1 citations · 1 across the 4 of their papers we have counts for
3 papers · 1 filter
Affective Context Amplifies Sycophancy in LLM Responses
Jiayi Li, Sanjana Menon, Brett Frischmann +2
As conversational companions, large language models (LLMs) often have access to users' emotional states. We study how this affective context modulates LLM sycophancy in subjective,…
A Tale of Two Identities: An Ethical Audit of Human and AI-Crafted Personas
Pranav Narayanan Venkit, Jiayi Li, Yingfan Zhou +2
As LLMs (large language models) are increasingly used to generate synthetic personas particularly in data-limited domains such as health, privacy, and HCI, it becomes necessary to…
Can Third-parties Read Our Emotions?
Jiayi Li, Yingfan Zhou, Pranav Narayanan Venkit +4
Natural Language Processing tasks that aim to infer an author's private states, e.g., emotions and opinions, from their written text, typically rely on datasets annotated by third-…