Explore the vast range of titles available.

Generative pre-trained language models have demonstrated strong capabilities in natural language processing tasks, but they still suffer from “fact hallucination” and weak knowledge timeliness in open-domain question answering and text generation. To improve the accuracy and knowledge consistency of generated content, this paper proposes a Knowledge Graph-based Retrieval Enhanced Generation Model (KG-RAG), which integrates structured knowledge graphs into traditional RAG architectures to enhance the model’s ability to understand semantic and inferential relationships. The model designs a dual-channel retrieval mechanism: on one hand, it uses Dense Passage Retrieval (DPR) for vectorized retrieval of unstructured texts; on the other hand, it employs graph neural networks (GNN) to structurally retrieve semantic paths within the knowledge graph, and through path attention mechanisms, it filters out the most relevant entity relationship chains to guide the knowledge injection module. Experimental results on the Natural Questions and PubMedQA datasets show that KG-RAG outperforms the original RAG model across multiple evaluation metrics. On the Natural Questions dataset, the ROUGE-L score of the KG-RAG model improves from 41.2 to 46.9, the BLEU score rises from 31.5 to 38.7, and the FactScore increases by 13.6%, significantly enhancing the knowledge consistency of the generated text. In the PubMedQA task, KG-RAG achieves an accuracy rate of 81% in medical question answering. 3%, an improvement of 6.8% points over RAG, demonstrates its advantage in knowledge reasoning within specialized fields. Furthermore, case studies show that KG-RAG can effectively integrate entity paths from knowledge graphs to generate more logical and factual answers in complex question-answering tasks. This method has broad application prospects in intelligent question-answering systems, multi-turn conversations, and educational Q&A scenarios. Future research will consider introducing dynamic knowledge update mechanisms and multimodal graph information to further enhance the capabilities and adaptability of KG-RAG in real-world tasks.

The rapid retrieval and precise acquisition of land use approval information are crucial for enhancing the efficiency and quality of land use approval, as well as for promoting the intelligent transformation of land use approval processes. As an advanced retrieval method, question-answering (Q&A) technology has become a core technical support for addressing current issues such as low approval efficiency and difficulty in obtaining information. However, existing Q&A technologies suffer from significant hallucination problems and limitations in considering spatiotemporal factors in the land use approval domain. To effectively address these issues, this study proposes a spatiotemporal–semantic coupling intelligent Q&A method for land use approval based on knowledge graphs (KGs) and intelligent agent technology, aiming to enhance the efficiency and quality of land use approval. Firstly, a land use approval knowledge graph (LUAKG) is constructed, systematically integrating domain knowledge such as policy clauses, legal regulations, and approval procedures. Then, by combining large language models (LLMs) and intelligent agent technology, a spatiotemporal–semantic coupling Q&A framework is designed. Through the use of spatiotemporal analysis tools, this framework can comprehensively consider spatial, temporal, and semantic factors when handling land approval tasks, enabling dynamic decision-making and precise reasoning. The research results show that, compared to traditional Q&A based on LLMs and Q&A based on retrieval-enhanced generation (RAG), the proposed method improves accuracy by 16% and 9% in general knowledge Q&A tasks. In the project review Q&A task, F1 scores and accuracy increase by 2% and 9%, respectively, compared to RAG-QA. Particularly, under the spatiotemporal–semantic multidimensional analysis, the improvement in F1 score and accuracy ranges from 2 to 6% and 7 to 10%, respectively.

The rapid retrieval and precise acquisition of land use approval information are crucial for enhancing the efficiency and quality of land use approval, as well as for promoting the intelligent transformation of land use approval processes. As an advanced retrieval method, question-answering (Q&A) technology has become a core technical support for addressing current issues such as low approval efficiency and difficulty in obtaining information. However, existing Q&A technologies suffer from significant hallucination problems and limitations in considering spatiotemporal factors in the land use approval domain. To effectively address these issues, this study proposes a spatiotemporal–semantic coupling intelligent Q&A method for land use approval based on knowledge graphs (KGs) and intelligent agent technology, aiming to enhance the efficiency and quality of land use approval. Firstly, a land use approval knowledge graph (LUAKG) is constructed, systematically integrating domain knowledge such as policy clauses, legal regulations, and approval procedures. Then, by combining large language models (LLMs) and intelligent agent technology, a spatiotemporal–semantic coupling Q&A framework is designed. Through the use of spatiotemporal analysis tools, this framework can comprehensively consider spatial, temporal, and semantic factors when handling land approval tasks, enabling dynamic decision-making and precise reasoning. The research results show that, compared to traditional Q&A based on LLMs and Q&A based on retrieval-enhanced generation (RAG), the proposed method improves accuracy by 16% and 9% in general knowledge Q&A tasks. In the project review Q&A task, F1 scores and accuracy increase by 2% and 9%, respectively, compared to RAG-QA. Particularly, under the spatiotemporal–semantic multidimensional analysis, the improvement in F1 score and accuracy ranges from 2 to 6% and 7 to 10%, respectively.

