Dataset Viewer
Auto-converted to Parquet Duplicate
messages
listlengths
3
3
system
stringclasses
1 value
user
stringlengths
473
37.6k
assistant
stringlengths
23
804
[ { "role": "system", "content": "You are an expert SQL assistant. Given a database schema and a question, generate the correct SQL query. Output only the SQL query, no explanation." }, { "role": "user", "content": "### Database Schema\nCREATE TABLE \"lists\"\n(\n user_id IN...
You are an expert SQL assistant. Given a database schema and a question, generate the correct SQL query. Output only the SQL query, no explanation.
### Database Schema CREATE TABLE "lists" ( user_id INTEGER references lists_users (user_id), list_id INTEGER not null primary key, list_title TEXT, list_movie_number INTEGER, list_update_timestamp_utc TEXT, list...
SELECT movie_title FROM movies WHERE movie_release_year = 1945 ORDER BY movie_popularity DESC LIMIT 1
[ { "role": "system", "content": "You are an expert SQL assistant. Given a database schema and a question, generate the correct SQL query. Output only the SQL query, no explanation." }, { "role": "user", "content": "### Database Schema\nCREATE TABLE \"lists\"\n(\n user_id IN...
You are an expert SQL assistant. Given a database schema and a question, generate the correct SQL query. Output only the SQL query, no explanation.
### Database Schema CREATE TABLE "lists" ( user_id INTEGER references lists_users (user_id), list_id INTEGER not null primary key, list_title TEXT, list_movie_number INTEGER, list_update_timestamp_utc TEXT, list...
SELECT movie_title, movie_release_year, director_name FROM movies ORDER BY movie_popularity DESC LIMIT 1
[ { "role": "system", "content": "You are an expert SQL assistant. Given a database schema and a question, generate the correct SQL query. Output only the SQL query, no explanation." }, { "role": "user", "content": "### Database Schema\nCREATE TABLE \"lists\"\n(\n user_id IN...
You are an expert SQL assistant. Given a database schema and a question, generate the correct SQL query. Output only the SQL query, no explanation.
### Database Schema CREATE TABLE "lists" ( user_id INTEGER references lists_users (user_id), list_id INTEGER not null primary key, list_title TEXT, list_movie_number INTEGER, list_update_timestamp_utc TEXT, list...
SELECT movie_title, movie_release_year FROM movies ORDER BY LENGTH(movie_popularity) DESC LIMIT 1
[ { "role": "system", "content": "You are an expert SQL assistant. Given a database schema and a question, generate the correct SQL query. Output only the SQL query, no explanation." }, { "role": "user", "content": "### Database Schema\nCREATE TABLE \"lists\"\n(\n user_id IN...
You are an expert SQL assistant. Given a database schema and a question, generate the correct SQL query. Output only the SQL query, no explanation.
### Database Schema CREATE TABLE "lists" ( user_id INTEGER references lists_users (user_id), list_id INTEGER not null primary key, list_title TEXT, list_movie_number INTEGER, list_update_timestamp_utc TEXT, list...
SELECT movie_title FROM movies GROUP BY movie_title ORDER BY COUNT(movie_title) DESC LIMIT 1
[ { "role": "system", "content": "You are an expert SQL assistant. Given a database schema and a question, generate the correct SQL query. Output only the SQL query, no explanation." }, { "role": "user", "content": "### Database Schema\nCREATE TABLE \"lists\"\n(\n user_id IN...
You are an expert SQL assistant. Given a database schema and a question, generate the correct SQL query. Output only the SQL query, no explanation.
### Database Schema CREATE TABLE "lists" ( user_id INTEGER references lists_users (user_id), list_id INTEGER not null primary key, list_title TEXT, list_movie_number INTEGER, list_update_timestamp_utc TEXT, list...
SELECT AVG(movie_popularity) FROM movies WHERE director_name = 'Stanley Kubrick'
