2026· Journal of Environmental Informatics· 0 citations
TL;DR
LLMs-RAG-CFA, a unified framework that combines large language models with retrieval-augmented generation (RAG) to deliver real-time, reliable, cost-efficient, and privacy-preserving CFA, offers a scalable, practical pathway for real-time carbon emission monitoring and supports improved sustainability practices.
Abstract
Carbon footprint accounting (CFA) is critical for decarbonization efforts but remains constrained by static databases, fragmented data sources, and labor-intensive expert workflows. Conventional life cycle assessment (LCA) methods struggle to adapt to dynamic production changes, policy updates, and enterprise-specific data privacy requirements. While large language models (LLMs) offer promising automation capabilities, no practical frameworks currently exist for fully automated CFA; directly applying LLMs introduces limitations such as weak factual grounding, poor responsiveness, high inference costs, and insufficient handling of confidential data. To address these gaps, this paper proposes LLMs-RAG-CFA, a unified framework that combines large language models with retrieval-augmented generation (RAG) to deliver real-time, reliable, cost-efficient, and privacy-preserving CFA. The system incorporates semantic segmentation, top-k domain-specific fragment retrieval, uncertainty-aware and input-length-aware prompt construction strategies to optimize real-time professional coverage, reduce uncertainty and reduce token consumption. Interval-based uncertainty metrics are designed to quantify retrievaland accounting-stage uncertainty, supporting more interpretable and trustworthy carbon assessments. Extensive experiments across five carbon-intensive industries (primary aluminum, lithium batteries, photovoltaics, new energy vehicles, and transformers) demonstrate that LLMs-RAG-CFA consistently outperforms baseline CFA workflows by achieving higher retrieval completeness, lower information deviation, and lower accounting deviation. A complete set of analysis covering real-time adaptability, cost trade-offs, and privacy handling further supports its practical viability. This framework offers a scalable, practical pathway for real-time carbon emission monitoring and supports improved sustainability practices.
A literature-based architectural framework for reliable knowledge retrieval systems that separates external knowledge management from LLM-based reasoning and generation is developed and indicates that reliable LLM deployment should be treated as an end-to-end architectural problem rather than solely a model-performance problem.
Bharat Kumar Reddy Karumuri· International Journal of Eng...· 0 citations
In high-risk industrial settings, leveraging large language models (LLMs) for automated accident analysis and generating safety reports has emerged as an efficient workflow. However, this approach is fundamentally constrained by the models’ inherent knowledge limitations, frequently resulting in analyses that lack domain-specific understanding and regulatory alignment.
To tackle this issue, we introduce SafeRAG, a multistage retrieval-augmented framework for safety report generation. Specifically, the framework uses an entity-centric approach that prompts the LLMs to internally generate domain-specific knowledge. Concurrently, it performs a hierarchical retrieval of external regulations relevant to the accident at topic, concept, and context levels. To obtain well-structured reports, we leverage prompt engineering, integrating internal and external knowledge. Furthermore, a domain-expert persona is also assigned to help LLMs analyze accidents from a specific perspective. To evaluate our approach, we construct a data set from 10,818 accident-description/report pairs collected from real-world industry reports. Experiments show that SafeRAG substantially outperforms baseline LLMs on metrics that include bidirectional encoder representations from transformers (BERTScore) and bidirectional auto-regressive transformers (BARTScore), demonstrating the effectiveness of our approach.
Qi Cao, Chiyu Zhang, Junxiong Ning et al.· SPE Journal· 0 citations
Ethereum is now integral to mission-critical sectors, including finance, healthcare, and supply chain management. Execution fees, commonly referred to as Gas, scale with the computational complexity of their functions. Smart contracts on Ethereum incur execution fees, known as Gas, which increase with computational complexity. Thus, optimizing Gas-intensive code while preserving functional equivalence significantly lowers deployment costs. No existing system continuously exploits evolving Gas usage patterns. We systematically analyze syntactic and semantic constructs that drive excessive Gas use. This yields six high-level categories covering twelve fine-grained antipatterns underpinning a curated knowledge base. We operationalize these insights with RAGas, a three-stage retrieval-augmented generation framework that uses a large language model to pinpoint and automatically fix Gas inefficiencies. Experiments on deployed contracts demonstrate that RAGas reduces Gas usage by up to 11% and achieves high precision and recall in detecting code snippets exhibiting Gas wastage.
Yishun Wang, Wenjin Yi, Wenkai Li et al.· 1 citation
Object-relational mapping (ORM) design remains largely driven by fixed heuristics that fail to capture workload-specific tradeoffs among query latency, insert cost, and memory footprint. We present Y-Map, a hybrid neural--symbolic framework for performance-aware ORM schema design that synthesizes valid schema candidates and predicts their performance without requiring workload execution at inference time. Y-Map leverages Alloy to enumerate correctness-preserving ORM schemas and ranks them using a multi-encoder regression model that fuses structural, syntactic, and semantic representations with compact schema-level features. By predicting continuous performance objectives---insert latency, query latency, and memory footprint---Y-Map enables Pareto-aware selection without per-candidate benchmarking during inference. We evaluate Y-Map on nine object models from e-commerce, banking, and healthcare. Relative to two representative baselines, Leant and DTS, Y-Map yields improved aggregate Pareto quality (Generational Distance and Hypervolume) while reducing inference time and memory overhead. The experimental results show that integrating symbolic validity guarantees with learned performance prediction provides a practical, scalable solution for workload-aware ORM optimization.
Constrained-guided mapping is proposed, a neuro-symbolic method with three stages: schema-grounded admissibility constraints with metadata mc =, where tau_c denotes the constraint type and delta_c provides executable relation and normalization logic, and constraint-restricted candidate generation with cascade relaxation to guarantee a nonempty feasible set under noise.
Sebastian Monka, Pramod Anantharam, Thị Minh et al.· 0 citations
Eagle, a comprehensive benchmarking framework tailored for evaluating OpsLLMs, delivers a deployable foundation for advancing large-model applications in AIOps and open-source the framework and dataset to foster community adoption and reproducibility.
Yuhe Liu, Changhua Pei, Hang Wang et al.· SIGSOFT FSE Companion· 0 citations
