Understanding Large Language Models
https://WebToolTip.com
2024 | English | ISBN: 9789180754705 | True PDF | 107 pages | 8 MB
Understanding Large Language Models: Towards Rigorous and Targeted Interpretability Using Probing Classifiers and Self-Rationalisation
Large language models (LLMs) have become the base of many natural language processing (NLP) systems due to their performance and easy adaptability to various tasks. However, much about their inner workings is still unknown. LLMs have many millions or billions of parameters, and large parts of their training happen in a self-supervised fashion: They simply learn to predict the next word, or missing words, in a sequence. This is effective for picking up a wide range of linguistic, factual and relational information, but it implies that it is not trivial what exactly is learned, and how it is represented within the LLM.