Climate Finance Bench

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Mankour, Rafik, Chafai, Yassine, Saleh, Hamada, Hassine, Ghassen Ben, Barreau, Thibaud, Tankov, Peter
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916765360979968
author Mankour, Rafik
Chafai, Yassine
Saleh, Hamada
Hassine, Ghassen Ben
Barreau, Thibaud
Tankov, Peter
author_facet Mankour, Rafik
Chafai, Yassine
Saleh, Hamada
Hassine, Ghassen Ben
Barreau, Thibaud
Tankov, Peter
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_22752
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Climate Finance Bench
Mankour, Rafik
Chafai, Yassine
Saleh, Hamada
Hassine, Ghassen Ben
Barreau, Thibaud
Tankov, Peter
Computation and Language
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.
title Climate Finance Bench
topic Computation and Language
url https://arxiv.org/abs/2505.22752