A structured medical triage test showed ChatGPT performing at levels that surprised researchers — but some physicians say the real surprise is how long we've avoided comparing AI's risks to the risks ...
This is a repository containing the code for GDPO: Learning to Directly Align Language Models with Diversity Using GFlowNets, published in EMNLP 2024 Main. @inproceedings{kwon-etal-2024-gdpo, title = ...
Trove is a lightweight toolkit for training and evaluating transformer-based dense retrievers. It aims to keep the codebase simple and hackable, while offering a clean, unified interface for quickly ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results