paper-with-me

홈 › Papers

Traceable Knowledge Graph Reasoning Enables LLM-Assisted Decision Support for Industrial VOCs in the Steel Industry

2026-05-26 · Changqing Su, Yu Ding, Zuhong Lin, Hongyu Liu, Xi He, Zheng Zeng, Liqing Li arxiv

Key knowledge for steel-industry volatile organic compounds (VOCs) governance is scattered across unstructured scientific literature, making it difficult to integrate process, pollutant, and control-technology evidence and increasing the risk of hallucination when general large language models (LLMs) answer low-frequency industrial questions. Here we developed Chat-ISV, a knowledge graph (KG) enhanced multi-agent Q&A system that parses a curated steel-industry VOCs literature corpus, constructs a Neo4j KG with 27180 nodes and 81779 semantic edges, and combines prompt-constrained extraction, chunk-centered topology optimization, multi-agent routing, source-backtracking retrieval, local literature retrieval, open-domain knowledge access, and interactive subgraph visualization. Benchmark tests and 400 expert blind evaluations showed that topology optimization reduced isolated nodes from 57% to 4.08% and that Chat-ISV achieved high factual reliability, with 96.93% precision, 72.63% recall, an F1-score of 0.830, and a mean score of 1.69/2.00. By converting fragmented environmental-engineering literature into traceable, queryable, and decision-support-oriented knowledge, Chat-ISV establishes a scalable environmental-informatics paradigm for reliable LLM deployment and intelligent pollution-control decision support in specialized industrial domains.

📄 PDF Abstract BibTeX arXiv:2605.27071

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Towards Agentic Defect Reasoning: A Graph-Assisted Retrieval Framework for Laser Powder Bed Fusion

2026-04-05 · Muhammad Rizwan Awan, Volker Pickert, Muhammad Waqar Ashraf, Saleh Ali 외 arxiv

Laser Powder Bed Fusion (LPBF) is highly sensitive to process parameters, which influence defect formation through complex thermal and fluid mechanisms. However, defect-related knowledge is dispersed across the literatur…

IdeaForge: A Knowledge Graph-Grounded Multi-Agent Framework for Cross-Methodology Innovation Analysis and Patent Claim Generation

2026-05-13 · Joy Bose arxiv

Current AI-assisted innovation systems typically apply a single ideation methodology (such as TRIZ or Design Thinking) using sequential prompt-based workflows that do not preserve intermediate reasoning structure. As a r…

Facilitating automated conversion of scientific knowledge into scientific simulation models with the Machine Assisted Generation, Calibration, and Comparison (MAGCC) Framework

2022-04-21 · Chase Cockrell, Scott Christley, Gary An

The Machine Assisted Generation, Comparison, and Calibration (MAGCC) framework provides machine assistance and automation of recurrent crucial steps and processes in the development, implementation, testing, and use of s…

Code Generation

Graph-Native Reinforcement Learning Enables Traceable Scientific Hypothesis Generation through Conceptual Recombination

2026-07-01 · Subhadeep Pal, Shashwat Sourav, Tirthankar Ghosal, Markus J. Buehler hf

Accelerating materials discovery requires AI systems that can generate scientifically valid hypotheses through multi-step, domain-grounded reasoning. Standard large language models often produce fluent but weakly traceab…

Reinforcement Learning

DysLexLens: A Low-Resource LLM Framework for Analysing Dyslexic Learners Insights from Online Forums

2026-06-26 · Dana Rezazadegan, Atie Kia, Phongpadid Nandavong, Dominique Carlon 외 arxiv

Dyslexic learners increasingly use artificial intelligence (AI) tools to support reading, writing, organisation, and study-related tasks. However, their lived experiences with these tools remain largely underexamined. Th…