[ { "role": "system", "content": "You are an expert SQL assistant. Given a database schema and a question, generate the correct SQL query. Output only the SQL query, no explanation." }, { "role": "user", "content": "### Database Schema\nCREATE TABLE \"lists\"\n(\n user_id IN...
You are an expert SQL assistant. Given a database schema and a question, generate the correct SQL query. Output only the SQL query, no explanation.
### Database Schema CREATE TABLE "lists" ( user_id INTEGER references lists_users (user_id), list_id INTEGER not null primary key, list_title TEXT, list_movie_number INTEGER, list_update_timestamp_utc TEXT, list...
SELECT AVG(T2.rating_score) FROM movies AS T1 INNER JOIN ratings AS T2 ON T1.movie_id = T2.movie_id WHERE T1.movie_title = 'When Will I Be Loved'
[ { "role": "system", "content": "You are an expert SQL assistant. Given a database schema and a question, generate the correct SQL query. Output only the SQL query, no explanation." }, { "role": "user", "content": "### Database Schema\nCREATE TABLE \"lists\"\n(\n user_id IN...
You are an expert SQL assistant. Given a database schema and a question, generate the correct SQL query. Output only the SQL query, no explanation.
### Database Schema CREATE TABLE "lists" ( user_id INTEGER references lists_users (user_id), list_id INTEGER not null primary key, list_title TEXT, list_movie_number INTEGER, list_update_timestamp_utc TEXT, list...
SELECT T3.user_avatar_image_url, T3.rating_date_utc FROM movies AS T1 INNER JOIN ratings AS T2 ON T1.movie_id = T2.movie_id INNER JOIN ratings_users AS T3 ON T3.user_id = T2.user_id WHERE T3.user_id = 41579158 ORDER BY T3.rating_date_utc DESC LIMIT 1
[ { "role": "system", "content": "You are an expert SQL assistant. Given a database schema and a question, generate the correct SQL query. Output only the SQL query, no explanation." }, { "role": "user", "content": "### Database Schema\nCREATE TABLE \"lists\"\n(\n user_id IN...
You are an expert SQL assistant. Given a database schema and a question, generate the correct SQL query. Output only the SQL query, no explanation.
### Database Schema CREATE TABLE "lists" ( user_id INTEGER references lists_users (user_id), list_id INTEGER not null primary key, list_title TEXT, list_movie_number INTEGER, list_update_timestamp_utc TEXT, list...
SELECT CAST(SUM(CASE WHEN user_subscriber = 1 THEN 1 ELSE 0 END) AS REAL) * 100 / COUNT(*) FROM ratings
[ { "role": "system", "content": "You are an expert SQL assistant. Given a database schema and a question, generate the correct SQL query. Output only the SQL query, no explanation." }, { "role": "user", "content": "### Database Schema\nCREATE TABLE \"lists\"\n(\n user_id IN...
You are an expert SQL assistant. Given a database schema and a question, generate the correct SQL query. Output only the SQL query, no explanation.
### Database Schema CREATE TABLE "lists" ( user_id INTEGER references lists_users (user_id), list_id INTEGER not null primary key, list_title TEXT, list_movie_number INTEGER, list_update_timestamp_utc TEXT, list...
SELECT T1.movie_title FROM movies AS T1 INNER JOIN ratings AS T2 ON T1.movie_id = T2.movie_id WHERE T2.user_trialist = 1 AND T2.rating_timestamp_utc LIKE '2020-04%'
[ { "role": "system", "content": "You are an expert SQL assistant. Given a database schema and a question, generate the correct SQL query. Output only the SQL query, no explanation." }, { "role": "user", "content": "### Database Schema\nCREATE TABLE \"lists\"\n(\n user_id IN...
You are an expert SQL assistant. Given a database schema and a question, generate the correct SQL query. Output only the SQL query, no explanation.
### Database Schema CREATE TABLE "lists" ( user_id INTEGER references lists_users (user_id), list_id INTEGER not null primary key, list_title TEXT, list_movie_number INTEGER, list_update_timestamp_utc TEXT, list...
SELECT T1.user_id FROM ratings AS T1 INNER JOIN movies AS T2 ON T1.movie_id = T2.movie_id WHERE T2.movie_title = 'Love Will Tear Us Apart' AND T1.rating_score = 1
