Watermark Basins: Black-Box Detection of Distilled LLMs

Watermark Basins: Black-Box Detection of Distilled LLMs. It centres on Fine-tuning, and also names AI Safety. Reported by arXiv. Bharat Hunt files it under AI Models and AI Research — the section covering a new or updated model, its capabilities, benchmarks or availability.

Written by Bharat Hunt from the headline and the coverage below. The original reporting is the source of truth.