This work investigates whether Large Language Model-generated labels and paraphrases can train small, fast classifiers for this task, and reports on evaluation for six properties currently relies on LLM-generated labels validated against a 50-page human-annotated sample.
Ratan J. Sebastian, Anett Hoppe· Proceedings of the 26th ACM/...· 0 citations
Web resources rarely carry the educational metadata that teachers use to judge whether a resource fits their lesson, and dedicated educational repositories that do carry it cover only a fraction of what teachers find through web search. Closing this gap in real time, at the point of search, requires classifiers that ar...
It is found that visual coherence and text-image alignment are nearly uncorrelated across terms and jointly separate distinct failure modes, and fine-tuning improves retrieval overall, but its gains favour shallower terms in the hierarchy, where text-image alignment improves most, beyond what concept frequency explains...
Ratan J. Sebastian, Anett Hoppe, Christoph Rippe et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.