Inthiswork, we focus on a classification problem and investigate the behavior of both noncalibrated and calibrated negativelog-likelihood (CNLL) ofadeep ensemble as a function of the ensemble size and the member network size.

It is widely acknowledged that large language models (LLMs) encode a vast reservoirofknowledge after being trained onmass data.

Annotateddimensionsinclude Valence, Arousal and Emotion label, with annotations gathered using Prolific.

Specifically, we train GPT-3, an autoregressive language model with 175 billion parameters, 10x more than any previous nonsparse language model, and test its performance in the few-shot setting. For all tasks, GPT-3 is applied without any gradient updates or fine-tuning, with tasks andfew-shot demonstrations specified purelyviatextinteraction withthemodel.