works on

From the 1 of 7 linked papers with an AI index.

activity
20242026
collaborators

7 papers

cs.CL2026

Misalignment Has a Personality: A Big Five Account of Emergent Misalignment

Hasibur Rahman, Smit Desai

The paper proposes that misalignment in fine‑tuned language models can be understood as shifts in Big Five personality traits, extracting calibrated personality vectors that predic…

cs.CL2026

Behavior-Adaptive Conversational Agents: Toward a Fluid Personality Framework

Hasibur Rahman, Smit Desai

Large language model (LLM)-based conversational agents (CAs) are now ubiquitous, creating new opportunities for AI-mediated behavior change. Their capacity to project nuanced perso…

cs.HC2026

Explanations as Dialogues: Toward Human-Centered Conversational Explainable AI

Niharika Mathur, Smit Desai

As AI systems become increasingly conversational, a gap emerges wherein explanations are studied as static artifacts, yet in practice, are experienced as dialogue. In this provocat…

cs.HC2026

The Differential Effects of Agreeableness and Extraversion on Older Adults' Perceptions of Conversational AI Explanations in Assistive Settings

Niharika Mathur, Hasibur Rahman, Smit Desai

Large Language Model-based Voice Assistants (LLM-VAs) are increasingly deployed in assistive settings for older adults, yet little is known about how an agent's personality shapes…

cs.HC2026

"Who wants to be nagged by AI?": Investigating the Effects of Agreeableness on Older Adults' Perception of LLM-Based Voice Assistants' Explanations

Niharika Mathur, Hasibur Rahman, Smit Desai

LLM-based voice assistants (VAs) increasingly support older adults aging in place, yet how an assistant's agreeableness shapes explanation perception remains underexplored. We cond…

cs.HC2025

Personas Evolved: Designing Ethical LLM-Based Conversational Agent Personalities

Smit Desai, Mateusz Dubiel, Nima Zargham +2

The emergence of Large Language Models (LLMs) has revolutionized Conversational User Interfaces (CUIs), enabling more dynamic, context-aware, and human-like interactions across div…