Evolution of Language Models: From n-grams to ChatGPT – Jiří Materna

Language modelling (LM) is a well-known task that has been used in many natural language processing applications for decades. In this talk, we will delve into the technical details of various LM implementations, such as n-gram models, recurrent neural networks, and transformers. We will describe their strengths, weaknesses, and limitations. Special attention will be paid to generative language models that form the foundation of recently popular models such as ChatGPT, GPT4, LLaMA, and others. Finally, we will discuss a fine-tuning technique called Reinforcement Learning from Human Feedback (RLHF), which is a key ingredient in the process of making large language models more useful and aligned with human values.

Language: English

Program:
17:30 Welcome talk
18:00 Talk
18:45 Discussion
19:00 Networking

Machine Learning Meetups (MLMU) is an independent platform for people interested in Machine Learning, Information Retrieval, Natural Language Processing, Computer Vision, Pattern Recognition, Data Journalism, Artificial Intelligence, Agent Systems and all the related topics. MLMU is a regular community meeting usually consisting of a talk, a discussion and subsequent networking. Except for Prague, MLMU also spread to Brno, Bratislava and Košice.
http://www.mlmu.cz/