ACM Talk - Dr Mehdi

ACM BPDC will be conducting its ACM Talk on Discovering Bias in Large Language Models (LLMs) in collaboration with the Computer Science Department on Saturday, 12th April 2025, at 7 PM online. This session will be led by Mehdi Bahrami, a Principal Researcher at Fujitsu, Santa Clara, CA, United States, who will provide valuable insights into Artificial Intelligence, Machine Learning, Natural Language Processing, Security & Privacy, and Data Science.

The rise of Large Language Models has revolutionized various industries, offering enhanced automation and performance benefits. However, these models are also prone to ethical challenges such as biases, stereotypes, misinformation, and hallucinations. Bahrami will discuss how these biases emerge, their real-world implications, and the increasing call for regulatory measures to ensure the responsible development and deployment of AI technologies.

This talk will explore methods for detecting and mitigating bias in LLMs, alongside strategies for promoting fairness and accountability in AI applications. Through theoretical insights and practical examples, attendees will gain a deeper understanding of ethical AI deployment. Open to all students and faculty, this session offers a valuable opportunity to engage in critical discussions on AI fairness, with certificates provided to all participants.