Claude-2 (Baseline)

Reported on 4 benchmarks across 2 tasks · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing4 results

Semantic ParsingonBIRD (BIg Bench for LaRge-scale Database Grounded Text-to-SQL Evaluation)
Execution Accuracy % (Dev)· 2023-09-28
42.7
best: 74.32 (DSAIR + GPT-4o)
Can LLMs Effectively Leverage Graph Structural Information through Prompts, and Why?arXiv:2309.16595
Semantic ParsingonBIRD (BIg Bench for LaRge-scale Database Grounded Text-to-SQL Evaluation)
Execution Accuracy % (Test)· 2023-09-28
49.02
best: 75.63 (XiYan-SQL)
Can LLMs Effectively Leverage Graph Structural Information through Prompts, and Why?arXiv:2309.16595
Text-To-SQLonBIRD (BIg Bench for LaRge-scale Database Grounded Text-to-SQL Evaluation)
Execution Accuracy % (Dev)· 2023-09-28
42.7
best: 74.32 (DSAIR + GPT-4o)
Can LLMs Effectively Leverage Graph Structural Information through Prompts, and Why?arXiv:2309.16595
Text-To-SQLonBIRD (BIg Bench for LaRge-scale Database Grounded Text-to-SQL Evaluation)
Execution Accuracy % (Test)· 2023-09-28
49.02
best: 75.63 (XiYan-SQL)
Can LLMs Effectively Leverage Graph Structural Information through Prompts, and Why?arXiv:2309.16595