LHRLAB/KBQA-o1

[ICML 2025] Official resources of "KBQA-o1: Agentic Knowledge Base Question Answering with Monte Carlo Tree Search".

41
/ 100
Emerging

This project helps researchers in natural language processing (NLP) to improve the accuracy of knowledge base question answering (KBQA) systems. It takes datasets like WebQSP, GrailQA, or GraphQ, along with Freebase knowledge graph files, and outputs a fine-tuned language model capable of more accurately answering complex questions by reasoning over the knowledge base. It's intended for NLP researchers and practitioners focused on enhancing semantic search and question-answering capabilities.

Use this if you are an NLP researcher aiming to develop advanced knowledge base question-answering systems with improved reasoning capabilities for complex queries.

Not ideal if you are looking for an out-of-the-box, end-user friendly application for general question answering, as this requires significant technical setup and expertise in machine learning model training.

knowledge-base-question-answering natural-language-processing semantic-search AI-research information-retrieval
No Package No Dependents
Maintenance 6 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 12 / 25

How are scores calculated?

Stars

34

Forks

5

Language

Python

License

MIT

Last pushed

Dec 06, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/LHRLAB/KBQA-o1"

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