[ { "role": "system", "content": "You are an expert SQL assistant. Given a database schema and a question, generate the correct SQL query. Output only the SQL query, no explanation." }, { "role": "user", "content": "### Database Schema\nCREATE TABLE \"lists\"\n(\n user_id IN...
You are an expert SQL assistant. Given a database schema and a question, generate the correct SQL query. Output only the SQL query, no explanation.
### Database Schema CREATE TABLE "lists" ( user_id INTEGER references lists_users (user_id), list_id INTEGER not null primary key, list_title TEXT, list_movie_number INTEGER, list_update_timestamp_utc TEXT, list...
SELECT DISTINCT T2.movie_title, T2.movie_popularity FROM ratings AS T1 INNER JOIN movies AS T2 ON T1.movie_id = T2.movie_id WHERE T1.rating_score = 5
[ { "role": "system", "content": "You are an expert SQL assistant. Given a database schema and a question, generate the correct SQL query. Output only the SQL query, no explanation." }, { "role": "user", "content": "### Database Schema\nCREATE TABLE \"lists\"\n(\n user_id IN...
You are an expert SQL assistant. Given a database schema and a question, generate the correct SQL query. Output only the SQL query, no explanation.
### Database Schema CREATE TABLE "lists" ( user_id INTEGER references lists_users (user_id), list_id INTEGER not null primary key, list_title TEXT, list_movie_number INTEGER, list_update_timestamp_utc TEXT, list...
SELECT T2.movie_title FROM ratings AS T1 INNER JOIN movies AS T2 ON T1.movie_id = T2.movie_id WHERE CAST(SUBSTR(T1.rating_timestamp_utc, 1, 4) AS INTEGER) = 2020 AND CAST(SUBSTR(T1.rating_timestamp_utc, 6, 2) AS INTEGER) > 4
[ { "role": "system", "content": "You are an expert SQL assistant. Given a database schema and a question, generate the correct SQL query. Output only the SQL query, no explanation." }, { "role": "user", "content": "### Database Schema\nCREATE TABLE \"lists\"\n(\n user_id IN...
You are an expert SQL assistant. Given a database schema and a question, generate the correct SQL query. Output only the SQL query, no explanation.
### Database Schema CREATE TABLE "lists" ( user_id INTEGER references lists_users (user_id), list_id INTEGER not null primary key, list_title TEXT, list_movie_number INTEGER, list_update_timestamp_utc TEXT, list...
SELECT T2.movie_title, T1.user_id, T1.rating_score, T1.critic FROM ratings AS T1 INNER JOIN movies AS T2 ON T1.movie_id = T2.movie_id WHERE T1.critic IS NOT NULL
[ { "role": "system", "content": "You are an expert SQL assistant. Given a database schema and a question, generate the correct SQL query. Output only the SQL query, no explanation." }, { "role": "user", "content": "### Database Schema\nCREATE TABLE \"lists\"\n(\n user_id IN...
You are an expert SQL assistant. Given a database schema and a question, generate the correct SQL query. Output only the SQL query, no explanation.
### Database Schema CREATE TABLE "lists" ( user_id INTEGER references lists_users (user_id), list_id INTEGER not null primary key, list_title TEXT, list_movie_number INTEGER, list_update_timestamp_utc TEXT, list...
SELECT CAST(SUM(CASE WHEN T2.rating_score = 5 THEN 1 ELSE 0 END) AS REAL) * 100 / COUNT(*) FROM movies AS T1 INNER JOIN ratings AS T2 ON T1.movie_id = T2.movie_id WHERE T1.movie_title = 'Welcome to the Dollhouse'
[ { "role": "system", "content": "You are an expert SQL assistant. Given a database schema and a question, generate the correct SQL query. Output only the SQL query, no explanation." }, { "role": "user", "content": "### Database Schema\nCREATE TABLE \"lists\"\n(\n user_id IN...
You are an expert SQL assistant. Given a database schema and a question, generate the correct SQL query. Output only the SQL query, no explanation.
