Ai2 Newsletter
September 2024
Top story - Our 100% open Mixture-of-Experts model is here!
This week, we welcomed the latest addition to the OLMo family, OLMoE — the first 100% open and good MoE LLM. Efficient enough to run locally, OLMoE's data, code, logs, experiments and analysis are all open and available to review.
ACL 2024 paper recognition round-up
We're thrilled for our teams who were recognized at the ACL 2024 Conference! OLMo received the Best Theme Paper, Dolma and AppWorld received the Best Resource Paper, and "Political Compass or Spinning Arrow?" was honored with an Outstanding Paper Award.
New paper featured in Nature
AI reflects human biases — like covert racism. In work recently published in Nature, our team shows how, despite efforts to remove overt racial bias, LLMs generate covertly racist decisions about people based on their dialect.
New evaluation tool Digital Socrates
At ACL 2024, our team presented Digital Socrates, an interpretable explanation evaluation tool that can automatically characterize the explanation capabilities of modern LLMs.
Ai2 at DEF CON 32
Our team attended this year's DEF CON to cohost the red teaming of OLMo at the AI Village. Christopher Fiorelli, one of our technical program managers, wrote a brief retrospective of the event from his point of view.