no code implementations • 2 Apr 2024 • Zekun Wu, Sahan Bulathwela, Maria Perez-Ortiz, Adriano Soares Koshiyama
Recent advancements in Large Language Models (LLMs) have significantly increased their presence in human-facing Artificial Intelligence (AI) applications.
no code implementations • 13 Feb 2024 • Airlie Hilliard, Cristian Munoz, Zekun Wu, Adriano Soares Koshiyama
However, whereas LMs with fewer parameters exhibit similar behaviour in personality traits, newer and LMs with more parameters exhibit a broader range of personality traits, with increased agreeableness, emotional stability, and openness.
no code implementations • 23 Nov 2023 • Wu Zekun, Sahan Bulathwela, Adriano Soares Koshiyama
In summary, our work establishes a robust and practical framework for auditing and evaluating the stereotypic bias in LLM.
no code implementations • 4 Oct 2018 • Adriano Soares Koshiyama, Nick Firoozye, Philip Treleaven
Derivative traders are usually required to scan through hundreds, even thousands of possible trades on a daily basis.