This paper provides an introductory survey to the generative principle test-based inference (gpt-3).
We survey both academic and commercial efforts applying this technology in diverse domains such as developing conversational ai chatbots, software development, creative work, domain knowledge, and business productivity.
This study teaches a large-scale natural language model to classify whether a question is related to data science by augmenting a small training set with additional training examples generated by the model itself.
We compare two classifiers : the classification endpoint with augmented examples, and the classification endpoint with an optimal training set chosen using a genetic algorithm.
We study the decision-making, information search, deliberation, and causal reasoning abilities of a recent large language model, using tools from cognitive psychology.
We find that much of the model s behavior is impressive : it solves vignette-based tasks similarly or better than human subjects, is able to make decent decisions from descriptions, outperforms humans in a multi-armed bandit task, and shows signatures of model-based reinforcement learning.
We present the first systematic and comprehensive study to compare the few-shot performance of the pre-trained language model (plm) gpt-3 in-context learning with fine-tuning smaller (i.e.,bert-sized) pre-trained language models on two highly representative biomedical information extraction tasks, named entity recognition and relation extraction.
Our results show that gpt-3 still significantly underperforms compared with simply fine-tuning a smaller plm using the same small training set.
Artificial intelligence is changing the way we create and evaluate information, and this is happening during an infodemic, which has been having dramatic effects on global health.
In this paper we evaluate whether recruited individuals can distinguish disinformation from accurate information,structured in the form of tweets, and determine whether a tweet is organic or synthetic, i.e., whether it has been written by a twitter user or by the artificial intelligence model gpt-3.