Scope3Trace: Evidence-Based Identification and Extraction of Scope 3 GHG Emissions from Sustainability Reports
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 30 of its 72 references that are in the map. First posted on arXiv 19 Jul 2026.
Builds on
30 of 72 references.
References · 30
- 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,988
- 2026TIP: Token Importance in On-Policy Distillationcited by 104
- 2026PACED: Distillation and On-Policy Self-Distillation at the Frontier of Student Competencecited by 28
- 2024Question Calibration and Multi-Hop Modeling for Temporal Question Answeringcited by 25
- 2025A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Modelscited by 25
- 2023Dual Path Modeling for Semantic Matching by Perceiving Subtle Conflictscited by 21
- 2025Beyond the Surface: Enhancing LLM-as-a-Judge Alignment with Human via Internal Representationscited by 15
- 2025ZARA: Training-Free Motion Time-Series Reasoning via Evidence-Grounded LLM Agentscited by 15
- 2025From Points to Coalitions: Hierarchical Contrastive Shapley Values for Prioritizing Data Samplescited by 12
- 2026Beyond GRPO and On-Policy Distillation: An Empirical Sparse-to-Dense Reward Principle for Language-Model Post-Trainingcited by 11
- 2025DRF: LLM-AGENT Dynamic Reputation Filtering Frameworkcited by 10
- 2025DSPC: Dual-Stage Progressive Compression Framework for Efficient Long-Context Reasoningcited by 10
18 more
- 2025Learning Game-Playing Agents with Generative Code Optimizationcited by 8
- 2025StructCoh: Structured Contrastive Learning for Context-Aware Text Semantic Matchingcited by 8
- 2026Seeing through the Conflict: Transparent Knowledge Conflict Handling in Retrieval-Augmented Generationcited by 6
- 2026HeLa-Mem: Hebbian Learning and Associative Memory for LLM Agentscited by 6
- 2024Space-aware Socioeconomic Indicator Inference with Heterogeneous Graphscited by 5
- 2025DRAFT-RL: Multi-Agent Chain-of-Draft Reasoning for Reinforcement Learning-Enhanced LLMscited by 4
- 2026Where Does Long-Context Supervision Actually Go? Effective-Context Exposure Balancingcited by 4
- 2026Possible or Definite? A Benchmark for Evaluating Diagnostic Uncertainty Preservation in Clinical Textcited by 4
- 2026SP-Mind: An Autonomous Reasoning Agent for Spatial Proteomics Analysiscited by 4
- 2024Statements: Universal Information Extraction from Tables with Large Language Models for ESG KPIscited by 3
- 2025Over++: Generative Video Compositing for Layer Interaction Effectscited by 3
- 2026Do Deployment Constraints Make LLMs Hallucinate Citations? An Empirical Study across Four Models and Five Prompting Regimescited by 3
- 2026Understanding and Mitigating Spurious Signal Amplification in Test-Time Reinforcement Learning for Math Reasoningcited by 3
- 2026Design and Implementation of an Open-Source Security Framework for Cloud Infrastructurecited by 2
- 2026LLM-Oriented Information Retrieval: A Denoising-First Perspectivecited by 1
- 2026BoostAPR: Boosting Automated Program Repair via Execution-Grounded Reinforcement Learning with Dual Reward Modelscited by 1
- 2026GHGbench: A Unified Multi-Entity, Multi-Task Benchmark for Carbon Emission Predictioncited by 1
- 2026TriLens: Per-Layer Logit-Lens Entropy for White-Box Hallucination Detectioncited by 1
Built on by
Not cited yet.