ESGBench: A Benchmark for Explainable ESG Question Answering in Corporate Sustainability Reports

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: George, Sherine, Saji, Nithish
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914165648523264
author George, Sherine
Saji, Nithish
author_facet George, Sherine
Saji, Nithish
contents We present ESGBench, a benchmark dataset and evaluation framework designed to assess explainable ESG question answering systems using corporate sustainability reports. The benchmark consists of domain-grounded questions across multiple ESG themes, paired with human-curated answers and supporting evidence to enable fine-grained evaluation of model reasoning. We analyze the performance of state-of-the-art LLMs on ESGBench, highlighting key challenges in factual consistency, traceability, and domain alignment. ESGBench aims to accelerate research in transparent and accountable ESG-focused AI systems.
format Preprint
id arxiv_https___arxiv_org_abs_2511_16438
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ESGBench: A Benchmark for Explainable ESG Question Answering in Corporate Sustainability Reports
George, Sherine
Saji, Nithish
Computation and Language
Information Retrieval
I.2.7; H.3.3
We present ESGBench, a benchmark dataset and evaluation framework designed to assess explainable ESG question answering systems using corporate sustainability reports. The benchmark consists of domain-grounded questions across multiple ESG themes, paired with human-curated answers and supporting evidence to enable fine-grained evaluation of model reasoning. We analyze the performance of state-of-the-art LLMs on ESGBench, highlighting key challenges in factual consistency, traceability, and domain alignment. ESGBench aims to accelerate research in transparent and accountable ESG-focused AI systems.
title ESGBench: A Benchmark for Explainable ESG Question Answering in Corporate Sustainability Reports
topic Computation and Language
Information Retrieval
I.2.7; H.3.3
url https://arxiv.org/abs/2511.16438