the-art dataset for LLM personalization that simula…
T-FIX: Text-Based Explanations with Features Interpretable to eXperts
Shreya Havaldar, Weiqiu You, Chaehyeon Kim +12
As LLMs are deployed in knowledge-intensive settings (e.g., surgery, astronomy, therapy), users are often domain experts who expect not just answers, but explanations that mirror p…
Culturally-Aware Conversations: A Framework & Benchmark for LLMs
Shreya Havaldar, Sunny Rai, Young-Min Cho +1
Existing benchmarks that measure cultural adaptation in LLMs are misaligned with the actual challenges these models face when interacting with users from diverse cultural backgroun…
Does Object Binding Naturally Emerge in Large Pretrained Vision Transformers?
Yihao Li, Saeed Salehi, Lyle Ungar +1
Object binding, the brain's ability to bind the many features that collectively represent an object into a coherent whole, is central to human cognition. It groups low-level percep…
Beyond the Strongest LLM: Multi-Turn Multi-Agent Orchestration vs. Single LLMs on Benchmarks
Aaron Xuxiang Tian, Ruofan Zhang, Jiayao Tang +12
We study multi-turn multi-agent orchestration, where multiple large language model (LLM) agents interact over multiple turns by iteratively proposing answers or casting votes until…
Effects of Static and Conversational AI-Generated Messages on Colorectal Cancer Screening Intent: a Randomized Clinical Trial
Neil K. R. Sehgal, Manuel Tonneau, Andy SL Tan +6
Large language model chatbots show increasing promise in persuasive communication, but their clinical utility remains uncertain, particularly in settings where sustained conversati…
PAL: Designing Conversational Agents as Scalable, Cooperative Patient Simulators for Palliative-Care Training
Neil K. R. Sehgal, Hita Kambhamettu, Allen Chang +3
Effective communication in serious illness and palliative care is essential but often under-taught due to limited access to training resources like standardized patients. We presen…
The Impact of Language Mixing on Bilingual LLM Reasoning
Yihao Li, Jiayi Xin, Miranda Muqing Miao +2
Proficient multilingual speakers often intentionally switch languages in the middle of a conversation. Similarly, recent reasoning-focused bilingual large language models (LLMs) wi…
Herd Behavior: Investigating Peer Influence in LLM-based Multi-Agent Systems
Young-Min Cho, Sharath Chandra Guntuku, Lyle Ungar
Recent advancements in Large Language Models (LLMs) have enabled the emergence of multi-agent systems where LLMs interact, collaborate, and make decisions in shared environments. W…
ZeroTuning: Unlocking the Initial Token's Power to Enhance Large Language Models Without Training
Feijiang Han, Xiaodong Yu, Jianheng Tang +3
Token-level attention tuning, a class of training-free methods including Post-hoc Attention Steering (PASTA) and Attention Calibration (ACT), has emerged as a promising approach fo…
Large Language Model Chatbot Conversations vs Public Health Materials and Parental HPV Vaccination Intentions: A Randomized Clinical Trial
Neil K. R. Sehgal, Sunny Rai, Manuel Tonneau +6
Health care systems are increasingly considering large language model (LLM)-based chatbots for vaccine communication, but evidence that they improve durable, behaviorally relevant…