About to finish teaching the final session of our course Prompting, Evaluation, Interpretation: An Introduction to LLMs in Text Analysis as part of the Deep Learning Summer School in Cologne. It’s been a great experience guiding everyone through the fascinating world of large language models and text analysis. We’ve (@janispagel) had a lot of fun and hope you’ve enjoyed it as much as we have!
[#]dl4lass #LLM #rTA
=> View attached media | View attached media
=> More informations about this toot | View the thread
Just compared Claude-Sonnet-3.5 with OpenAI's o1 on a CLS task – classifying text inputs from US short stories with regard to focalization. Turns out, Sonnet doesn't recognize zero focalization and achieved an F1-score of 0.47, while o1 performed better with 0.69. Not bad - but problematic, as the hidden tokens of the optimizer (?) from o1 would be of particular interest.
[#]CLS #AI #ClaudeSonnet #OpenAI's_o1 #TextClassification #Focalization
=> More informations about this toot | View the thread
=> This profile with reblog | Go to axelpichler@fedihum.org account This content has been proxied by September (3851b).Proxy Information
text/gemini