Meta TextSeal2 Combines Watermark Keys to Survive Speculative Decoding
Watermarks usually lose detection power when teams speed up generation with speculative decoding, and TextSeal2 shows a practical fix that keeps both speed and signal intact. Researchers and platform teams building provenance or AI-content detection pipelines can benchmark it directly against TextSeal and textGrain using the reported 89% versus 71% and 67% detection numbers. The Qwen3.5-9B setup gives a concrete open-model reference for reproduction.
