|
Event Knowledge in Textual and Multimodal Large Language Modelstitle | Event Knowledge in Textual and Multimodal Large Language Models |
---|
start_date | 2023/10/10 |
---|
schedule | 13h |
---|
online | yes |
---|
visio | https://ucl.zoom.us/j/97789056031?pwd=TVU3aEw4cFpLcnRMV1VGN0p5Wm91UT09 |
---|
location_info | Room B01 & on Zoom |
---|
summary | The ability of Large Language Models (LLMs) to achieve impressive performances in natural language processing tasks derives from the large amounts of knowledge they recover from distributional statistics in huge textual corpora. However, the precise type, breadth and reliability of this knowledge is still an open issue. In this talk, I will present ongoing research that aims at testing the knowledge of events and their participants in LLMs. Besides textual ones, multimodal LLMs are also investigated, to estimate the contribution of the knowledge extracted from images. |
---|
responsibles | Esposito |
---|
Workflow historyfrom state (1) | to state | comment | date |
submitted | published | | 2023/10/04 14:01 UTC |
| |
|