Language Models Can't Detect Their Own Training Data
A new study published on arXiv cs.CL reveals that language models struggle to detect sentences in their training data even when they are unusually easy to predict. Two model families, OLMo-2 and Pythia, have released their pretraining corpora for public scrutiny. By comparing the frequency of sentences appearing across these corpora, researchers can determine whether a sentence was part of the…
1 source primary source
Key points
- Two model families released their pretraining corpora
- Language models struggle to detect sentences from their own training data
- Models with up to 13 billion parameters show a faint trace of exposure
Read the original at arXiv cs.CL · by Arman Nik Khah primary sourceOpen source ↗
Topics · follow one to build your own front page
OLMo-2Pythia
The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.
More in Generative AI & Models
All →- Microsoft releases Microsoft-Decision-1, a Qwen3.5-9B-based scoring model · 2 src
- Mistral releases Mistral Large 4, nicknamed Le Chonk, a 1-trillion-parameter multimodal model · 1 src
- Google rolls out Gemini 4 Argon with new safety safeguards · 1 src
- Google launches Gemini 4 Argon model · 11 src
- Meta adds AI tools to let users shape Facebook Feed and Reels · 3 src
Comments
via GitHub Discussions