Aryo Pradipta Gema
@aryopg.bsky.social
AI Safety Fellow @Anthropic | PhD at University of Edinburgh | LLM Hallucinations | Clinical NLP | Opinions are my own.
Personal page: https://aryopg.github.io
Personal page: https://aryopg.github.io
This goes without saying: As someone from a non-English speaking country, I salute the effort to democratise LLM evaluations across languages. But we must also ensure we don't democratise mistakes.
December 6, 2024 at 9:44 AM
This goes without saying: As someone from a non-English speaking country, I salute the effort to democratise LLM evaluations across languages. But we must also ensure we don't democratise mistakes.
Oops! Some errors we noticed in MMLU-Redux still exist in some languages (e.g., rapid intervention to "solve" ebola). (I just checked the 2 languages that I understand: Indonesian and Malay)
December 5, 2024 at 11:11 PM
Oops! Some errors we noticed in MMLU-Redux still exist in some languages (e.g., rapid intervention to "solve" ebola). (I just checked the 2 languages that I understand: Indonesian and Malay)
Would you be so kind including me to the party? @ramandutt4.bsky.social
November 20, 2024 at 5:00 PM
Would you be so kind including me to the party? @ramandutt4.bsky.social
I'd love to be added!
November 17, 2024 at 6:53 PM
I'd love to be added!