Climate Finance Bench

Rafik Mankour, Yassine Chafai, Hamada Saleh, Ghassen Ben Hassine, Thibaud Barreau +1 more

5/28/2025

cs.CL

No official code found. Best implementation: Pladifes/climate_finance_bench (4 stars, last commit 2025-05-22).

Abstract

Climate Finance Bench introduces an open benchmark that targets question-answering over corporate climate disclosures using Large Language Models. We curate 33 recent sustainability reports in English drawn from companies across all 11 GICS sectors and annotate 330 expert-validated question-answer pairs that span pure extraction, numerical reasoning, and logical reasoning. Building on this dataset, we propose a comparison of RAG (retrieval-augmented generation) approaches. We show that the retriever's ability to locate passages that actually contain the answer is the chief performance bottleneck. We further argue for transparent carbon reporting in AI-for-climate applications, highlighting advantages of techniques such as Weight Quantization.

View on arXiv View PDF

Code Implementations(1)

Pladifes/climate_finance_benchCommunity100%

41Jupyter NotebookApr 18, 20251 years ago

Similar Papers

CarbonChat: Large Language Model-Based Corporate Carbon Emission Analysis and Climate Knowledge Q&A System

87% match2025

Chitchat with AI: Understand the supply chain carbon disclosure of companies worldwide through Large Language Model

85% match2025

Listen to the Context: Towards Faithful Large Language Models for Retrieval Augmented Generation on Climate Questions

84% match2025

Climate AI for Corporate Decarbonization Metrics Extraction

84% match2024

Reporting and Analysing the Environmental Impact of Language Models on the Example of Commonsense Question Answering with External Knowledge

82% match1 repo12024

CF-RAG: A Dataset and Method for Carbon Footprint QA Using Retrieval-Augmented Generation

82% match2025

Cite this paper

@article{mankour2025climate,
  title  = {Climate Finance Bench},
  author = {Rafik Mankour and Yassine Chafai and Hamada Saleh and Ghassen Ben Hassine and Thibaud Barreau and Peter Tankov},
  year   = {2025},
  eprint = {2505.22752},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2505.22752v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

[![Code of Paper](https://codeofpaper.com/badge/2505.22752.svg)](https://codeofpaper.com/paper/2505.22752)