mlsanityData to 7 Oct 2026

ESGReveal: An LLM-based approach for extracting structured data from ESG reports

arXiv 2312.17264 ↗First posted 25 Dec 2023cs.CL cs.IRcited by 15

Not on the map. Why?

Abstract (arXiv)

ESGReveal is an innovative method proposed for efficiently extracting and analyzing Environmental, Social, and Governance (ESG) data from corporate reports, catering to the critical need for reliable ESG information retrieval. This approach utilizes Large Language Models (LLM) enhanced with Retrieval Augmented Generation (RAG) techniques. The ESGReveal system includes an ESG metadata module for targeted queries, a preprocessing module for assembling databases, and an LLM agent for data extraction. Its efficacy was appraised using ESG reports from 166 companies across various sectors listed on the Hong Kong Stock Exchange in 2022, ensuring comprehensive industry and market capitalization representation. Utilizing ESGReveal unearthed significant insights into ESG reporting with GPT-4, demonstrating an accuracy of 76.9% in data extraction and 83.7% in disclosure analysis, which is an improvement over baseline models. This highlights the framework's capacity to refine ESG data analysis precision. Moreover, it revealed a demand for reinforced ESG disclosures, with environmental and social data disclosures standing at 69.5% and 57.2%, respectively, suggesting a pursuit for more corporate transparency. While current iterations of ESGReveal do not process pictorial information, a functionality intended for future enhancement, the study calls for continued research to further develop and compare the analytical capabilities of various LLMs. In summary, ESGReveal is a stride forward in ESG data processing, offering stakeholders a sophisticated tool to better evaluate and advance corporate sustainability efforts. Its evolution is promising in promoting transparency in corporate reporting and aligning with broader sustainable development aims.

Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). Builds on 15 of its 37 references that are in the map. First posted on arXiv 25 Dec 2023.

Builds on

15 of 37 references.

References · 15

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  3. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  4. 2023Qwen Technical Reportcited by 3,273
  5. 2017Billion-scale similarity search with GPUscited by 2,477
  6. 2021GLM: General Language Model Pretraining with Autoregressive Blank Infillingcited by 1,026
  7. 2022LayoutLMv3: Pre-training for Document AI with Unified Text and Image Maskingcited by 481
  8. 2023FinGPT: Open-Source Financial Large Language Modelscited by 244
  9. 2023CHATREPORT: Democratizing Sustainability Disclosure Analysis through LLM-based Toolscited by 29
  10. 2022HLATR: Enhance Multi-stage Text Retrieval with Hybrid List Aware Transformer Rerankingcited by 19
  11. 2023LORE: Logical Location Regression Network for Table Structure Recognitioncited by 19
  12. 2020Analyzing Sustainability Reports Using Natural Language Processingcited by 18
3 more
  1. 2023Bloated Disclosures: Can ChatGPT Help Investors Process Information?cited by 9
  2. 2023Glitter or Gold? Deriving Structured Insights from Sustainability Reports via Large Language Modelscited by 6
  3. 2022Automatic ESG Assessment of Companies by Mining and Evaluating Media Coverage Data: NLP Approach and Toolcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 8; 2026: 6.

15 papers.

Sort:

By area:

  1. 2025Quantile Regression with Large Language Models for Price Predictioncited by 9
  2. 2024SusGen-GPT: A Data-Centric LLM for Financial NLP and Sustainability Report Generationcited by 7
  3. 2025Optimizing Large Language Models for ESG Activity Detection in Financial Textscited by 5
  4. 2025SustainableQA: A Comprehensive Question Answering Dataset for Corporate Sustainability and EU Taxonomy Reportingcited by 5
  5. 2026ESGLens: An LLM-Based RAG Framework for Interactive ESG Report Analysis and Score Predictioncited by 2
  6. 2025Automated Analysis of Sustainability Reports: Using Large Language Models for the Extraction and Prediction of EU Taxonomy-Compliant KPIscited by 1
  7. 2026Advancing ESG Intelligence: An Expert-level Agent and Comprehensive Benchmark for Sustainable Financecited by 1
  8. 2025DeepGreen: Effective LLM-Driven Greenwashing Monitoring System Designed for Empirical Testing -- Evidence from Chinacited by 0
  9. 2025Semi-Supervised Multi-Label Feature Selection with Consistent Sparse Graph Learningcited by 0
  10. 2025Discourse vs emissions: Analysis of corporate narratives, symbolic practices, and mimicry through LLMscited by 0
  11. 2025EmeraldMind: A Knowledge Graph-Augmented Framework for Greenwashing Detectioncited by 0
  12. 2026Toward Trustworthy Evaluation of Sustainability Rating Methodologies: A Human-AI Collaborative Framework for Benchmark Dataset Constructioncited by 0
3 more
  1. 2026Limited Marginal Benefit of Reasoning-Heavy LLM Deployment in ESG Narrative Scoring: A 4-Model Consensus Study on Japanese Listed Firmscited by 0
  2. 2026SchemaRAG: Dynamic Large Schema Reduction for LLM-driven Structured Information Extractioncited by 0
  3. 2026Empirical Evaluation of Open-Source Large Language Models for Retrieval-Augmented Generation in ESG Domaincited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Enhancing Retrieval for ESGLLM via ESG-CID -- A Disclosure Content Index Finetuning Dataset for Mapping GRI and ESRS
  2. 2026Benchmarking Embedding Models for ESG Data ↗
  3. 2024Leveraging Large Language Models to Democratize Access to Costly Datasets for Academic Research
  4. 2025Sustainable Digitalization of Business with Multi-Agent RAG and LLM
  5. 2026Augmenting Fundamental Analysis with Large Language Models: A RAG-Based System for Generating Investor Briefs
  6. 2024OmniEval: An Omnidirectional and Automatic RAG Evaluation Benchmark in Financial Domain
  7. 2026ESG-Bench: Benchmarking Long-Context ESG Reports for Hallucination Mitigation
  8. 2024Deploying Large Language Models With Retrieval Augmented Generation