ArticleScientific reports2026
Enhancing the capabilities of large language models for API calls through knowledge graphs.
Article in Scientific reports, 2026. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Not yet cited in PubMed.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
0 citing papers in PubMed.
No citing paper in PubMed yet.
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
5 authors.
Funding
No grant is acknowledged in the PubMed record.
Abstract
API calls by large language model (LLM) represent a cutting-edge technique in data analysis. However, the potential of LLM to effectively utilize tools through API calls remains underexplored in knowledge-intensive sectors such as the meteorological industry. In this paper, we propose a system, named KG2data, that integrates knowledge graphs, LLM, React agents, and tool usage technologies to perform API calls for intelligent data acquisition and query handling in the meteorological domain. We test the accuracy of the system's API calls using a virtual API. The baseline systems for comparison are chat2data (KG2data without knowledge) and RAG2data (KG2data with a vector database replacing the knowledge graph). Our experimental results demonstrate that the proposed system (1.43%, 0% and 88.57% in 3 evaluation metrics) outperforms RAG2data (16%, 10% and 72.14% in 3 evaluation metrics) and chat2data (7.14%, 8.57% and 71.43% in 3 evaluation metrics) in terms of failure rate of name recognition, failure rate of hallucination recognition and accuracy rate for API calls. Our system integrates knowledge graph, LLM, and ReAct-master agent technologies. Unlike current LLM used for API calls, our system overcomes the challenge of limited domain-specific knowledge of LLM, which often makes it difficult to address complex queries containing specialized terminology or lengthy questions. By utilizing knowledge graphs as long-term memory, our system significantly improves conten-retrieval coverage, handling of complex queries, industry-specific logical reasoning, deep semantic relationships among entities, and the integration of heterogeneous data. Additionally, it addresses the high computational costs associated with training or fine-tuning LLM, making it more adaptable to the dynamic nature of domain knowledge and APIs. In summary, the KG2data system offers a fresh perspective for intelligent knowledge-based question answering and data analysis in knowledge-intensive industries.
Indexed as
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.