# ESGLens: An LLM-Based RAG Framework for Interactive ESG Report Analysis and Score Prediction

arXiv: https://arxiv.org/abs/2604.19779 · HTML: https://mlsanity.com/paper/2604.19779/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Legal and financial RAG, one of 15 directions in Retrieval-augmented generation.
- Builds on 16 of its 37 references that are in the map.
- First posted on arXiv 29 Mar 2026.

## Placed in

- Retrieval-augmented generation / [Legal and financial RAG](https://mlsanity.com/rag/legal-and-financial-rag/)

## Builds on (most cited first, 16 of 16)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [REALM: Retrieval-Augmented Language Model Pre-Training](https://mlsanity.com/paper/2002.08909/) (2020)
- [CHATREPORT: Democratizing Sustainability Disclosure Analysis through LLM-based Tools](https://mlsanity.com/paper/2307.15770/) (2023)
- [ESGReveal: An LLM-based approach for extracting structured data from ESG reports](https://mlsanity.com/paper/2312.17264/) (2023)
- [ESGBERT: Language Model to Help with Classification Tasks Related to Companies Environmental, Social, and Governance Practices](https://mlsanity.com/paper/2203.16788/) (2022)
- [Developing Retrieval Augmented Generation (RAG) based LLM Systems from PDFs: An Experience Report](https://mlsanity.com/paper/2410.15944/) (2024)
- [ESGenius: Benchmarking LLMs on Environmental, Social, and Governance (ESG) and Sustainability Knowledge](https://mlsanity.com/paper/2506.01646/) (2025)
- [CuriousLLM: Elevating Multi-Document Question Answering with LLM-Enhanced Knowledge Graph Reasoning](https://mlsanity.com/paper/2404.09077/) (2024)
- [MMESGBench: Pioneering Multimodal Understanding and Complex Reasoning Benchmark for ESG Tasks](https://mlsanity.com/paper/2507.18932/) (2025)
- [ESG Reporting Lifecycle Management with Large Language Models and AI Agents](https://mlsanity.com/paper/2603.10646/) (2026)
- [Leveraging BERT Language Models for Multi-Lingual ESG Issue Identification](https://mlsanity.com/paper/2309.02189/) (2023)
- [EulerESG: Automating ESG Disclosure Analysis with LLMs](https://mlsanity.com/paper/2511.21712/) (2025)

## Built on by (most cited first, 2 of 2)

- [Limited Marginal Benefit of Reasoning-Heavy LLM Deployment in ESG Narrative Scoring: A 4-Model Consensus Study on Japanese Listed Firms](https://mlsanity.com/paper/2606.13693/) (2026)
- [Empirical Evaluation of Open-Source Large Language Models for Retrieval-Augmented Generation in ESG Domain](https://mlsanity.com/paper/2609.15242/) (2026)

## Abstract (arXiv)

Environmental, Social, and Governance (ESG) reports are central to investment decision-making, yet their length, heterogeneous content, and lack of standardized structure make manual analysis costly and inconsistent. We present ESGLens, a proof-of-concept framework combining retrieval-augmented generation (RAG) with prompt-engineered extraction to automate three tasks: (1)~structured information extraction guided by Global Reporting Initiative (GRI) standards, (2)~interactive question-answering with source traceability, and (3)~ESG score prediction via regression on LLM-generated embeddings. ESGLens is purpose-built for the domain: a report-processing module segments heterogeneous PDF content into typed chunks (text, tables, charts); a GRI-guided extraction module retrieves and synthesizes information aligned with specific standards; and a scoring module embeds extracted summaries and feeds them to a regression model trained against London Stock Exchange Group (LSEG) reference scores. We evaluate the framework on approximately 300 reports from companies in the QQQ, S&P~500, and Russell~1000 indices (fiscal year 2022). Among three embedding methods (ChatGPT, BERT, RoBERTa) and two regressors (Neural Network, LightGBM), ChatGPT embeddings with a Neural Network achieve a Pearson correlation of 0.48 (R2 ≈ 0.23) against LSEG ground-truth scores -- a modest but statistically meaningful signal given the ~300-report training set and restriction to the environmental pillar. A traceability audit shows that 8 of 10 extracted claims verify against the source document, with two failures attributable to few-shot example leakage. We discuss limitations including dataset size and restriction to environmental indicators, and release the code to support reproducibility.