Abstract
Many existing end-to-end systems for hybrid question answering tasks can often be boiled down to a “prompt-and-pray” paradigm, where the user has limited control and insight into the intermediate reasoning steps used to achieve the final result. Additionally, due to the context size limitation of many transformer-based LLMs, it is often not reasonable to expect that the full structured and unstructured context will fit into a given prompt in a zero-shot setting, let alone a few-shot setting. We introduce BlendSQL, a superset of SQLite to act as a unified dialect for orchestrating reasoning across both unstructured and structured data. For hybrid question answering tasks involving multi-hop reasoning, we encode the full decomposed reasoning roadmap into a single interpretable BlendSQL query. Notably, we show that BlendSQL can scale to massive datasets and improve the performance of end-to-end systems while using 35% fewer tokens. Our code is available and installable as a package at https://github.com/parkervg/blendsql.- Anthology ID:
- 2024.findings-acl.25
- Volume:
- Findings of the Association for Computational Linguistics: ACL 2024
- Month:
- August
- Year:
- 2024
- Address:
- Bangkok, Thailand
- Editors:
- Lun-Wei Ku, Andre Martins, Vivek Srikumar
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 453–466
- Language:
- URL:
- https://aclanthology.org/2024.findings-acl.25
- DOI:
- 10.18653/v1/2024.findings-acl.25
- Cite (ACL):
- Parker Glenn, Parag Dakle, Liang Wang, and Preethi Raghavan. 2024. BlendSQL: A Scalable Dialect for Unifying Hybrid Question Answering in Relational Algebra. In Findings of the Association for Computational Linguistics: ACL 2024, pages 453–466, Bangkok, Thailand. Association for Computational Linguistics.
- Cite (Informal):
- BlendSQL: A Scalable Dialect for Unifying Hybrid Question Answering in Relational Algebra (Glenn et al., Findings 2024)
- PDF:
- https://preview.aclanthology.org/dois-2013-emnlp/2024.findings-acl.25.pdf