2 citations · 3 across the 4 of their papers we have counts for
4 papers
BenSyc: Benchmarking Conversational Sycophancy and Human Alignment in LLMs for Bengali Contexts
Kazi Noshin, Sajib Acharjee Dip, Ranat Das Prangon +4
Large language models (LLMs) increasingly participate in emotionally sensitive social conversations, where responses may shift from balanced support toward excessive validation or…
The Illusion of Agreement with ChatGPT: Sycophancy and Beyond
Kazi Noshin, Sharifa Sultana
While concerns about ChatGPT-induced harms due to sycophancy and other behaviors, including gaslighting, have grown among researchers, how users themselves experience and mitigate…
User Detection and Response Patterns of Sycophantic Behavior in Conversational AI
Kazi Noshin, Syed Ishtiaque Ahmed, Sharifa Sultana
Despite growing attention to LLM sycophancy from researchers and developers, users' own experiences of this behavior remain underexplored. We examine how everyday users experience…
Unmasking Parkinson's Disease with Smile: An AI-enabled Screening Framework
Tariq Adnan, Md Saiful Islam, Wasifur Rahman +6
We present an efficient and accessible PD screening method by leveraging AI-driven models enabled by the largest video dataset of facial expressions from 1,059 unique participants.…