Donnerstag, 07. Dezember 2023, 16:45 - 18:15 iCal
Skipping Chit-chat with ChatGPT
Large Language Models and Structured Outputs
Invited talk by Ondrej Dusek (Charles University, Prague)
Hörsaal 1
Oskar-Morgenstern-Platz 1, 1090 Wien
Vortrag
Abstract: The current state of the art in text generation are large language models (LLMs) pretrained on vast amounts of text and finetuned to produce solutions given instructions. LLMs represent significant progress, allowing the user to request outputs for various tasks by stating a query in natural language and being able to follow examples provided by the user (in-context learning/prompting), without the need for further training (finetuning) on task-specific data. However, they retain some of the problems of the previous generation of language models, in particular their opacity and lack of controllability. This talk will show experiments on using LLMs with prompting only for multiple tasks: data-to-text generation, task-oriented dialogues, and dialogue evaluation. All these tasks operate with structure (structured data input, structured outputs, structured dialogue), which is not what these LLMs were specifically pretrained for. I show that LLMs are usable for these tasks, but also point out their limitations and potential areas of improvement.
Veranstalter
Kontakt
Lukas Thoma
Universität Wien
Forschungsgruppe Data Mining and Machine Learning
+43-1-4277-79501
lukas.thoma@univie.ac.at
Erstellt am Freitag, 01. Dezember 2023, 18:02
Letzte Änderung am Dienstag, 05. Dezember 2023, 09:23