AlibabaResearch / AlibabaResearch/DAMO-ConvAI
Can I use different prompts for different databases In the BIRD-SQL benchmark?
Open
- Dominant language
- Python
- Stars
- 1.6k
- Forks
- 250
- PR merge metrics
- No merged PRs in 30d
Description
We are running the BIRD-SQL benchmark using our self-developed T2S agent. I noticed that many errors may be due to some databases not having a detailed enough context. So I’d like to ask: can I use different prompts for different databases while running the benchmark? Would that be considered compliant? Thank you.
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.