You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Benchmarking Long-Context Reasoning on Scientific Articles
We will release the code and data later. Stay tuned!
If you are interested in testing your model with our benchmark or using our constructed training data in your long-context post-training, please contact miao.li@ed.ac.uk.
About
Benchmarking long-context reasoning on scientific articles