zhuohaoyu/KIEval

[ACL'24] A Knowledge-grounded Interactive Evaluation Framework for Large Language Models

21
/ 100
Experimental

This tool helps AI researchers and developers accurately assess how well large language models (LLMs) understand and apply domain-specific knowledge. It takes a conventional LLM benchmark question and generates a multi-round, knowledge-focused dialogue to evaluate if the model truly comprehends the subject or is merely recalling pre-trained answers. The output is a robust evaluation of the LLM's true knowledge application, even when benchmark data might be contaminated.

No commits in the last 6 months.

Use this if you need to reliably evaluate the deep comprehension and real-world applicability of large language models on knowledge-intensive tasks, beyond simple memorization.

Not ideal if you are looking for a quick, high-level performance score that doesn't account for data contamination or interactive knowledge application.

LLM evaluation AI model assessment Knowledge understanding Natural Language Processing AI research
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 8 / 25
Community 6 / 25

How are scores calculated?

Stars

39

Forks

2

Language

Python

License

Last pushed

Jul 19, 2024

Commits (30d)

0

Get this data via API

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

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