It is shown that measured performance and reliability depend on the requested format (JSON, XML or inline Key-Values) and a lightweight selection procedure is proposed to determine the best format per model-dataset combination using only a small development slice; thus reducing trial-and-error in practice.
Pierre Lepagnol, Sahar Ghannay, Thomas Gerald et al.· International Conference on...· 1 citation
This work investigates whether multimodal LLMs may generate pedagogical questions, and whether they can judge a question as pedagogical or not, in English and French and shows that while LLMs as a judge is an efficient framework, many problems could arise and that aligning prediction with human annotators is a difficul...
Thomas Gerald, Sahar Ghannay, Julie Lascar et al.· International Conference on...· 0 citations
This paper introduces a fully graph-based pipeline where the classifier never directly processes the input text, and reveals that graphs and text are complementary: combining both modalities achieves 92.1% accuracy on SNLI.
Younes Boufouss, Luc Pommeret, Thomas Gerald et al.· Conference on Automated Know...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.