Add BGPT REFUTE (scientific critique & epistemic calibration benchmark)#40
Open
connerlambden wants to merge 1 commit into
Open
Add BGPT REFUTE (scientific critique & epistemic calibration benchmark)#40connerlambden wants to merge 1 commit into
connerlambden wants to merge 1 commit into
Conversation
Author
|
For reviewers: REFUTE ships runnable integrations (Inspect AI + lm-eval), a finalized eval.yaml (inspect-ai), Croissant FAIR metadata, and a philosophy-of-science writeup on why skill ≠ truth. Integrator guide: https://huggingface.co/datasets/BGPT-OFFICIAL/refute/blob/main/INTEGRATORS.md · Essay: https://huggingface.co/datasets/BGPT-OFFICIAL/refute/blob/main/EPISTEMICS.md |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Adds REFUTE, an Apache-2.0 benchmark testing whether models critique recent science summaries with calibrated, evidence-grounded judgment. Public leaderboard, technical report, and runnable Inspect AI + lm-eval integrations. Integrator guide: https://huggingface.co/datasets/BGPT-OFFICIAL/refute/blob/main/INTEGRATORS.md