Scope3Trace is proposed, an evidence-grounded information extraction framework designed to extract interpretable and traceable Scope 3 emissions information from real-world ESG and sustainability reports and contributes a dual-level, evidence-grounded, multimodal dataset.
Abstract
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.
An evidence-grounded LLM-assisted semantic-to-structure framework that combines BERTopic evidence with schema-constrained hierarchical induction and software-enforced staged locking is proposed that supports structural controllability and evidence traceability, but not universal superiority or improved semantic quality...
The preliminary results of an Open Information Extraction task, based on Large Language Models, to obtain structured business-related data from documents about climate change, with specifically focus on the performance of a European model, Mistral, compared to similar commercial US models.
Large language models (LLMs) have been increasingly used for financial document analysis, including earnings call transcripts (ECTs). Beyond generating standalone claims, users increasingly prefer grounded analyses that pair claims with verifiable citations from source documents to enable independent validation. Howeve...
Ying-Zhu Zhao, Vlad Pandelea, Han Yuan et al.· 0 citations
EviMap is an interactive system providing researchers and practitioners with an auditable thematic overview of heterogeneous corpora spanning 2,108 to 101,699 documents, with a comparison against flat and hierarchical LLM baselines.
Science, technology, and innovation policies are crucial for competitiveness, yet their diversity and scale make them difficult to map and monitor consistently. Existing approaches rely heavily on manual survey efforts, which are costly and challenging to scale across countries. Large language models (LLMs) enable new...
Carolyn Cole, M. Deschryvere, Toqeer Ehsan et al.· FLINS-ISKE· 0 citations
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduNov 20, 2026
Senior Research Scientist Jim Glass discusses how his MIT-IBM Computing Research Lab collaboration connects perception and language, and addresses the shortcoming of current models.
MIT News · Artificial Intelligence· news.mit.eduNov 19, 2026
An MIT and Dana-Farber Institute-led team used large language models to examine nearly 4,000 studies and hundreds of code repositories, revealing gaps in the information needed to scrutinize and reuse published research.
By studying the computational foundations of language learning, Associate Professor Jacob Andreas builds intelligent systems that can communicate effectively with humans.
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.