用大模型+检索增强生成，自动分析企业环保报告并预测评分
ESGLens: An LLM-Based RAG Framework for Interactive ESG Report Analysis and Score Prediction
- 基于GRI标准，从杂乱报告中提取结构化信息
- 通过大模型嵌入预测环境评分，相关性达0.48
- 支持交互式问答且可追溯来源，适合金融分析场景
环境、社会与治理（ESG）报告是投资决策的核心，但其篇幅长、内容异构、无统一结构，导致人工分析成本高且不一致。我们提出ESGLens，一个结合检索增强生成（RAG）与提示工程的原型框架，自动化完成三项任务：(1) 依据全球报告倡议组织（GRI）标准提取结构化信息；(2) 支持可溯源的交互式问答；(3) 基于大模型生成的嵌入向量进行回归，预测ESG评分。该框架专为领域设计：报告处理模块将异构PDF内容分割为文本、表格、图表等类型块；GRI引导提取模块检索并合成符合特定标准的信息；评分模块对提取摘要进行嵌入，并输入至回归模型，训练目标为伦敦证券交易所集团（LSEG）的参考评分。在约300份来自QQQ、标普500及罗素1000指数公司（2022财年）的报告上评估。在三种嵌入方法（ChatGPT、BERT、RoBERTa）与两种回归器（神经网络、LightGBM）中，使用ChatGPT嵌入配合神经网络，与LSEG真实评分的皮尔逊相关系数达0.48（R²≈0.23），在仅含300个样本且限定于环境维度的情况下，已具统计显著性。溯源审计显示，10条提取声明中有8条可验证，两例失败源于少量示例泄露。讨论了数据规模小和仅限环境指标等局限，并开源代码以支持复现。
原文摘要 · Abstract (English)
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 ($R^{2} \approx 0.23$) against LSEG ground-truth scores -- a modest but statistically meaningful signal given the ${\sim}300$-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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。