# Automated Analysis of Sustainability Reports: Using Large Language Models for the Extraction and Prediction of EU Taxonomy-Compliant KPIs

arXiv: https://arxiv.org/abs/2512.24289 · HTML: https://mlsanity.com/paper/2512.24289/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 24 references that are in the map.
- First posted on arXiv 30 Dec 2025.

## Builds on (most cited first, 6 of 6)

- [Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedback](https://mlsanity.com/paper/2305.14975/) (2023)
- [Large Language Models in Finance: A Survey](https://mlsanity.com/paper/2311.10723/) (2023)
- [Large Language Models for Generative Information Extraction: A Survey](https://mlsanity.com/paper/2312.17617/) (2023)
- [ESGReveal: An LLM-based approach for extracting structured data from ESG reports](https://mlsanity.com/paper/2312.17264/) (2023)
- [ESGenius: Benchmarking LLMs on Environmental, Social, and Governance (ESG) and Sustainability Knowledge](https://mlsanity.com/paper/2506.01646/) (2025)
- [Optimizing Large Language Models for ESG Activity Detection in Financial Texts](https://mlsanity.com/paper/2502.21112/) (2025)

## Built on by (most cited first, 1 of 1)

- [REGREACT: Self-Correcting Multi-Agent Pipelines for Structured Regulatory Information Extraction](https://mlsanity.com/paper/2604.12054/) (2026)

## Abstract (arXiv)

The manual, resource-intensive process of complying with the EU Taxonomy presents a significant challenge for companies. While Large Language Models (LLMs) offer a path to automation, research is hindered by a lack of public benchmark datasets. To address this gap, we introduce a novel, structured dataset from 190 corporate reports, containing ground-truth economic activities and quantitative Key Performance Indicators (KPIs). We use this dataset to conduct the first systematic evaluation of LLMs on the core compliance workflow. Our results reveal a clear performance gap between qualitative and quantitative tasks. LLMs show moderate success in the qualitative task of identifying economic activities, with a multi-step agentic framework modestly enhancing precision. Conversely, the models comprehensively fail at the quantitative task of predicting financial KPIs in a zero-shot setting. We also discover a paradox, where concise metadata often yields superior performance to full, unstructured reports, and find that model confidence scores are poorly calibrated. We conclude that while LLMs are not ready for full automation, they can serve as powerful assistive tools for human experts. Our dataset provides a public benchmark for future research.