Although large language models (LLMs) have demonstrated powerful capabilities in general domains, they may output information in the medical field that could be incorrect, incomplete, or fabricated. They are also unable to answer personalized questions related to departments or individual patient health. Retrieval-augmented generation technology (RAG) can introduce external knowledge bases and utilize the retrieved information to generate answers or text, thereby enhancing prediction accuracy. We introduced internal departmental data and 17 commonly used gastroenterology guidelines as a knowledge base. Based on RAG, we developed the Endo-chat medical chat application, which can answer patient questions related to gastrointestinal endoscopy. We then included 200 patients undergoing gastrointestinal endoscopy, randomly divided into two groups of 100 each, for a questionnaire survey. A comparative evaluation was conducted between the traditional manual methods and Endo-chat. Compared to ChatGPT, Endo-chat can accurately and professionally answer relevant questions after matching the knowledge base. In terms of response efficiency, completeness, and patient satisfaction, Endo-chat outperformed manual methods significantly. There was no statistical difference in response accuracy between the two. Patients showed a preference for AI services and expressed support for the introduction of AI. All participating nurses in the survey believed that introducing AI could reduce nursing workload. In clinical practice, Endo-chat can be used as a highly effective auxiliary tool for digestive endoscopic care.

The Retrieval-Augmented Generation (RAG) framework shows great potential in terms of improving the reasoning and knowledge utilization capabilities of language models. However, most existing RAG systems heavily rely on large language models (LLMs) and suffer severe performance degradation when using small language models (SLMs), which limits their efficiency and deployment in resource-constrained environments. To address this challenge, we propose Retrieval-Adaptive-Planning RAG (RAP-RAG), a lightweight and high-efficiency RAG framework with adaptive retrieval task planning that is compatible with both SLMs and LLMs simultaneously. RAP-RAG is built on three key components: (1) a heterogeneous weighted graph index that integrates semantic similarity and structural connectivity; (2) a set of retrieval methods that balance efficiency and reasoning power; and (3) an adaptive planner that dynamically selects appropriate strategies based on query features. Experiments on the LiHua-World, MultiHop-RAG, and Hybrid-SQuAD datasets show that RAP-RAG consistently outperforms representative baseline models such as GraphRAG, LightRAG, and MiniRAG. Compared to lightweight baselines, RAP-RAG achieves 3–5% accuracy improvement while maintaining high efficiency and maintains comparable efficiency in both small and large model settings. In addition, our proposed framework reduces storage size by 15% compared to mainstream frameworks. Component analysis further confirms the necessity of weighted graphs and adaptive programming for robust retrieval under multi-hop reasoning and heterogeneous query conditions. These results demonstrate that RAP-RAG is a practical and efficient framework for retrieval-enhanced generation, suitable for large-scale and resource-constrained scenarios.

Dense retrievers rely heavily on high-quality training triplets, yet existing data construction strategies remain inadequate for reasoning-intensive retrieval tasks involving multi-hop reasoning, entity relation tracing, and implicit evidence composition. Positive samples are often based on shallow semantic relevance and fail to capture explicit reasoning chains, while negative samples are typically sampled from lexical overlap or random candidates and therefore provide limited supervision for learning clear decision boundaries. To address these issues, we propose S-Gens, a structure-aware synthetic data generation framework for enhancing reasoning-intensive dense retrieval. S-Gens uses relation paths in an external knowledge graph to synthesize queries and structurally consistent positive samples, and further constructs semantically similar but structurally inconsistent hard negatives. To improve data reliability, we introduce a Siamese graph neural network-based consistency filtering mechanism. Because S-Gens operates entirely during offline supervision construction, it remains model-agnostic, preserves the original inference architecture, and is complementary to graph-guided retrieval or RAG pipelines that inject structure online. Experiments on five benchmark datasets show that S-Gens consistently improves multiple trainable retrievers, with the largest gains on multi-hop reasoning tasks such as WebQSP and HotpotQA. These results indicate that structure-aware synthetic supervision can effectively improve dense retrieval in reasoning-intensive settings.

