tsinghua-fib-lab/AAAI2025_MIA-Tuner
[AAAI'25 Oral] "MIA-Tuner: Adapting Large Language Models as Pre-training Text Detector".
This project helps evaluate whether a piece of text has been used to train a specific large language model (LLM). You provide a text input and specify an LLM, and the tool tells you if that text likely appeared in the LLM's training data. This is useful for researchers, data scientists, or anyone working with LLMs who needs to understand data leakage or model memorization.
147 stars. No commits in the last 6 months.
Use this if you need to determine if a specific text was part of a large language model's pre-training data.
Not ideal if you are looking for a general text plagiarism checker or a tool to detect AI-generated content.
Stars
147
Forks
10
Language
Python
License
—
Category
Last pushed
Mar 17, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/tsinghua-fib-lab/AAAI2025_MIA-Tuner"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
steering-vectors/steering-vectors
Steering vectors for transformer language models in Pytorch / Huggingface
jianghoucheng/AlphaEdit
AlphaEdit: Null-Space Constrained Knowledge Editing for Language Models, ICLR 2025 (Outstanding Paper)
kmeng01/memit
Mass-editing thousands of facts into a transformer memory (ICLR 2023)
boyiwei/alignment-attribution-code
[ICML 2024] Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications
jianghoucheng/AnyEdit
AnyEdit: Edit Any Knowledge Encoded in Language Models, ICML 2025