Declarative Techniques for NL Queries over Heterogeneous Data
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909856072466432 |
|---|---|
| author | Khabiri, Elham Kephart, Jeffrey O. Heath III, Fenno F. Jayaraman, Srideepika Tipu, Fateh A. Li, Yingjie Shah, Dhruv Fokoue, Achille Bhamidipaty, Anu |
| author_facet | Khabiri, Elham Kephart, Jeffrey O. Heath III, Fenno F. Jayaraman, Srideepika Tipu, Fateh A. Li, Yingjie Shah, Dhruv Fokoue, Achille Bhamidipaty, Anu |
| contents | In many industrial settings, users wish to ask questions in natural language, the answers to which require assembling information from diverse structured data sources. With the advent of Large Language Models (LLMs), applications can now translate natural language questions into a set of API calls or database calls, execute them, and combine the results into an appropriate natural language response. However, these applications remain impractical in realistic industrial settings because they do not cope with the data source heterogeneity that typifies such environments. In this work, we simulate the heterogeneity of real industry settings by introducing two extensions of the popular Spider benchmark dataset that require a combination of database and API calls. Then, we introduce a declarative approach to handling such data heterogeneity and demonstrate that it copes with data source heterogeneity significantly better than state-of-the-art LLM-based agentic or imperative code generation systems. Our augmented benchmarks are available to the research community. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_16470 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Declarative Techniques for NL Queries over Heterogeneous Data Khabiri, Elham Kephart, Jeffrey O. Heath III, Fenno F. Jayaraman, Srideepika Tipu, Fateh A. Li, Yingjie Shah, Dhruv Fokoue, Achille Bhamidipaty, Anu Databases Artificial Intelligence Software Engineering In many industrial settings, users wish to ask questions in natural language, the answers to which require assembling information from diverse structured data sources. With the advent of Large Language Models (LLMs), applications can now translate natural language questions into a set of API calls or database calls, execute them, and combine the results into an appropriate natural language response. However, these applications remain impractical in realistic industrial settings because they do not cope with the data source heterogeneity that typifies such environments. In this work, we simulate the heterogeneity of real industry settings by introducing two extensions of the popular Spider benchmark dataset that require a combination of database and API calls. Then, we introduce a declarative approach to handling such data heterogeneity and demonstrate that it copes with data source heterogeneity significantly better than state-of-the-art LLM-based agentic or imperative code generation systems. Our augmented benchmarks are available to the research community. |
| title | Declarative Techniques for NL Queries over Heterogeneous Data |
| topic | Databases Artificial Intelligence Software Engineering |
| url | https://arxiv.org/abs/2510.16470 |