Legalbench
Hugging FaceDataset Card for Dataset Name Homepage: https://hazyresearch.stanford.edu/legalbench/ Repository: https://github.com/HazyResearch/legalbench/ Paper: https://arxiv.org/abs/2308.11462 Dataset Description Dataset Summary The LegalBench project is an ongoing open science effort to collaboratively curate tasks for evaluating legal reasoning in English large language models (LLMs). The benchmark currently consists of 162 tasks gathered from 40… See the full description on the dataset page: https://huggingface.co/datasets/nguha/legalbench.
Ask a question about this data
Type any question in plain English — Helix builds the chart with AI. Sign in to run it and save your charts.
Data preview
5 rows · 3 columns · showing first 5| # | column_1 integer | answer text | text text |
|---|---|---|---|
| 1 | 0 | generic | The mark "Ivory" for a product made of elephant tusks. |
| 2 | 1 | descriptive | The mark "Tasty" for bread. |
| 3 | 2 | suggestive | The mark "Caress" for body soap. |
| 4 | 3 | arbitrary | The mark "Virgin" for wireless communications. |
| 5 | 4 | fanciful | The mark "Aswelly" for a taxi service. |
Auto-generated charts
Legalbench: 5 rows by 3 columns. These exploratory charts are generated automatically from the data - open the dataset in Helix to ask your own questions.
Charts
Total column_1 by answer
Top answer values ranked by summed column_1.
Distribution of column_1
Histogram of column_1 values.
column_1 by answer
Spread of column_1 across answer groups.
Interesting queries to try
Columns
- index numeric
- answer text
- text text