### Database Schema CREATE TABLE "lists" ( user_id INTEGER references lists_users (user_id), list_id INTEGER not null primary key, list_title TEXT, list_movie_number INTEGER, list_update_timestamp_utc TEXT, list...
SELECT CAST(SUM(CASE WHEN T1.movie_release_year = 2021 THEN 1 ELSE 0 END) AS REAL) * 100 / COUNT(*) FROM movies AS T1 INNER JOIN ratings AS T2 ON T1.movie_id = T2.movie_id
[ { "role": "system", "content": "You are an expert SQL assistant. Given a database schema and a question, generate the correct SQL query. Output only the SQL query, no explanation." }, { "role": "user", "content": "### Database Schema\nCREATE TABLE \"lists\"\n(\n user_id IN...
You are an expert SQL assistant. Given a database schema and a question, generate the correct SQL query. Output only the SQL query, no explanation.
### Database Schema CREATE TABLE "lists" ( user_id INTEGER references lists_users (user_id), list_id INTEGER not null primary key, list_title TEXT, list_movie_number INTEGER, list_update_timestamp_utc TEXT, list...
SELECT director_name FROM movies WHERE movie_title = 'Sex, Drink and Bloodshed'
[ { "role": "system", "content": "You are an expert SQL assistant. Given a database schema and a question, generate the correct SQL query. Output only the SQL query, no explanation." }, { "role": "user", "content": "### Database Schema\nCREATE TABLE \"lists\"\n(\n user_id IN...
You are an expert SQL assistant. Given a database schema and a question, generate the correct SQL query. Output only the SQL query, no explanation.
### Database Schema CREATE TABLE "lists" ( user_id INTEGER references lists_users (user_id), list_id INTEGER not null primary key, list_title TEXT, list_movie_number INTEGER, list_update_timestamp_utc TEXT, list...
SELECT list_title FROM lists ORDER BY list_followers DESC LIMIT 1
[ { "role": "system", "content": "You are an expert SQL assistant. Given a database schema and a question, generate the correct SQL query. Output only the SQL query, no explanation." }, { "role": "user", "content": "### Database Schema\nCREATE TABLE \"lists\"\n(\n user_id IN...
You are an expert SQL assistant. Given a database schema and a question, generate the correct SQL query. Output only the SQL query, no explanation.
### Database Schema CREATE TABLE "lists" ( user_id INTEGER references lists_users (user_id), list_id INTEGER not null primary key, list_title TEXT, list_movie_number INTEGER, list_update_timestamp_utc TEXT, list...
SELECT list_url FROM lists WHERE list_update_timestamp_utc LIKE '2012%' AND list_followers BETWEEN 1 AND 2 ORDER BY list_update_timestamp_utc DESC LIMIT 1
[ { "role": "system", "content": "You are an expert SQL assistant. Given a database schema and a question, generate the correct SQL query. Output only the SQL query, no explanation." }, { "role": "user", "content": "### Database Schema\nCREATE TABLE \"lists\"\n(\n user_id IN...
You are an expert SQL assistant. Given a database schema and a question, generate the correct SQL query. Output only the SQL query, no explanation.
### Database Schema CREATE TABLE "lists" ( user_id INTEGER references lists_users (user_id), list_id INTEGER not null primary key, list_title TEXT, list_movie_number INTEGER, list_update_timestamp_utc TEXT, list...
SELECT list_id FROM lists_users WHERE user_id = 85981819 ORDER BY list_creation_date_utc ASC LIMIT 1
[ { "role": "system", "content": "You are an expert SQL assistant. Given a database schema and a question, generate the correct SQL query. Output only the SQL query, no explanation." }, { "role": "user", "content": "### Database Schema\nCREATE TABLE \"lists\"\n(\n user_id IN...
You are an expert SQL assistant. Given a database schema and a question, generate the correct SQL query. Output only the SQL query, no explanation.
