Author

M. Kamruzzaman

h-index 9 View on Semantic Scholar

We have 2 of 23 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Jul 2026

Token-Level Diagnosis of Sycophancy in LLMs with Attribution-Guided Steering

The ASI is introduced, an Integrated Gradients-based token attribution method, which measures the degree to which a model's decision is driven by authority-related text, and a attribution-guided contrastive activation steering method is proposed to mitigate LLM sycophancy.

H. Nguyen, M. Kamruzzaman, Anshuman Chhabra et al. · arXiv.org · 1 citation

Jul 2026

Demographic Prompting at Scale: When More Attributes Hurt LLM-Human Agreement

The results demonstrate that demographic prompting is not a monolithic intervention: its utility is highly context-dependent, shaped by attribute signal quality, task characteristics, and model architecture.

M. Kamruzzaman, Shrabony Das, Gene Louis Kim · arXiv.org · 0 citations