568 citations · 582 across the 15 of their papers we have counts for
16 papers
Same Chart, Different Story: Bias in Vision-Language Chart Interpretation
Mizanur Rahman, Huan Wu, Arash Asgari +2
Vision-language models (VLMs) are increasingly used to interpret charts and generate natural-language explanations for socially consequential data. However, they may produce differ…
LLMs Silently Correct African American English: Auditing and Mitigating Dialect Bias via Activation Steering
Huan Wu, Ali Emami, Muhammad Furquan Hassan +5
African American English (AAE), a rule-governed dialect spoken by over 30 million people, is routinely misinterpreted and "corrected" by large language models (LLMs). Across six in…
Training Therapeutic Judges and Multi-Agent Systems for Human-Aligned Mental Health Support
Mizanur Rahman, Abeer Badawi, Elahe Rahimi +4
Large language models show promise for mental health support, yet therapeutic quality improves only when evaluation functions as an actionable control signal rather than a passive…
Towards Understanding and Measuring COGNITIVE ATROPHY in LLM Behaviour
Abeer Badawi, Moyosoreoluwa Olatosi, Negin Baghbanzadeh +5
Recent incidents involving LLMs used for mental-health support reveal a critical evaluation gap: surface-level safety scores do not capture how models behave across realistic, emot…
Algorithms Trained on Normal Chest X-rays Can Predict Health Insurance Types
Chi-Yu Chen, Rawan Abulibdeh, Arash Asgari +8
Artificial intelligence is revealing what medicine never intended to encode. Deep vision models, trained on chest X-rays, can now detect not only disease but also invisible traces…
We Politely Insist: Your LLM Must Learn the Persian Art of Taarof
Nikta Gohari Sadr, Sahar Heidariasl, Karine Megerdoomian +2
Large language models (LLMs) struggle to navigate culturally specific communication norms, limiting their effectiveness in global contexts. We focus on Persian taarof, a social nor…