### Database Schema CREATE TABLE "lists" ( user_id INTEGER references lists_users (user_id), list_id INTEGER not null primary key, list_title TEXT, list_movie_number INTEGER, list_update_timestamp_utc TEXT, list...
SELECT COUNT(*) FROM ratings WHERE movie_id = 1269 AND rating_score <= 2 AND user_eligible_for_trial = 1 AND user_has_payment_method = 1
[ { "role": "system", "content": "You are an expert SQL assistant. Given a database schema and a question, generate the correct SQL query. Output only the SQL query, no explanation." }, { "role": "user", "content": "### Database Schema\nCREATE TABLE \"lists\"\n(\n user_id IN...
You are an expert SQL assistant. Given a database schema and a question, generate the correct SQL query. Output only the SQL query, no explanation.
### Database Schema CREATE TABLE "lists" ( user_id INTEGER references lists_users (user_id), list_id INTEGER not null primary key, list_title TEXT, list_movie_number INTEGER, list_update_timestamp_utc TEXT, list...
SELECT movie_title, movie_popularity FROM movies WHERE movie_release_year = 2021 AND director_name = 'Steven Spielberg'
[ { "role": "system", "content": "You are an expert SQL assistant. Given a database schema and a question, generate the correct SQL query. Output only the SQL query, no explanation." }, { "role": "user", "content": "### Database Schema\nCREATE TABLE \"lists\"\n(\n user_id IN...
You are an expert SQL assistant. Given a database schema and a question, generate the correct SQL query. Output only the SQL query, no explanation.
### Database Schema CREATE TABLE "lists" ( user_id INTEGER references lists_users (user_id), list_id INTEGER not null primary key, list_title TEXT, list_movie_number INTEGER, list_update_timestamp_utc TEXT, list...
SELECT movie_release_year, director_name FROM movies WHERE movie_release_year IS NOT NULL ORDER BY movie_release_year ASC LIMIT 1
[ { "role": "system", "content": "You are an expert SQL assistant. Given a database schema and a question, generate the correct SQL query. Output only the SQL query, no explanation." }, { "role": "user", "content": "### Database Schema\nCREATE TABLE \"lists\"\n(\n user_id IN...
You are an expert SQL assistant. Given a database schema and a question, generate the correct SQL query. Output only the SQL query, no explanation.
### Database Schema CREATE TABLE "lists" ( user_id INTEGER references lists_users (user_id), list_id INTEGER not null primary key, list_title TEXT, list_movie_number INTEGER, list_update_timestamp_utc TEXT, list...
SELECT user_id FROM lists_users WHERE user_subscriber = 1 GROUP BY user_id HAVING MAX(SUBSTR(list_creation_date_utc, 1, 4)) - MIN(SUBSTR(list_creation_date_utc, 1, 4)) >= 10
[ { "role": "system", "content": "You are an expert SQL assistant. Given a database schema and a question, generate the correct SQL query. Output only the SQL query, no explanation." }, { "role": "user", "content": "### Database Schema\nCREATE TABLE \"lists\"\n(\n user_id IN...
You are an expert SQL assistant. Given a database schema and a question, generate the correct SQL query. Output only the SQL query, no explanation.
### Database Schema CREATE TABLE "lists" ( user_id INTEGER references lists_users (user_id), list_id INTEGER not null primary key, list_title TEXT, list_movie_number INTEGER, list_update_timestamp_utc TEXT, list...
SELECT COUNT(T2.user_id) FROM movies AS T1 INNER JOIN ratings AS T2 ON T1.movie_id = T2.movie_id WHERE T1.movie_title = 'Pavee Lackeen: The Traveller Girl' AND T2.rating_score = 4
[ { "role": "system", "content": "You are an expert SQL assistant. Given a database schema and a question, generate the correct SQL query. Output only the SQL query, no explanation." }, { "role": "user", "content": "### Database Schema\nCREATE TABLE \"lists\"\n(\n user_id IN...
