Scope3Trace: Evidence-Based Identification and Extraction of Scope 3 GHG Emissions from Sustainability Reports
Quick Answer
Scope3Trace is an evidence-grounded framework for extracting Scope 3 GHG emissions from ESG reports, overcoming challenges of sparse disclosures and heterogeneous formats.
Quick Take
It utilizes a hybrid rule- approach for reliable extraction and verification, achieving high accuracy in identifying organization-level emissions. The framework also introduces a multimodal dataset for enhanced analysis.
Key Points
- Scope3Trace integrates PDF collection, OCR parsing, and LLM-assisted extraction.
- Achieves high accuracy in extracting Scope 1-3 totals and category-level disclosures.
- Introduces a dual-level, evidence-grounded multimodal dataset for sustainability reports.
- Addresses challenges of sparse disclosures and heterogeneous document formats.
- Enhances reliability of emissions information extraction from ESG reports.
DeepSignal Analysis
What happened
Scope3Trace is a new framework designed to extract Scope 3 GHG emissions from ESG reports. It addresses challenges such as sparse disclosures and varying document formats by using a hybrid rule-LLM approach. The framework also includes a multimodal dataset for better analysis of emissions data.
Key evidence
- Scope 3 emissions are significant as they represent the majority of corporate carbon footprints, yet their analysis is complicated by sparse disclosures and heterogeneous report formats.
- Scope3Trace employs a hybrid rule-LLM approach to enhance the reliability of emissions extraction from sustainability reports, achieving high accuracy in identifying organization-level emissions.
- The framework contributes a dual-level, evidence-grounded, multimodal dataset that includes organization-level Scope 3 disclosures extracted from various sustainability reports.
Why it matters
The ability to accurately extract and verify Scope 3 emissions data is crucial for companies aiming to reduce their carbon footprints. By improving the reliability of emissions data extraction, Scope3Trace can facilitate better corporate accountability and transparency in sustainability reporting. This is particularly important as stakeholders increasingly demand credible environmental impact assessments.
Paper Resources
📖 Reader Mode
~2 min readAbstract:Scope 3 greenhouse gas (GHG) emissions account for the majority of corporate carbon footprints, yet remain difficult to analyze at scale due to sparse disclosures, heterogeneous report document formats, and limited evidence traceability. Existing approaches typically rely on large language models to extract emissions information from ESG reports, but often lack explicit evidence grounding or depend on costly manual annotation and verification to ensure extraction reliability. To address these challenges, we propose Scope3Trace, an evidence-grounded information extraction framework designed to extract interpretable and traceable Scope 3 emissions information from real-world ESG and sustainability reports. The framework integrates a document information extraction pipeline that performs PDF collection and OCR parsing, LLM-assisted page localization and table reconstruction, and hybrid rule-LLM extraction of organization- and building-level emissions disclosures with evidence-grounded verification. Building upon this framework, we further contribute a dual-level, evidence-grounded, multimodal dataset comprising organization-level Scope 3 disclosures extracted from heterogeneous sustainability reports. Scope3Trace enables reliable extraction and transparent integration of heterogeneous sustainability disclosures, achieving high accuracy in extracting Scope 1-3 totals and category-level disclosures from sustainability reports.
| Comments: | 23 pages |
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2607.17122 [cs.CL] |
| (or arXiv:2607.17122v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2607.17122 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Yifan Duan [view email]
[v1]
Sun, 19 Jul 2026 08:13:54 UTC (3,850 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CL
See more →TriAgent: Divergence-Aware Committees for Cost-Efficient Financial Sentiment Analysis
TriAgent introduces a cost-efficient multi-agent system for financial sentiment analysis, combining VADER, FinBERT, and Qwen2.5. It achieves an F1 score of ~0.87 with significant savings of $9.3M/year at a 10M-user scale compared to GPT-4o-mini, while also detecting hallucinations with an AUC of 0.90.