Skip to content
Open
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
15 changes: 14 additions & 1 deletion README.md
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
# ESGenius Benchmark

This repository contains the dataset and evaluation code that accompany the **ESGenius** paper. The benchmark focuses on question answering within the domains of Environmental, Social and Governance (ESG) and sustainability. The full paper is provided as [`ESGenius_arxiv_v1.pdf`](ESGenius_arxiv_v1.pdf).
This repository contains the dataset and evaluation code released with the **ESGenius** paper. The benchmark focuses on question answering within the domains of Environmental, Social and Governance (ESG) and sustainability. The full paper is provided as [`ESGenius_arxiv_v1.pdf`](ESGenius_arxiv_v1.pdf).

## Dataset

Expand Down Expand Up @@ -40,6 +40,19 @@ Example header from the reference file:

- **`figures/`** – images of word clouds and summary plots used in the paper.


The following figures summarise the dataset and evaluation results:

![Question word cloud](figures/ESGenius_QA_question_wordcloud.png)
![Answer option word cloud](figures/ESGenius_QA_option_wordcloud.png)
![Source text word cloud](figures/ESGenius_Source_Text_wordcloud.png)

![Question distribution](figures/num_questions_distribution_pie.png)
![Page distribution](figures/pages_distribution_pie.png)

![Main results](figures/main_results.png)
![Accuracy vs model size](figures/acc_vs_model_size.png)

## Running Evaluations

1. Install dependencies (PyTorch, Transformers, pandas, etc.).
Expand Down