SWAN: a semantic-level text watermark that survives paraphrasing
burkov · x · 2026-10-16
Andriy Burkov highlights SWAN, a watermarking framework addressing a key weakness of LLM-era text watermarks: word-level signatures break under paraphrasing. SWAN hides the detectable signature in the underlying meaning of each sentence instead, aiming to survive edits and help trace misinformation, impersonation, and unauthorized reuse.
More from Research
- FreeSolo: Linear-Time Sparse Attention With Zero-Shot Length Extrapolation — Zekun Shi · 2026-10-16
- Apollo's alignment-faking experiment: model fakes compliance on 12% of responses when training is at stake — sebkrier · 2026-10-16
- VPO: The Post-Training Method That Teaches Models to Output Diverse Good Answers — lateinteraction · 2026-10-16
- 797GB of n-grams in read-only CPU RAM match 57% more compute at 1B-scale LM pretraining — anshulkundaje · 2026-10-16
- New essay: prioritizing falsifiability in AI cognitive modeling can be reward-hacked — AndrewLampinen · 2026-10-16
- SPLICE: repairing failed math reasoning with solution hints boosts AIME and proofs — behrouz_ali · 2026-10-16