Jul 2026· 2026 IEEE 9th International Conference on Big Data and Artificial Intelligence (BDAI)· pp. 167-174· 0 citations· 32 references
Abstract
Multi-version iteration and cross-aircraft configuration differences in flight test restriction documents pose significant challenges to crew situational awareness. This paper presents an intelligent parsing and multi-dimensional comparison system based on large language models. An anchor-driven hierarchical partitioning strategy converts unstructured Word documents into a structured knowledge base covering all aircraft and all versions. A fault-tolerant comparison engine following a rule pre-screening, LLM fine-grained judgment and rule fallback pipeline extracts semantic differences across adjacent versions, cross-aircraft configurations and full historical traceability. A dual-layer importance assessment mechanism that integrates domain rules with LLM reasoning produces task-oriented and explainable priority rankings. Experiments on 29 authentic documents from five test aircraft show that the parsing accuracy reaches 97.8%, the F1 scores of three comparison tasks all exceed 89%, the module coverage of generated PDF reports reaches 98.3% and structural compliance reaches 100%. The system reduces crew document review time from hours to minutes. From an occupational health and safety perspective, fragmented and ambiguous safety-critical documentation represents an information hazard that may increase the probability of human error during flight-test preparation and execution. By transforming multi-version restriction documents into an auditable, importance-ranked, and task-oriented report, the proposed system acts as a digital risk-control measure that reduces crews' exposure to information discontinuity, highlights safety-relevant changes, and supports more consistent knowledge transfer during personnel rotation. These findings suggest that LLM-assisted document intelligence can contribute not only to document-processing efficiency, but also to the prevention of document-induced human-error risks in high-risk aviation workplaces.
Large-scale engineering projects generate continuous streams of compliance-critical documents, including material submissions, method statements, inspection and test plans, safety data sheets, and contractor certificates. Each must be verified against project specifications, regulatory codes, and contractual requirements. Current manual expert review is slow, inconsistent, and provides limited audit depth. Existing AI approaches typically use Retrieval-Augmented Generation to retrieve relevant clauses but do not conduct structured, rule-bound verification. This paper presents an agentic document verification framework that moves beyond passive retrieval to active, rule-aware compliance checking. The system uses a semantically indexed knowledge base built from project specifications, regulatory standards, and historical approval records. A dedicated Verification Agent decomposes documents into structured claim units, including numerical parameters, referenced standards, tabular test results, and graphical certificates. These are evaluated against dynamically constructed project rule sets using a Chain-of-Thought inference pattern. The framework generates compliance reports with pass, fail, or query verdicts, confidence scores, and traceable evidence bindings for each decision point. Material submissions are the primary validation domain because their dense technical content, cross-referenced tables, graphs, and third-party certificates rigorously test multi-modal parsing and verification capabilities. Validation used an industrial pilot across 10 live projects in the Electrical and Mechanical engineering sector. Results from 63 processed submissions show a 70.9% reduction in average review time, from 52.5 minutes under the existing digital workflow to 15.3 minutes with the AI-assisted system. Results also show an 88% system agreement rate, with human overwrites required in only 12% of verdicts. By incorporating a Propose-Decide-Evidence governance model, the system retains the human engineer as final decision-maker while establishing an efficient, auditable, continuously improving compliance workflow.
Ka Tai Lau, Man Chit, Jovian Cheung et al.· AHFE International· 0 citations
FlightLLM, a prior-guided semantic LLM-based approach for interpretable flight safety analysis that achieves competitive classification performance while generating direct and reasonable explanations for event causes is proposed.
Production customer-service bots must improve answer quality across iterative releases, yet large language models must not bypass evidence boundaries, policy rules, or human-handoff safeguards. We present an \textbf{Evidence-Grounded Customer-Service Agent Workflow} deployed in a real-world customer-service setting. BM25 recall, issue-title-vector recall, issue-description-vector recall, weighted RRF fusion, and cross-encoder reranking construct grounded FAQ evidence for controlled LLM decisions. Policy-guided orchestration then combines this RAG evidence with scenario-specific rule evidence, conversation memory, and clarification state inside a fixed LangGraph DAG~\cite{langgraph2024}. The paper contributes three reusable deployment patterns: \textbf{hybrid RAG evidence construction}, where multi-channel retrieval and reranking produce auditable FAQ candidates; \textbf{evidence-grounded issue/action decision}, where an Evidence-Grounded Decision Module selects an issue/action from typed FAQ evidence and scenario-specific rule evidence; and \textbf{trace-driven RAG and reranker improvement}, where traces diagnose whether failures come from recall, ranking, final candidate selection, clarification, rule-derived evidence, or action policy, and where reranker fine-tuning is evaluated not only for in-domain gain but also for forgetting risk.
Chunming Wu, Dafei Qiu, Congde Yuan et al.· 0 citations
This work presents an AI-assisted approach that generates candidate hazard scenarios from NASA's Aviation Safety Reporting System (ASRS), and proposes a hybrid variant, conditioning narrative generation on a structured hypothesis produced via evolutionary abduction, improving correctness and reducing variability.
Cristian Mascia, R. Pietrantuono, Daniel Rodríguez et al.· 0 citations
In the context of industrial digitalization and the widespread adoption of process automation systems, Knowledge Management Systems (KMS) play a key role in providing operational personnel with up-to-date instructions and regulations. However, the inherent ambiguity of natural language in technical documentation remains a serious obstacle, leading to incorrect operator actions, process deviations, and increased safety risks. This article investigates the integration of Large Language Models (LLMs) into KMS and its impact on user experience and human–machine interaction in industrial automation environments. A method called Semantic Latent Choice Detection is presented, designed to systematically identify interpretation ambiguities in process instructions and operator commands. Unlike existing approaches that require access to the internal model architecture (“white box”) or token-level logits, the proposed method is logit-free and operates with closed commercial LLMs (“black box”) via standard API interfaces. The method analyzes the semantic similarity of binary text blocks and polysemous terms within the context of a specific technological process. Using a metallurgical production case study, we demonstrate how the system detects hidden semantic collisions (e.g., the difference between “adding ferroalloys into the ladle” and “feeding ferroalloys onto the conveyor”) that are missed by traditional rule-based validation methods. Instead of arbitrarily selecting an interpretation, the system initiates a clarification request to the human operator, thereby reducing cognitive load, preventing erroneous automated decisions, and increasing trust in the KMS. An empirical evaluation conducted in a real-world industrial setting (unit control rooms and dispatch centers) shows a statistically significant reduction in errors related to misinterpretation of process regulations. The article contributes to the fields of automation engineering, knowledge management, and human-centered automation by proposing a novel method for validating operational instructions in high-risk industrial environments.
Viktor A. Vedeneev, V. Kondratiev, K. Suslov et al.· Automation· 1 citation
This study aims to construct and validate a retrieval-augmented generation (RAG)-driven workflow for automatically generating SJT items and provides preliminary evidence for the feasibility of an automated development pathway for psychological assessment tools based on LLMs and RAG technology.
Yaqian Liu, Qida Hao, Jian Cheng et al.· AHFE International· 0 citations