SPELUNKER: Item Similarity Search Using Large Language Models and Custom K-Nearest Neighbors
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909806459092992 |
|---|---|
| author | Rodrigues, Ana Mata, João Rego, Rui |
| author_facet | Rodrigues, Ana Mata, João Rego, Rui |
| contents | This paper presents a hybrid system for intuitive item similarity search that combines a Large Language Model (LLM) with a custom K-Nearest Neighbors (KNN) algorithm. Unlike black-box dense vector systems, this architecture provides superior interpretability by first using an LLM to convert natural language queries into structured, attribute-based searches. This structured query then serves as input to a custom KNN algorithm with a BallTree search strategy, which uses a heterogeneous distance metric to preserve distinct data types. Our evaluation, conducted on a dataset of 500 wine reviews, demonstrates the system's effectiveness. The LLM achieved an F1-score of 0.9779 in information extraction, while also demonstrating high fidelity with a Jaro string similarity of 0.9321. When we augmented the KNN algorithm with LLM-based re-ranking, we observed a statistically significant improvement in recall (p=0.013), indicating the LLM's ability to identify and promote relevant items that align with nuanced user intent. This approach effectively bridges the gap between human language and machine-understandable item representations, offering a transparent and nuanced search capability. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_21323 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SPELUNKER: Item Similarity Search Using Large Language Models and Custom K-Nearest Neighbors Rodrigues, Ana Mata, João Rego, Rui Information Retrieval This paper presents a hybrid system for intuitive item similarity search that combines a Large Language Model (LLM) with a custom K-Nearest Neighbors (KNN) algorithm. Unlike black-box dense vector systems, this architecture provides superior interpretability by first using an LLM to convert natural language queries into structured, attribute-based searches. This structured query then serves as input to a custom KNN algorithm with a BallTree search strategy, which uses a heterogeneous distance metric to preserve distinct data types. Our evaluation, conducted on a dataset of 500 wine reviews, demonstrates the system's effectiveness. The LLM achieved an F1-score of 0.9779 in information extraction, while also demonstrating high fidelity with a Jaro string similarity of 0.9321. When we augmented the KNN algorithm with LLM-based re-ranking, we observed a statistically significant improvement in recall (p=0.013), indicating the LLM's ability to identify and promote relevant items that align with nuanced user intent. This approach effectively bridges the gap between human language and machine-understandable item representations, offering a transparent and nuanced search capability. |
| title | SPELUNKER: Item Similarity Search Using Large Language Models and Custom K-Nearest Neighbors |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2509.21323 |