Ref: https://huggingface.co/learn/nlp-course  Parallel compu…

Ref: https://huggingface.co/learn/nlp-course  Parallel computation is applicable for transformer model; therefore, it is easy to increase the size of the model with a larger corpus data. Language model (LM) and large language model (LLM) are mostly based on transformer model. LM is divided into three groups: encoder-only model, decoder-only model, and encoder-decoder model. For example, the Bidirectional Encoder Representations from Transformers (BERT) model can be used to generate embedding vectors from text data for text classification, because BERT is (1)__________________( a. encoder-only model, b. decoder-only model). For example, OpenAI’s ChatGPT is based on Generative Pre-trained Transformer (GPT) 4 and 4.5. GPT models are more suitable for text generation in diverse tasks, because GPT is a (2)__________________( a. encoder-only model, b. decoder-only model).

Bonus question (5 points) An economist wants to study the ef…

Bonus question (5 points) An economist wants to study the effect of sentiment in online product reviews for wine on the stock price of the wine firm using generative AI, natural language processing (NLP), deep learning, and econometrics. Before starting the research project, the economist asks a generative AI about prior literature related to the topics in a table format as follows: Ref: OpenAI. ChatGPT 4 . https://chat.openai.com; this is the true example based on the result in 2024. However, there is no such research yet; therefore, the generative AI provides non-existent literature reviews. We call this type of problem (1)__________ (a. overfitting, b. copyright issue, c. privacy issue, d. hallucination, e. computational resource constraints; 3 points). In addition, the dataset for pre-training of LLMs often relies on web data. Biases in web data can influence Gen AI (2) ___________ (a. True b. False; 2 points). Ref: Zhao, W. X., Zhou, K., Li, J., Tang, T., Wang, X., Hou, Y., … & Wen, J. R. (2023). A survey of large language models. arXiv preprint