dataset
mleb-scalr
isaacus
or hover any field below to flag it
Overview
Name
mleb-scalr
Source
isaacus
Episodes
0
Robot count
0
Format
json
Description
SCALR (MLEB version)
This is the version of the SCALR evaluation dataset used in the Massive Legal Embeddings Benchmark (MLEB) by Isaacus.
This dataset tests the ability of information retrieval models to retrieve relevant legal holdings to complex, reasoning-intensive legal questions.
Structure 🗂️
As per the MTEB information retrieval dataset format, this dataset comprises three splits, default, corpus and queries.
The default split pairs questions (query-id) with… See the full description on the dataset page: https://huggingface.co/datasets/isaacus/mleb-scalr.
Robots used
null
Links
HuggingFace dataset