← Text-To-SQL
Papers with Code · CC BY-SA 4.0

BIRD (BIg Bench for LaRge-scale Database Grounded Text-to-SQL Evaluation)

아카이브 평가 41건 · 마지막 적재/변경

평가 기록

과거 수집 기록이며 최신 순위가 아닙니다. 데이터셋 버전·split·실험 조건과 지표 방향이 검증되지 않은 결과는 직접 비교할 수 없습니다. 날짜는 논문 날짜이며 최신 평가일을 뜻하지 않습니다.

표가 화면보다 넓으면 좌우로 스크롤하여 논문과 구현 링크를 확인하세요.

원본 기록 순서 · 순위 미부여
모델원본 지표·값논문구현
GPT-4 (Baseline)
Execution Accuracy % (Test)
54.89
Execution Accuracy % (Dev)
46.35
Can LLMs Effectively Leverage Graph Structural Information through Prompts, and Why?
2023-09-28
코드 1 · 코드 2
Claude-2 (Baseline)
Execution Accuracy % (Test)
49.02
Execution Accuracy % (Dev)
42.70
Can LLMs Effectively Leverage Graph Structural Information through Prompts, and Why?
2023-09-28
코드 1 · 코드 2
Open SQL-7B
Execution Accuracy % (Test)
47.74
Execution Accuracy % (Dev)
37.68
연결 없음
논문 날짜 미기재
연결 없음
CoT + ChatGPT
Execution Accuracy % (Test)
40.08
Execution Accuracy % (Dev)
36.64
Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs
2023-05-04
코드 1
ChatGPT (Baseline)
Execution Accuracy % (Test)
39.30
Execution Accuracy % (Dev)
37.22
Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs
2023-05-04
코드 1
Codex (Baseline)
Execution Accuracy % (Test)
36.47
Execution Accuracy % (Dev)
34.35
Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs
2023-05-04
코드 1
Palm-2 (Baseline)
Execution Accuracy % (Test)
33.04
Execution Accuracy % (Dev)
27.38
Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs
2023-05-04
코드 1
MSc-SQL
Execution Accuracy % (Dev)
65.6
MSc-SQL: Multi-Sample Critiquing Small Language Models For Text-To-SQL Translation
2024-10-16
코드 1
SFT CodeS-15B + SQLFixAgent
Execution Accuracy % (Dev)
64.62
연결 없음
논문 날짜 미기재
연결 없음
DELLM + MAC-SQL
Execution Accuracy % (Dev)
48.92
Knowledge-to-SQL: Enhancing SQL Generation with Data Expert LLM
2024-02-18
코드 1
Human Performance
Execution Accurarcy (Human)
92.96
Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs
2023-05-04
코드 1