LHRLAB/ChatKBQA

[ACL 2024] Official resources of "ChatKBQA: A Generate-then-Retrieve Framework for Knowledge Base Question Answering with Fine-tuned Large Language Models".

42
/ 100
Emerging

This project helps anyone who needs to quickly find precise answers to natural language questions from a vast knowledge base, like Wikipedia or Freebase. You input a question in plain English, and it outputs a precise, structured query (like SPARQL) that can be executed against a knowledge graph, along with the correct answer. It's designed for data analysts, researchers, or anyone working with large, interconnected datasets who needs accurate information without manually constructing complex database queries.

337 stars. No commits in the last 6 months.

Use this if you need to reliably convert everyday questions into executable queries for large knowledge graphs, especially when high accuracy and structured outputs are critical.

Not ideal if your data isn't structured as a knowledge graph or if you primarily work with unstructured text documents rather than factual entities and their relationships.

knowledge-base-query semantic-search question-answering data-retrieval information-extraction
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 14 / 25

How are scores calculated?

Stars

337

Forks

30

Language

Python

License

MIT

Last pushed

Sep 22, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/LHRLAB/ChatKBQA"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.