LEAP: LLM-powered End-to-end Automatic Library for Processing Social Science Queries on Unstructured Data
Summary: LEAP filters vague NL social‑science queries, composes ML annotation functions (built-in or user) to turn unstructured text into structured tables, and generates executable analysis code. On QUIET‑ML (120 real queries) it achieves 92% pass@1, 100% pass@3 at $1.06 avg cost. (summarized by gpt-5-mini on Feb 09 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Chuxuan Hu
- 2. Austin Peters
- 3. Daniel Kang
Incoming Citations (Sorted by Pagerank)
Showing 1 of 1 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 10,069 | Drama: Unifying Data Retrieval and Analysis for Open-Domain Analytic Queries | 2026 | SIGMOD | 4.1945683e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 4 of 4 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 369 | Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation | 2024 | VLDB | 0.0002547515 |
| 1,732 | CatSQL: Towards Real World Natural Language to SQL Applications | 2023 | VLDB | 0.00010732004 |
| 2,771 | A Relational Approach to Incrementally Extracting and Querying Structure in Unstructured Data | 2007 | VLDB | 8.1421432e-05 |
| 2,988 | NL2SQL is a solved problem... Not! | 2024 | CIDR | 7.7761714e-05 |
Previous
Page 1 / 1
Next