Benchmark

LEGOBench

Benchmark for generating scientific leaderboards from papers.

Theme
Evaluation, Reliability & Trustworthy AI
Type
Benchmark
Funding
Unfunded

Paper and code

LEGOBench: Scientific Leaderboard Generation Benchmark

Shruti Singh, Alam, Malwat, Mayank Singh. Findings of EMNLP 2024.

PaperGitHub

Theme →Datasets and models →Publications →