zhiyuanhubj/UoT

[NeurIPS 2024] Uncertainty of Thoughts: Uncertainty-Aware Planning Enhances Information Seeking in Large Language Models

28
/ 100
Experimental

This project helps professionals like medical diagnosticians, technical support staff, or game players solve complex problems by asking smarter questions. It takes an initial problem description or set of symptoms and guides a large language model to ask the most effective follow-up questions to pinpoint the correct diagnosis, solution, or answer. The output is a more efficient and accurate problem-solving process, reducing the number of questions needed to reach a successful conclusion.

106 stars. No commits in the last 6 months.

Use this if you need a large language model to intelligently seek information by asking probing questions, rather than making assumptions, to solve open-ended problems.

Not ideal if your problem space is very clearly defined and requires a fixed, exhaustive set of questions, or if you prefer a model to directly provide an answer without interactive questioning.

medical-diagnosis customer-support troubleshooting interactive-problem-solving information-seeking
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 8 / 25
Community 11 / 25

How are scores calculated?

Stars

106

Forks

8

Language

Python

License

Last pushed

Aug 05, 2024

Commits (30d)

0

Get this data via API

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

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