Enhanced Semantic Retrieval with Structured Prompt and Dimensionality Reduction for Big Data
The exponential increase in textual data generated across sectors such as healthcare, finance, and smart manufacturing has intensified the need for effective Big Data analytics. Large language models (LLMs) have become critical tools because of their advanced language processing capabilities. Howeve...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-07-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/13/15/2469 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849406237125378048 |
|---|---|
| author | Donghyeon Kim Minki Park Jungsun Lee Inho Lee Jeonghyeon Jin Yunsick Sung |
| author_facet | Donghyeon Kim Minki Park Jungsun Lee Inho Lee Jeonghyeon Jin Yunsick Sung |
| author_sort | Donghyeon Kim |
| collection | DOAJ |
| description | The exponential increase in textual data generated across sectors such as healthcare, finance, and smart manufacturing has intensified the need for effective Big Data analytics. Large language models (LLMs) have become critical tools because of their advanced language processing capabilities. However, their static nature limits their ability to incorporate real-time and domain-specific knowledge. Retrieval-augmented generation (RAG) addresses these limitations by enriching LLM outputs through external content retrieval. Nevertheless, traditional RAG systems remain inefficient, often exhibiting high retrieval latency, redundancy, and diminished response quality when scaled to large datasets. This paper proposes an innovative structured RAG framework specifically designed for large-scale Big Data analytics. The framework transforms unstructured partial prompts into structured semantically coherent partial prompts, leveraging element-specific embedding models and dimensionality reduction techniques, such as principal component analysis. To further improve the retrieval accuracy and computational efficiency, we introduce a multi-level filtering approach integrating semantic constraints and redundancy elimination. In the experiments, the proposed method was compared with structured-format RAG. After generating prompts utilizing two methods, silhouette scores were computed to assess the quality of embedding clusters. The proposed method outperformed the baseline by improving the clustering quality by 32.3%. These results demonstrate the effectiveness of the framework in enhancing LLMs for accurate, diverse, and efficient decision-making in complex Big Data environments. |
| format | Article |
| id | doaj-art-0cb4cedf7e424b8f90dcdc984781a8ec |
| institution | Kabale University |
| issn | 2227-7390 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematics |
| spelling | doaj-art-0cb4cedf7e424b8f90dcdc984781a8ec2025-08-20T03:36:27ZengMDPI AGMathematics2227-73902025-07-011315246910.3390/math13152469Enhanced Semantic Retrieval with Structured Prompt and Dimensionality Reduction for Big DataDonghyeon Kim0Minki Park1Jungsun Lee2Inho Lee3Jeonghyeon Jin4Yunsick Sung5Department of Computer Information and Communication Engineering, Dongguk University-Seoul, Seoul 04620, Republic of KoreaDepartment of Computer Information and Communication Engineering, Dongguk University-Seoul, Seoul 04620, Republic of KoreaDepartment of Computer Information and Communication Engineering, Dongguk University-Seoul, Seoul 04620, Republic of KoreaDepartment of Computer Science and Artificial Intelligence, Dongguk University-Seoul, Seoul 04620, Republic of KoreaDepartment of Computer Science and Artificial Intelligence, Dongguk University-Seoul, Seoul 04620, Republic of KoreaDepartment of Computer Science and Artificial Intelligence, Dongguk University-Seoul, Seoul 04620, Republic of KoreaThe exponential increase in textual data generated across sectors such as healthcare, finance, and smart manufacturing has intensified the need for effective Big Data analytics. Large language models (LLMs) have become critical tools because of their advanced language processing capabilities. However, their static nature limits their ability to incorporate real-time and domain-specific knowledge. Retrieval-augmented generation (RAG) addresses these limitations by enriching LLM outputs through external content retrieval. Nevertheless, traditional RAG systems remain inefficient, often exhibiting high retrieval latency, redundancy, and diminished response quality when scaled to large datasets. This paper proposes an innovative structured RAG framework specifically designed for large-scale Big Data analytics. The framework transforms unstructured partial prompts into structured semantically coherent partial prompts, leveraging element-specific embedding models and dimensionality reduction techniques, such as principal component analysis. To further improve the retrieval accuracy and computational efficiency, we introduce a multi-level filtering approach integrating semantic constraints and redundancy elimination. In the experiments, the proposed method was compared with structured-format RAG. After generating prompts utilizing two methods, silhouette scores were computed to assess the quality of embedding clusters. The proposed method outperformed the baseline by improving the clustering quality by 32.3%. These results demonstrate the effectiveness of the framework in enhancing LLMs for accurate, diverse, and efficient decision-making in complex Big Data environments.https://www.mdpi.com/2227-7390/13/15/2469big datalarge language models (LLMs)retrieval-augmented generation (RAG)structured promptsemantic embeddingdimensionality reduction |
| spellingShingle | Donghyeon Kim Minki Park Jungsun Lee Inho Lee Jeonghyeon Jin Yunsick Sung Enhanced Semantic Retrieval with Structured Prompt and Dimensionality Reduction for Big Data Mathematics big data large language models (LLMs) retrieval-augmented generation (RAG) structured prompt semantic embedding dimensionality reduction |
| title | Enhanced Semantic Retrieval with Structured Prompt and Dimensionality Reduction for Big Data |
| title_full | Enhanced Semantic Retrieval with Structured Prompt and Dimensionality Reduction for Big Data |
| title_fullStr | Enhanced Semantic Retrieval with Structured Prompt and Dimensionality Reduction for Big Data |
| title_full_unstemmed | Enhanced Semantic Retrieval with Structured Prompt and Dimensionality Reduction for Big Data |
| title_short | Enhanced Semantic Retrieval with Structured Prompt and Dimensionality Reduction for Big Data |
| title_sort | enhanced semantic retrieval with structured prompt and dimensionality reduction for big data |
| topic | big data large language models (LLMs) retrieval-augmented generation (RAG) structured prompt semantic embedding dimensionality reduction |
| url | https://www.mdpi.com/2227-7390/13/15/2469 |
| work_keys_str_mv | AT donghyeonkim enhancedsemanticretrievalwithstructuredpromptanddimensionalityreductionforbigdata AT minkipark enhancedsemanticretrievalwithstructuredpromptanddimensionalityreductionforbigdata AT jungsunlee enhancedsemanticretrievalwithstructuredpromptanddimensionalityreductionforbigdata AT inholee enhancedsemanticretrievalwithstructuredpromptanddimensionalityreductionforbigdata AT jeonghyeonjin enhancedsemanticretrievalwithstructuredpromptanddimensionalityreductionforbigdata AT yunsicksung enhancedsemanticretrievalwithstructuredpromptanddimensionalityreductionforbigdata |