Muhammad Umar Salman — accepted AI-conference papers

2025

Building Trust in Clinical LLMs: Bias Analysis and Dataset Transparency

Svetlana Maslenkova, Clement Christophe, Marco AF Pimentel, Tathagata Raha, Muhammad Umar Salman, Ahmed Al Mahrooqi +4

EMNLP 2025

Large language models offer transformative potential for healthcare, yet their responsible and equitable development depends critically on a deeper understanding of how training data characteristics influence model behavior, including the potential for bias. Current practices in dataset curation and

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2024

Beyond Fine-tuning: Unleashing the Potential of Continuous Pretraining for Clinical LLMs.

Clement Christophe, Tathagata Raha, Svetlana Maslenkova, Muhammad Umar Salman, Praveenkumar Kanithi, Marco AF Pimentel +1

EMNLP 2024finding

Large Language Models (LLMs) have demonstrated significant potential in revolutionizing clinical applications. In this study, we investigate the efficacy of four techniques in adapting LLMs for clinical use-cases: continuous pretraining, instruct fine-tuning, NEFTune, and prompt engineering. We empl…

Cited by 0 Source ↗PDF ↗Scholar ↗

2023

Detecting Propaganda Techniques in Code-Switched Social Media Text

Muhammad Umar Salman, Asif Hanif, Shady Shehata, Preslav Nakov

EMNLP 2023long main

Propaganda is a form of communication intended to influence the opinions and the mindset of the public to promote a particular agenda. With the rise of social media, propaganda has spread rapidly, leading to the need for automatic propaganda detection systems. Most work on propaganda detection has f…

Cited by 0 Source ↗code ↗Scholar ↗