You are an expert SQL assistant. Given a database schema and a question, generate the correct SQL query. Output only the SQL query, no explanation.
### Database Schema CREATE TABLE "lists" ( user_id INTEGER references lists_users (user_id), list_id INTEGER not null primary key, list_title TEXT, list_movie_number INTEGER, list_update_timestamp_utc TEXT, list...
SELECT T2.user_eligible_for_trial, T1.list_followers FROM lists AS T1 INNER JOIN lists_users AS T2 ON T1.user_id = T1.user_id AND T1.list_id = T2.list_id WHERE T1.list_title = 'World War 2 and Kids'
[ { "role": "system", "content": "You are an expert SQL assistant. Given a database schema and a question, generate the correct SQL query. Output only the SQL query, no explanation." }, { "role": "user", "content": "### Database Schema\nCREATE TABLE \"lists\"\n(\n user_id IN...
You are an expert SQL assistant. Given a database schema and a question, generate the correct SQL query. Output only the SQL query, no explanation.
### Database Schema CREATE TABLE "lists" ( user_id INTEGER references lists_users (user_id), list_id INTEGER not null primary key, list_title TEXT, list_movie_number INTEGER, list_update_timestamp_utc TEXT, list...
SELECT T2.movie_release_year, T1.user_id FROM ratings AS T1 INNER JOIN movies AS T2 ON T1.movie_id = T2.movie_id WHERE T1.movie_id = ( SELECT movie_id FROM movies WHERE director_name = 'Quentin Tarantino' ORDER BY movie_release_year ASC LIMIT 2, 1 ) AND T1.rating_score = 4
[ { "role": "system", "content": "You are an expert SQL assistant. Given a database schema and a question, generate the correct SQL query. Output only the SQL query, no explanation." }, { "role": "user", "content": "### Database Schema\nCREATE TABLE \"lists\"\n(\n user_id IN...
You are an expert SQL assistant. Given a database schema and a question, generate the correct SQL query. Output only the SQL query, no explanation.
### Database Schema CREATE TABLE "lists" ( user_id INTEGER references lists_users (user_id), list_id INTEGER not null primary key, list_title TEXT, list_movie_number INTEGER, list_update_timestamp_utc TEXT, list...
SELECT T2.director_url FROM ratings AS T1 INNER JOIN movies AS T2 ON T1.movie_id = T2.movie_id WHERE T1.user_id = 2452551 AND T1.critic_likes = 39
[ { "role": "system", "content": "You are an expert SQL assistant. Given a database schema and a question, generate the correct SQL query. Output only the SQL query, no explanation." }, { "role": "user", "content": "### Database Schema\nCREATE TABLE \"lists\"\n(\n user_id IN...
You are an expert SQL assistant. Given a database schema and a question, generate the correct SQL query. Output only the SQL query, no explanation.
### Database Schema CREATE TABLE "lists" ( user_id INTEGER references lists_users (user_id), list_id INTEGER not null primary key, list_title TEXT, list_movie_number INTEGER, list_update_timestamp_utc TEXT, list...
SELECT AVG(T1.rating_score), T2.director_name FROM ratings AS T1 INNER JOIN movies AS T2 ON T1.movie_id = T2.movie_id WHERE T2.movie_title = 'When Will I Be Loved'
[ { "role": "system", "content": "You are an expert SQL assistant. Given a database schema and a question, generate the correct SQL query. Output only the SQL query, no explanation." }, { "role": "user", "content": "### Database Schema\nCREATE TABLE \"lists\"\n(\n user_id IN...
You are an expert SQL assistant. Given a database schema and a question, generate the correct SQL query. Output only the SQL query, no explanation.
### Database Schema CREATE TABLE "lists" ( user_id INTEGER references lists_users (user_id), list_id INTEGER not null primary key, list_title TEXT, list_movie_number INTEGER, list_update_timestamp_utc TEXT, list...
SELECT T1.list_movie_number, T2.user_has_payment_method FROM lists AS T1 INNER JOIN lists_users AS T2 ON T1.list_id = T2.list_id ORDER BY T1.list_movie_number DESC LIMIT 1
End of preview. Expand in Data Studio

