Large Language Models: What They Are, Why They Are
                         Important, and What They Fail At
                         Roberto Navigli1
                         1
                             Sapienza University of Rome, Italy


                                         Abstract
                                         The advent of Large Language Models (LLMs) like GPT-4 represents a significant leap forward in the field of
                                         Artificial Intelligence, offering unprecedented capabilities in understanding, generating, and interacting with
                                         human language. This talk aims to demystify these complex systems, explaining their fundamental architecture,
                                         how they are trained on vast datasets, and the underlying technologies that enable their sophisticated processing
                                         abilities. We will explore the importance of LLMs, highlighting their role in driving innovation, enhancing
                                         productivity, and opening new avenues for human-computer interaction. However, with great power comes
                                         great responsibility, and LLMs are not without their limitations and challenges. This presentation will critically
                                         examine the inherent weaknesses of LLMs, such as biases in training data, the potential for generating misleading
                                         information, and ethical concerns. We will delve into real-world examples to illustrate these failures, offering
                                         a balanced perspective on the capabilities and limitations of these models. Finally, I will overview ongoing
                                         research in my group aimed at mitigating these shortcomings, including extracting facts from generated text and
                                         interconnecting them to the source text.
                                         Disclaimer: 90% of this abstract was generated by GPT-4.




                          CILC 2024: 39th Italian Conference on Computational Logic, June 26-28, 2024, Rome, Italy
                          $ navigli@diag.uniroma1.it (R. Navigli)
                           0000-0003-3831-9706 (R. Navigli)
                                      © 2024 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).


CEUR
                  ceur-ws.org
Workshop      ISSN 1613-0073
Proceedings