5 papers
HAL: Inducing Human-likeness in LLMs with Alignment
Masum Hasan, Junjie Zhao, Ehsan Hoque
Aligning language models to qualitative behavioral traits, such as human-likeness, remains difficult because they are hard to define, measure, and optimize. As a result, improvemen…
Harf-Speech: A Clinically Aligned Framework for Arabic Phoneme-Level Speech Assessment
Asif Azad, MD Sadik Hossain Shanto, Mohammad Sadat Hossain +6
Automated phoneme-level pronunciation assessment is vital for scalable speech therapy and language learning, yet validated tools for Arabic remain scarce. We present Harf-Speech, a…
Can LLMs Emulate Human Belief Dynamics?
Adiba Mahbub Proma, Neeley Pate, James N. Druckman +3
Can LLMs simulate how humans form and change beliefs in social networks? We put this to the test by replicating an established study on belief dynamics, evaluating 12 LLMs across m…
Personalized Large Language Models Can Increase the Belief Accuracy of Social Networks
Adiba Mahbub Proma, Neeley Pate, Sean Kelty +3
Large language models (LLMs) are increasingly involved in shaping public understanding on contested issues. This has led to substantial discussion about the potential of LLMs to re…
AI Standardized Patient Improves Human Conversations in Advanced Cancer Care
Kurtis Haut, Masum Hasan, Thomas Carroll +3
Serious illness communication (SIC) in end-of-life care faces challenges such as emotional stress, cultural barriers, and balancing hope with honesty. Despite its importance, one o…