8 papers
Token-Level Diagnosis of Sycophancy in LLMs with Attribution-Guided Steering
Hieu Nguyen, Mahammed Kamruzzaman, Anshuman Chhabra +1
Sycophancy refers to the tendency for large language models (LLMs) to match user beliefs at the cost of factual correctness, thereby undermining model reliability. Prior work on ev…
Demographic Prompting at Scale: When More Attributes Hurt LLM--Human Agreement
Mahammed Kamruzzaman, Shrabon Kumar Das, Gene Louis Kim
We investigate how annotator demographic attributes, supplied as prompt cues, shape the alignment between large language model (LLM) predictions and human annotations across five t…
From Anger to Joy: How Nationality Personas Shape Emotion Attribution in Large Language Models
Mahammed Kamruzzaman, Abdullah Al Monsur, Gene Louis Kim +1
Emotions are a fundamental facet of human experience, varying across individuals, cultural contexts, and nationalities. Given the recent success of Large Language Models (LLMs) as…
Breaking the Benchmark: Revealing LLM Bias via Minimal Contextual Augmentation
Kaveh Eskandari Miandoab, Mahammed Kamruzzaman, Arshia Gharooni +3
Large Language Models have been shown to demonstrate stereotypical biases in their representations and behavior due to the discriminative nature of the data that they have been tra…
Prompting Techniques for Reducing Social Bias in LLMs through System 1 and System 2 Cognitive Processes
Mahammed Kamruzzaman, Gene Louis Kim
Dual process theory posits that human cognition arises via two systems. System 1, which is a quick, emotional, and intuitive process, which is subject to cognitive biases, and Syst…
The Impact of Disability Disclosure on Fairness and Bias in LLM-Driven Candidate Selection
Mahammed Kamruzzaman, Gene Louis Kim
As large language models (LLMs) become increasingly integrated into hiring processes, concerns about fairness have gained prominence. When applying for jobs, companies often reques…