Open access

RAFE-XAI: A Retrieval-Augmented Feature Engineering and Explainable NLP Framework for Urban Infrastructure Risk Classification

Jul 2026 · Mathematics · 0 citations · 29 references

TL;DR

This study introduces RAFE-XAI, a retrieval-augmented feature engineering and explainable natural language processing framework for urban infrastructure risk classification that incorporates semantic sentence embeddings, retrieval-based evidence, neighborhood-derived label distributions, domain-specific risk indicators, infrastructure asset cues, location indicators, and evidence-based explainability.

Abstract

Urban infrastructure systems increasingly depend on textual reports generated by citizens, inspection teams, maintenance units, emergency platforms, and smart city services. Accurate identification of critical risks in these reports is essential for enhancing urban resilience and enabling timely decision-making. Nevertheless, urban infrastructure risk classification is challenging due to the brevity, noise, domain specificity, and context dependence of these reports. This study introduces RAFE-XAI, a retrieval-augmented feature engineering and explainable natural language processing framework for urban infrastructure risk classification. The term retrieval-augmented is used here in a classification-oriented sense: retrieved reports are used to construct additional features and evidence, not to generate output text as in Retrieval-Augmented Generation systems. The proposed framework incorporates semantic sentence embeddings, retrieval-based evidence, neighborhood-derived label distributions, domain-specific risk indicators, infrastructure asset cues, location indicators, and evidence-based explainability. The framework does not construct an explicit graph, adjacency matrix, graph neural network, or message-passing mechanism. Instead, retrieval is used to derive neighbor label-distribution features, which are combined with semantic embeddings and interpretable keyword, asset, and location indicators. To assess the effectiveness of this approach, UIR-Text, a semi-synthetic urban infrastructure risk dataset with scenario-level group splitting to mitigate data leakage, was constructed. Experimental results on UIR-Text show that fine-tuned DistilBERT achieves the strongest predictive performance, with Macro-F1 scores of 0.8278 for category classification, 0.9120 for binary critical-risk detection, and 0.3379 for four-level severity classification. Among the explainable feature-engineering models, RAFE-XAI with Random Forest achieves the strongest category classification performance, with Accuracy 0.8400, Macro-F1 0.8043, Weighted-F1 0.8444, and MCC 0.8062. These results suggest that fine-tuned transformers provide the highest predictive performance on this benchmark, while RAFE-XAI offers a transparent retrieval-augmented alternative that exposes retrieved evidence, neighbor label distributions, and domain cues. Four-level severity classification remains challenging, even with fine-tuned DistilBERT, indicating the need for richer impact-aware variables.

DOI Semantic Scholar

Read PDF

Similar papers

Open access Aug 2026

TMCAS: Efficient Large Language Model-Assisted Topic Modeling for Civil Aviation Safety Reports

This paper proposes TMCAS, an efficient large language model-assisted topic modeling framework for civil aviation safety reports that achieves superior clustering and interpretability while substantially reducing inference cost compared with document-wise LLM baselines.

Xiangge Li, Haofeng Wang, Xiuting Zhou et al. · Electronics · 0 citations

Open access Aug 2026

Leveraging Large Language Models for Automated Assessment and Mapping in Participatory Urban Planning

The findings demonstrate the feasibility of leveraging AI and LLMs to create a responsive and interactive platform that not only streamlines data collection but also enriches the participatory planning process.

Mohammad Hasan Zali, Mohammad Ghanbarei Baba ahmadi, Meysam Argany et al. · The International Archives o... · 0 citations

Open access Aug 2026

A retrieval-augmented and distribution-imbalance-aware contrastive framework for low-resource agricultural pest and disease named entity recognition with large language models

