Configure Programmatic Tool Calling, control which tools programs can invoke, and resume programs after client-owned function calls.

Just published. You may have heard that LLMs have favorite words: "delve", "underscore", "intricate", and so on. Here we demonstrate that the prevalence of these words in the academic literature has d...

While large language models (LLMs) are increasingly used as automatic judges for question answering (QA) and other reference-conditioned evaluation tasks, little is known about their ability to adhere...

Despite investing tens of billions of dollars into OpenAI, Microsoft is still, apparently, competing with its business partner.

I have bittersweet news to share. Yesterday we merged a PR deprecating TensorFlow and Flax support in transformers. Going forward, we're focusing all our efforts on PyTorch to remove a lot of th...

Many industry verticals are confronted with small-sized tabular data. In this low-data regime, it is currently unclear whether the best performance can be expected from simple baselines, or more compl...

Is MMLU Western-centric? 🤔 As part of a massive cross-institutional collaboration: 🗽Find MMLU is heavily overfit to western culture 🔍 Professional…

The new hires, all experts in computer vision, are the latest AI researchers to jump to a direct competitor in an intensively competitive talent market.