Sepsis is a severe syndrome of organ dysfunction caused by infection; it has high heterogeneity and high in-hospital mortality, representing a grim clinical challenge for precision medicine in critical care. We aimed to extract reported sepsis biomarkers to provide users with comprehensive biomedical information and integrate retrieval augmented generation (RAG) and prompt engineering to enhance the accuracy, stability, and interpretability of clinical decisions recommended by large language models (LLMs). To address the challenge, we established and updated the first knowledge-enhanced platform, MetaSepsisKnowHub, comprising 427 sepsis biomarkers and 423 studies, aiming to systematically collect and annotate sepsis biomarkers to guide personalized clinical decision-making in the diagnosis and treatment of human sepsis. We curated a tailored LLM framework incorporating RAG and prompt engineering and incorporated 2 performance evaluation scales: the System Usability Scale and the Net Promoter Score. The overall quantitative ratings of expert-reviewed clinical recommendations based on RAG surpassed baseline responses generated by 4 LLMs and showed a statistically significant improvement in textual questions (GPT-4: mean 75.79, SD 7.11 vs mean 81.59, SD 9.87; P=.02; GPT-4o: mean 70.36, SD 7.63 vs mean 77.98, SD 13.26; P=.02; Qwen2.5-instruct: mean 77.08 SD 3.75 vs mean 85.46, SD 7.27; P<.001; and DeepSeek-R1: mean 77.67, SD 3.66 vs mean 86.42, SD 8.56; P<.001), but no significant statistical differences could be measured in clinical scenarios. The RAG assessment score comparing RAG-based responses and expert-provided benchmark answers illustrated prominent factual correctness, accuracy, and knowledge recall compared to the baseline responses. After use, the average the System Usability Scale score was 82.20 (SD 14.17) and the Net Promoter Score was 72, demonstrating high user satisfaction and loyalty. We highlight the pioneering MetaSepsisKnowHub platform, and we show that combining MetaSepsisKnowHub with RAG can minimize limitations on precision and maximize the breadth of LLMs to shorten the bench-to-bedside distance, serving as a knowledge-enhanced paradigm for future application of artificial intelligence in critical care medicine.

Retrieval-augmented generation (RAG) has shown strong potential for knowledge-intensive tasks, yet its performance degrades sharply when applied to structured long-context documents in power systems, where dense entity–relation dependencies, cross-document references, and strict traceability requirements exist. To address this Structured Long-Context RAG (SLCRAG) challenge, this paper proposes a hierarchical graph-enhanced RAG (HG-RAG) framework tailored for power system question answering. HG-RAG constructs a globally consistent knowledge graph via sliding-window entity–relation extraction to mitigate semantic fragmentation, and employs multi-granularity structured indexing for precise entity/relation retrieval. A hierarchical structured retrieval mechanism with multi-hop expansion and semantic distillation maximizes recall while minimizing redundancy. Furthermore, a regex-enhanced retrieval module records authoritative file_path provenance and constrains downstream retrieval to the same source documents, effectively eliminating cross-document interference—especially in cases where different documents contain similar entities and relations. Combined with version control and deduplication-merging, HG-RAG supports incremental knowledge updates with minimal forgetting and negligible token overhead. Experimental results on a domain-authentic power system QA dataset demonstrate that HG-RAG outperforms LightRAG and GraphRAG, achieving up to 85.47% accuracy in short-answer tasks with significantly lower token consumption. Ablation studies confirm that semantic distillation primarily improves precision and efficiency, while regex-enhanced retrieval safeguards recall in edge cases.

This paper presents two algorithms used to derive Aerosol Optical Depth (AOD) from a synergy of satellite and ground-based observations, as well as aerosol transport model output. The Spinning Enhanced Visible Infrared Radiometer (SEVIRI) instrument on board Meteosat Second Generation (MSG) allows us to monitor aerosol loading over land at high temporal and spatial resolution. We present the algorithms which were fed with the data acquired via the SEVIRI channel 1, and also channels 1 and 3 in conjunction. In both cases, the surface reflectance is the most important parameter that should be estimated during the retrieval process. The surface properties are estimated during days with a low AOD (less than 0.1 at 500 nm) based on the radiance measured by the SEVIRI detector and aerosol optical properties modeled with the aerosol transport model or measured by the MODIS sensor. For data from the model and the MODIS, ground-based stations equipped with a sun photometer have been applied to correct the AOD fields using the optimal interpolation method. By assuming that surface reflectance at the SEVIRI resolution changes slowly over time, the AOD has been computed. Comparison of the SEVIRI AOD with the sun photometer observations shows good agreement/correlation. The mean bias is small (an order of 0.01–0.02) and the root mean square (rms) is about 0.05 for both one- and two-channel methods. In addition, the rms for the one-channel method does not change with the AOD.