yinzhangyue/SelfAware

Do Large Language Models Know What They Don’t Know?

32
/ 100
Emerging

This project provides a dataset and tools to assess if large language models (LLMs) can recognize when they don't have the answer to a question. It takes a list of questions (some answerable, some not) and an LLM's responses, then evaluates how accurately the LLM identifies unanswerable questions. The primary user is anyone working with or evaluating the reliability and knowledge boundaries of AI chatbots and conversational agents.

102 stars. No commits in the last 6 months.

Use this if you need to objectively measure an AI model's ability to 'know what it doesn't know' and avoid making up incorrect information.

Not ideal if you're looking for a tool to train or fine-tune an LLM, as this project focuses on evaluation rather than model development.

AI evaluation chatbot reliability model uncertainty question answering systems LLM self-knowledge
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 7 / 25

How are scores calculated?

Stars

102

Forks

5

Language

Python

License

Apache-2.0

Last pushed

Nov 08, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/yinzhangyue/SelfAware"

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