Topic models have been evolving rapidly over the years, from conventional to recent neural models.

Among all the contributing factors, the quality and selection of data is becoming increasingly recognized for its importance in training LLMs effectively.

While tabular classification has traditionally relied on from-scratch training, a recent breakthrough called prior-data fitted networks (PFNs) challenges this approach. Similar to large language models, PFNs make use of pretraining and in-context learning to achieve strong performance on new tasks in a single forward pass.

To address issues of group-level fairness in machine learning, it is natural to adjust model parameters based on specific fairness objectives over a sensitive-attributed validation set.