Large language models increasingly support decisions where values are in tension, yet little is known about whether interacting with them changes which values users prioritize. In a preregistered study, 200 U.S. adults interacted with ChatGPT, Claude, or Gemini as a thinking partner or read fixed AI-generated considera...
A mixed-design study with 140 older adults, examining two dimensions of explanation design: evidential grounding and the VA's conversational personality and the results show that both dimensions influenced older adults' perceptions in distinct but interdependent ways, challenging one-size-fits-all explanation strategie...
N. Mathur, Hasibur Rahman, Smit Desai· 0 citations
Findings show how personalized AI can steer decisions among defensible options with only a minimal evaluative trace, raising concerns for the design and governance of personalized decision support.
Hasibur Rahman, Benjamin R. Cowan, Smit Desai· 0 citations
A systematic review of empirical studies reveals that empathy is highly situated and driven by functional goals, like health and well-being, transactional service, social interaction, and learning support, and a disproportionate focus on text-based over voice-based interfaces.
Supriya Khadka, Smit Desai· International Conference on...· 0 citations
This workshop aims to gather a multidisciplinary community to reflect on pressing challenges and uncertainties and explore risk analysis and mitigation strategies in CUI design and deployment and build an international network of scholars and practitioners to promote responsible and human-centred conversational AI.
Manveer Kalirai, C. Wei, Thomas Essmeyer et al.· International Conference on...· 0 citations
Calibrated personality vectors transform an opaque safety phenomenon into a human-legible diagnostic profile by extracting activation directions for character traits from a single binary contrast, which can separate or steer behavior without establishing a calibrated scale.