Dataset Card for bird-text2sql-bench

bird-text2sql-bench 是 BIRD(BIg Bench for Large-Scale Database Grounded Text-to-SQL) 官方訓練集之 OpenAI Messages 格式版本,共 9,428 筆。相較於 Spider 1.0,BIRD 使用真實大型資料庫(70 個,涵蓋電商、運動、教育、醫療等 37+ 領域),並提供 evidence(數值提示)欄位,本資料集將 evidence### Hint 段落併入 user prompt,形成可直接餵入 SFT pipeline 之 system / user / assistant 三 role 對話。除原生之 messages 欄位外,另拆解出獨立之 system / user / assistant 字串欄位,可同時作為 SFT 語料與 benchmark evaluation pipeline 之直接輸入。

Dataset Details

Dataset Description

BIRD benchmark 由香港大學與微軟研究院合作於 NeurIPS 2023 發表,目的為測試 LLM 在真實資料庫之 Text-to-SQL 能力。其訓練集之特色:

  1. 資料庫為真實世界之大型 schema,包含髒資料、寬表、外部知識需求;
  2. 每題附帶 evidence 欄位,提供回答問題所需之外部知識或數值對應(例如「age refers to column birth_year」),模擬實務中 analyst 手上之 domain hint;
  3. 涵蓋之領域遠比 Spider 廣泛,適合訓練需要處理實務資料庫之 Text-to-SQL 模型。

本資料集為其 train split 之 OpenAI Messages 格式版本,不修改任何原始問題、SQL、evidence 或資料庫 schema,僅進行格式重組與欄位拆解:

  • messages:完整之 OpenAI Messages 結構(list of {role, content});
  • system:固定提示語 "You are an expert SQL assistant...";
  • user### Database Schema### Question +(若有)### Hint
  • assistant:標準答案 SQL。

提供拆解後之獨立欄位,方便 benchmark pipeline 直接以 user 為 prompt 餵入模型、以 assistant 為 ground truth 進行 execution accuracy 比對,而無需再次解析 messages 結構。

  • Curated by: Liang Hsun Huang
  • Language(s) (NLP): English
  • License: CC BY-SA 4.0(繼承自 BIRD benchmark)

Dataset Sources

Uses

Direct Use

本資料集主要設計用於:

  • Text-to-SQL 模型之 SFT 訓練(以 messages 為訓練目標),特別是需要處理真實大型 schema 之情境;
  • Text-to-SQL 模型之 benchmark 評測(以 system + user 組 prompt,對齊 assistant 為 ground truth);
  • 學習如何運用 external hint / evidence 進行 SQL 生成;
  • spider-text2sql-bench 搭配作為 Text-to-SQL 之完整訓練/評測組合;
  • 作為 GRPO / RL-based Text-to-SQL 訓練之 reference policy 初始化語料。

Out-of-Scope Use

本資料集不適用於下列用途:

  • 作為 BIRD 官方評測之測試集使用,本資料集僅為 train split;
  • 作為非 SQLite 方言之訓練來源;
  • 作為中文 Text-to-SQL 之直接訓練資料;
  • 作為不含 evidence 之純語意解析任務之唯一來源。

Dataset Structure

{
  "messages": [
    {"role": "system", "content": "You are an expert SQL assistant. Given a database schema and a question, generate the correct SQL query. Output only the SQL query, no explanation."},
    {"role": "user", "content": "### Database Schema\nCREATE TABLE ...\n\n### Question\nWhat is the average age?\n\n### Hint\nage refers to column `birth_year`"},
    {"role": "assistant", "content": "SELECT AVG(birth_year) FROM person"}
  ],
  "system": "You are an expert SQL assistant. Given a database schema and a question, generate the correct SQL query. Output only the SQL query, no explanation.",
  "user": "### Database Schema\nCREATE TABLE ...\n\n### Question\nWhat is the average age?\n\n### Hint\nage refers to column `birth_year`",
  "assistant": "SELECT AVG(birth_year) FROM person"
}

無 evidence 之樣本則省略 ### Hint 區塊。

欄位 型別 說明
messages list[{role, content}] OpenAI Messages 結構(system / user / assistant)
system string 拆解後之 system prompt(同 messages[0].content
user string 拆解後之 user prompt(同 messages[1].content
assistant string 拆解後之 assistant 標準答案 SQL(同 messages[2].content
統計項目 數值
筆數 9,428
來源 split BIRD train
資料庫數量 70(真實大型資料庫)
領域數量 37+
特色 evidence 欄位併入 user prompt
SQL 方言 SQLite
格式 Parquet

