News
Feedback on proposalsWritten on 11.07.23 by Sebastian Schuster Hi everyone, If you submitted a proposal, you should now be able to see my feedback on CMS (unless I already sent you feedback via email). Sebastian |
Paper deadline movedWritten on 06.07.23 by Sebastian Schuster Hi everyone, In case you were not in today's seminar: I moved the paper deadline to October 16, 2023, which hopefully gives you a bit more flexibility in planning your summer. And thank you for submitting the proposals. I will try to send you some comments by the end of this week. Lastly, if… Read more Hi everyone, In case you were not in today's seminar: I moved the paper deadline to October 16, 2023, which hopefully gives you a bit more flexibility in planning your summer. And thank you for submitting the proposals. I will try to send you some comments by the end of this week. Lastly, if you missed last week's seminar, please fill out the course evaluation before July 12. You can access it at this URL: https://qualis.uni-saarland.de/eva/?l=141331&p=tx5kns Best,
|
Reminder: Special date/time in Week 6Written on 08.05.23 (last change on 11.05.23) by Sebastian Schuster Hi everyone, Just a reminder that due to the public holiday and the cancelled sessions in July, we'll have the first special meeting for the seminar next week on Tuesday (May 16) 8:30-10:00 in Room -1.05. In order to give the presenters some time to read through/think about the comments, please… Read more Hi everyone, Just a reminder that due to the public holiday and the cancelled sessions in July, we'll have the first special meeting for the seminar next week on Tuesday (May 16) 8:30-10:00 in Room -1.05. In order to give the presenters some time to read through/think about the comments, please submit them by Monday, May 15 at noon instead of the usual midnight deadline. See you on Thursday! Sebastian |
Seminar: What do language models really understand?
Course Description: Large language models such as GPT-3 and ChatGPT have led to great advances in the field of natural language processing, and in many cases they provide responses to prompts that suggest that possess non-trivial abilities to understand language. At the same time, however, these models are primarily trained on text and have no explicit connection with the real world, whereas humans learn language by interacting with other humans and forming associations between words and phrases and entities and events in the world.
In this seminar, we will focus on the question to what extent large language models understand language. We’ll cover different philosophical schools of what it means to understand language, and then focus on a series of recent empirical papers that aim to evaluate different aspects of language understanding in models.
Course website: https://sebschu.com/lm-understanding-seminar/
Evaluation link: https://qualis.uni-saarland.de/eva/?l=141331&p=tx5kns