Amid the rapid advancement of smart agriculture, a substantial volume of unstructured knowledge embedded in agricultural pest and disease texts urgently necessitates structured representation through high-quality named entity recognition. However, Chinese agricultural domain entities exhibit pronounced long-tail distributions, coupled with scarce annotated samples and semantic boundaries heavily reliant on implicit domain-specific knowledge structures. These challenges lead to performance degradation and insufficient generalization capabilities of traditional sequence labeling models and general pre-trained models under low-resource scenarios. To address these issues, this paper proposes a parameter-efficient large model adaptation framework that integrates retrieval-augmented semantic conditioning modeling with distribution-imbalance-aware contrastive representation learning for agricultural pest and disease text entity recognition. The proposed method reframes agricultural named entity recognition as a structured prediction problem conditioned on semantic neighborhood variables. By constructing query-relevant semantic neighborhoods and organizing the retrieved examples as contextual demonstrations, the proposed method provides retrieval-conditioned references for more stable entity boundary determination. At the representation learning level, a category-aware contrastive optimization mechanism is introduced, prioritizing the construction of semantically similar hard negative samples to reshape the geometric structure of the embedding space and mitigate frequency-dominated optimization biases induced by long-tail distributions. For model adaptation, a low-rank parameter-efficient fine-tuning strategy is employed to enable controlled transfer of large language models to the agricultural domain, reducing training costs while preserving general semantic capabilities. Extensive experiments under multi-gradient low-resource settings are conducted on two Chinese agricultural pest and disease datasets, AgCNER and CropDiseaseNER. Experimental results demonstrate that the proposed framework significantly outperforms both traditional sequence labeling methods and conventional large model fine-tuning strategies across varying data scales. Specifically, compared with the BERT-BiLSTM baseline, the proposed framework achieves F1-score improvements of 6.75 percentage points in the AgCNER-3k low-resource scenario and 15.30 percentage points in the CropDiseaseNER-0.4k extreme low-resource scenario. These findings indicate that retrieval-augmented semantic conditioning modeling and distribution-imbalance-aware contrastive representation optimization collaboratively mitigate structural instability arising from low resources and long-tail distributions, offering an efficient and scalable pathway for adapting large models to agricultural knowledge graph construction and intelligent decision-making in smart agriculture.

Fuyong Liu, Zhaohui Du, Hongmei Fei et al. · Journal of King Saud Univers... · 0 citations

Aug 2026

AddressRAG: A Novel Retrieval Method for Toponym and Address Based on Knowledge Graph and Large Language Models

Efficient and precise toponym and address retrieval has become a cornerstone for sectors such as logistics, intelligent navigation, and urban planning. However, conventional address retrieval methods often struggle with semantic ambiguity, incomplete information, or nonstandard address formats, resulting in suboptimal retrieval accuracy and limited robustness. To tackle these challenges, this study proposes AddressRAG, an innovative intelligent retrieval framework that integrates Knowledge Graphs (KG) with Large Language Models (LLM). AddressRAG employs a custom Semantic Text Augmentation (STA) mechanism to enhance the administrative hierarchy and spatial constraints of the raw data. Then we construct an enhanced hierarchical knowledge graph based on prompt tuning. Furthermore, a hierarchical community reporting mechanism was introduced for AddressRAG to accurately capture macro‐level administrative constraints and micro‐level spatial relationships. Experiments on a cross‐city dataset showed that AddressRAG obtained higher observed mean scores in faithfulness, answer relevance, candidate retrieval, and administrative hierarchy consistency, with uncertainty quantified using bootstrap confidence intervals. This research provides critical technical support for scalable and adaptive toponym address retrieval.

Li Xu, Zhanlong Chen, Meng-Xi Zhang · Transactions on GIS · 0 citations

Open access Jul 2026

Retrieval-Augmented Large Language Model for Institutional Knowledge Management and Decision Assistance in Public Organizations

It is demonstrated that integrating semantic retrieval with grounded LLM generation can improve knowledge accessibility, transparency, and reliability for AI-assisted decision support in public organizations.

Yohanes Bowo Widodo · International Journal of Eng... · 0 citations

Preprint Aug 2026

GeoRisk-RAG: A Hierarchy-Aware Risk Framework for Improving RAG Reliability through Selective Answering

Current work on improving reliability in large language model (LLM)- generated answers has primarily leveraged Retrieval-Augmented Generation (RAG), knowledge-graph augmentation, and reinforcement learning. While these methods are adept at enhancing and measuring reliability through semantic similarity and faithfulness, they often struggle to distinguish semantic similarity from geographic validity. This is especially critical in natural hazard management domains where geographic granularity (i.e., town vs. city vs. state) is significant for decision-making, as responses valid in one municipality may not transfer to another. In such domains, a confidently wrong answer carries greater risk than abstaining. We present GeoRisk-RAG, a novel hierarchy-aware framework that addresses this geographic-validity gap through selective answering. This framework explicitly estimates geographic applicability using a Directed Acyclic Graph (DAG)-based distance for context retrieval before response generation. Experiments on a novel held-out wildfire-related question-answering (QA) dataset show that GeoRisk-RAG significantly reduces false confidence rates for location-dependent questions, lowering the rate to 0.009 compared with ~0.090 for standard semantic similarity and reranking baselines, while consistently achieving higher human preference alignment. This work provides a more comprehensive assessment of end-to-end RAG pipelines by integrating geographic validity and selective-answering behavior for safer decision-making in geospatial domains.

M. Ravi, Shailik Sarkar, Lulwah Alkulaib et al. · 0 citations