使用此原始資料集之知名模型

模型 機構 使用方式
OmniSQL Renmin University SFT 訓練資料之一(搭配 SynSQL-2.5M、Spider)
XiYan-SQL Alibaba Stage 1 + Stage 2 SFT 訓練資料
CodeS RUC (SIGMOD 2024) Spider + BIRD train SFT
CHESS Stanford 訓練 Schema Selector 與 SQL Generator
Arctic-Text2SQL-R1 Snowflake GRPO RL 亦使用 BIRD train

Dataset Creation

Curation Rationale

BIRD 原始釋出格式需依照官方 harness 組裝才能用於訓練,且 evidence 欄位之納入方式各論文做法不一。本資料集將 evidence 以固定之 ### Hint 區塊併入 user prompt,並於 messages 之外同時提供拆解後之 system / user / assistant 欄位,讓 benchmark pipeline 可直接取用,提供一個可直接使用之 SFT 與 benchmark 基準格式。

Source Data

Data Collection and Processing

  1. 從 BIRD benchmark 官方釋出之 train.json 讀取 question / SQL / evidence / db_id;
  2. 從官方提供之 SQLite 資料庫以 sqlite_master 萃取 CREATE TABLE 語句作為 schema;
  3. 組裝為 OpenAI Messages 格式,evidence 以 ### Hint 併入 user prompt(若 evidence 為空則省略);
  4. 另外將每筆對話拆解為獨立之 system / user / assistant 字串欄位;
  5. 儲存為單檔 parquet。

Who are the source data producers?

原始問題、SQL 與 evidence 由 BIRD benchmark 之標註團隊(香港大學 / 微軟研究院)產出,詳見原始論文。

Annotations

Annotation process

本資料集不包含額外人工標註。

Who are the annotators?

不適用。

Personal and Sensitive Information

BIRD 之資料庫皆為公開或授權之資料來源,詳見原始論文與授權條款。

Bias, Risks, and Limitations

  • evidence 品質差異:部分 evidence 為關鍵知識,部分僅為次要提示,訓練時模型可能對 evidence 過度依賴;
  • 真實資料庫之髒資料:schema 中可能含有拼錯之欄位、不一致之命名,對模型之 schema linking 為挑戰亦為特色;
  • SQL 方言限定:SQLite,其他方言不適用;
  • 資料規模中等:9,428 筆屬中等規模,大規模訓練時建議與合成資料搭配。

Recommendations

建議使用者:

  • 將本資料集與 spider-text2sql-bench 合併作為 Text-to-SQL SFT 主力語料或 benchmark 組合;
  • ### Hint 之使用方式進行 ablation,觀察模型是否過度依賴 evidence;
  • 作為 RL 訓練(GRPO / DPO)之 SFT 基線,再接續 reward-based 優化;
  • 遵循原始 BIRD benchmark 之 CC BY-SA 4.0 授權規則。

Citation

@inproceedings{li2023bird,
  title={Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs},
  author={Li, Jinyang and Hui, Binyuan and Qu, Ge and Yang, Jiaxi and Li, Binhua and Li, Bowen and Wang, Bailin and Qin, Bowen and Geng, Ruiying and Huo, Nan and others},
  booktitle={NeurIPS},
  year={2023}
}

@misc{bird-text2sql-bench,
  title        = {bird-text2sql-bench: BIRD in OpenAI Messages + Split Columns Format for Text-to-SQL SFT and Benchmark},
  author       = {Liang Hsun Huang},
  year         = {2024},
  howpublished = {\url{https://huggingface.co/datasets/lianghsun/bird-text2sql-bench}},
  note         = {Reformatted from BIRD benchmark train split (CC BY-SA 4.0) with additional system/user/assistant columns for benchmark pipelines.}
}

Dataset Card Authors

Liang Hsun Huang

Dataset Card Contact

Liang Hsun Huang

Downloads last month
3

Papers for lianghsun/bird-text2sql-bench