yihuaihong/ConceptVectors

[EMNLP 2025 Main] ConceptVectors Benchmark and Code for the paper "Intrinsic Evaluation of Unlearning Using Parametric Knowledge Traces"

36
/ 100
Emerging

This project helps researchers and developers working with large language models (LLMs) to intrinsically evaluate how effectively models "unlearn" specific concepts. It provides a benchmark dataset and code to analyze changes within the model's parameters when knowledge is supposed to be removed. The output helps model developers understand if unlearning methods truly erase information, making LLMs safer and more reliable.

No commits in the last 6 months.

Use this if you are developing or evaluating unlearning techniques for LLMs and need to assess whether specific concepts are genuinely removed from the model's internal knowledge representation, beyond just behavioral tests.

Not ideal if you are a general LLM user or a practitioner only interested in the high-level behavior of an unlearned model without delving into its internal parametric changes.

LLM Unlearning Model Evaluation AI Safety Natural Language Processing Machine Learning Research
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 11 / 25

How are scores calculated?

Stars

39

Forks

5

Language

Jupyter Notebook

License

CC-BY-4.0

Last pushed

Aug 20, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/yihuaihong/ConceptVectors"

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