Large language models (LLMs) are increasingly being adapted to achieve task-specificity for deployment in real-world decision systems. Several previous works have investigated the bias transfer hypothesis (BTH) by studying the effect of the fine-tuning adaptation strategy on model fairness to find that fairness in pre-trained masked language models have limited effect on the fairness of models when adapted using fine-tuning. In this work, we expand the study of BTH to causal models under prompt adaptations, as prompting is an accessible, and compute-efficient way to deploy models in real-world systems. In contrast to previous works, we establish that intrinsic biases in pre-trained Mistral, Falcon and Llama models are strongly correlated (rho >= 0.94) with biases when the same models are zero- and few-shot prompted, using a pronoun co-reference resolution task. Further, we find that bias transfer remains strongly correlated even when LLMs are specifically prompted to exhibit fair or biased behavior (rho >= 0.92), and few-shot length and stereotypical composition are varied (rho >= 0.97). Our findings highlight the importance of ensuring fairness in pre-trained LLMs, especially when they are later used to perform downstream tasks via prompt adaptation.

Artificial intelligence is getting a little smarter every day. Digital learning continues its expansion at all levels of education. Bots are designed to make our lives easier, more informative, and more interesting. Their machine learning capabilities make them a promising technology in education. The knowledge base of chatbots will only grow, and the bots themselves will be able to learn along with students.

While Artificial Intelligence and automation technologies is still nascent, the building blocks exist to suggest that Machine Learning could ease the burden of complex analysis, surface insights and trigger actions on behalf of managers. Workforce management is essentially the art and science of managing people in order to have a productive workforce. While there is a lot of science and methodology around this domain, with many current modern methods evolving from the foundational scientific management techniques propounded by Taylor over a century ago, it still requires the fine art of understanding an individual's capabilities and balancing human expectations to get the most out of people. Traditionally, in high empathy countries like India, this has largely been the responsibility of the manager, who balances an organisation's needs with individual wants and abilities. In short, the manager decides who needs to do what, when and where.