Cerebra: Aligning Implicit Knowledge in Interactive SQL Authoring
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914413697564672 |
|---|---|
| author | Zhou, Yunfan Shi, Qiming Luo, Zhongsu Cai, Xiwen Huang, Yanwei Kim, Dae Hyun Weng, Di Wu, Yingcai |
| author_facet | Zhou, Yunfan Shi, Qiming Luo, Zhongsu Cai, Xiwen Huang, Yanwei Kim, Dae Hyun Weng, Di Wu, Yingcai |
| contents | LLM-driven tools have significantly lowered barriers to writing SQL queries. However, user instructions are often underspecified, assuming the model understands implicit knowledge, such as dataset schemas, domain conventions, and task-specific requirements, that isn't explicitly provided. This results in frequently erroneous scripts that require users to repeatedly clarify their intent. Additionally, users struggle to validate generated scripts because they cannot verify whether the model correctly applied implicit knowledge. We present Cerebra, an interactive NL-to-SQL tool that aligns implicit knowledge between users and LLMs during SQL authoring. Cerebra automatically retrieves implicit knowledge from historical SQL scripts based on user instructions, presents this knowledge in an interactive tree view for code review, and supports iterative refinement to improve generated scripts. To evaluate the effectiveness and usability of Cerebra, we conducted a user study with 16 participants, demonstrating its improved support for customized SQL authoring. The source code of Cerebra is available at https://github.com/zjuidg/CHI26-Cerebra. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_21363 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Cerebra: Aligning Implicit Knowledge in Interactive SQL Authoring Zhou, Yunfan Shi, Qiming Luo, Zhongsu Cai, Xiwen Huang, Yanwei Kim, Dae Hyun Weng, Di Wu, Yingcai Human-Computer Interaction LLM-driven tools have significantly lowered barriers to writing SQL queries. However, user instructions are often underspecified, assuming the model understands implicit knowledge, such as dataset schemas, domain conventions, and task-specific requirements, that isn't explicitly provided. This results in frequently erroneous scripts that require users to repeatedly clarify their intent. Additionally, users struggle to validate generated scripts because they cannot verify whether the model correctly applied implicit knowledge. We present Cerebra, an interactive NL-to-SQL tool that aligns implicit knowledge between users and LLMs during SQL authoring. Cerebra automatically retrieves implicit knowledge from historical SQL scripts based on user instructions, presents this knowledge in an interactive tree view for code review, and supports iterative refinement to improve generated scripts. To evaluate the effectiveness and usability of Cerebra, we conducted a user study with 16 participants, demonstrating its improved support for customized SQL authoring. The source code of Cerebra is available at https://github.com/zjuidg/CHI26-Cerebra. |
| title | Cerebra: Aligning Implicit Knowledge in Interactive SQL Authoring |
| topic | Human-Computer Interaction |
| url | https://arxiv.org/abs/2603.21363 |