It is shown that useful explanations can extend beyond the model a verbalizer was trained to describe and show that pretrained verbalizers recover words that models have learned to conceal through fine-tuning, without additional verbalizer training.
Federico Torrielli, Gianluca Barmina, Andrea Blasi Núñez et al.· 0 citations
Daisy, a factual knowledge benchmark for Danish cultural heritage, based on curated topics from the Danish Culture Canon 2006, is introduced, with results showing that contemporary language models perform surprisingly poorly on this task.
Jacob Nielsen, Stine Lyngsø Beltoft, Peter Schneider-Kamp et al.· arXiv.org· 0 citations
A strongly typed domain-specific language with Haskell-like syntax, that enables a write-once, run everywhere paradigm for LLM architectures, Axon fosters open cooperation and empowers researchers to implement highly specialized architectures without giving up optimization infrastructure or accepting deployment lock-in...
Jacob Nielsen, Danial Namazifard, Lukas Galke Poech 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.