DBRouting: Routing End User Queries to Databases for Answerability
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866929688855707648 |
|---|---|
| author | Mandal, Priyangshu Patwardhan, Manasi Patidar, Mayur Vig, Lovekesh |
| author_facet | Mandal, Priyangshu Patwardhan, Manasi Patidar, Mayur Vig, Lovekesh |
| contents | Enterprise level data is often distributed across multiple sources and identifying the correct set-of data-sources with relevant information for a knowledge request is a fundamental challenge. In this work, we define the novel task of routing an end-user query to the appropriate data-source, where the data-sources are databases. We synthesize datasets by extending existing datasets designed for NL-to-SQL semantic parsing. We create baselines on these datasets by using open-source LLMs, using both pre-trained and task specific embeddings fine-tuned using the training data. With these baselines we demonstrate that open-source LLMs perform better than embedding based approach, but suffer from token length limitations. Embedding based approaches benefit from task specific fine-tuning, more so when there is availability of data in terms of database specific questions for training. We further find that the task becomes more difficult (i) with an increase in the number of data-sources, (ii) having data-sources closer in terms of their domains,(iii) having databases without external domain knowledge required to interpret its entities and (iv) with ambiguous and complex queries requiring more fine-grained understanding of the data-sources or logical reasoning for routing to an appropriate source. This calls for the need for developing more sophisticated solutions to better address the task. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_16220 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DBRouting: Routing End User Queries to Databases for Answerability Mandal, Priyangshu Patwardhan, Manasi Patidar, Mayur Vig, Lovekesh Computation and Language Enterprise level data is often distributed across multiple sources and identifying the correct set-of data-sources with relevant information for a knowledge request is a fundamental challenge. In this work, we define the novel task of routing an end-user query to the appropriate data-source, where the data-sources are databases. We synthesize datasets by extending existing datasets designed for NL-to-SQL semantic parsing. We create baselines on these datasets by using open-source LLMs, using both pre-trained and task specific embeddings fine-tuned using the training data. With these baselines we demonstrate that open-source LLMs perform better than embedding based approach, but suffer from token length limitations. Embedding based approaches benefit from task specific fine-tuning, more so when there is availability of data in terms of database specific questions for training. We further find that the task becomes more difficult (i) with an increase in the number of data-sources, (ii) having data-sources closer in terms of their domains,(iii) having databases without external domain knowledge required to interpret its entities and (iv) with ambiguous and complex queries requiring more fine-grained understanding of the data-sources or logical reasoning for routing to an appropriate source. This calls for the need for developing more sophisticated solutions to better address the task. |
| title | DBRouting: Routing End User Queries to Databases for Answerability |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2501.16220 |