AI Paper Atlas

Research map / Large language models / Language, safety and interpretability

Towards Reliable Marking and Verification of AI-Generated Text via Geometry-aware Sentence-level Watermarking

Yubing Ren, Ping Guo, Yanan Cao

ICML 2026 · Large language models › Language, safety and interpretability · approach: Text watermarking

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
fine-tune BGE-m3 encoder with alignment-uniformity loss (ablation)X-Guard · High-resource, attack averageaverage WSR: 0.627 -> 0.643Improved
fine-tune BGE-m3 encoder with alignment-uniformity loss (ablation)X-Guard · Low-resource, no attackWSR: 0.955 -> 0.956No clear effect
swap encoder to XLM-R or Qwen3-Embedding-0.6B (ablation)X-Guard · High/low-resourceWSR: 0.616 / 0.641 attack avg (high-res)No clear effect
increase number of partitions |Omega| from 2 to 8 (ablation)X-Guard · injection success rateinjection success rate: 0.80 -> nearly 1.00Improved
increase number of partitions |Omega| to 16 (ablation)X-Guard · attack robustnessrobustness: above 0.95 -> around 0.70Hurt
raise watermarked region ratio gamma (ablation)X-Guard · Chinese CulturaX 100 sentencesdetection vs false positivesMixed
use A2PQ centroid-aligned partitioning with isotropic embeddings instead of SemStamp LSHX-Guard · Toy injection success probabilityinjection success probability: 44.9% -> 89.9%Improved
X-Guard vs SemStamp sentence-level watermarkX-Guard · Text continuation, low-resource, optimized adaptive attackWSR: 25.30% -> 35.97%Improved
X-Guard vs token-level watermarks under paraphraseX-Guard · Text continuation, high-resource, mono-lingual paraphraseWSR: 0.15% (KGW) -> 49.61% (X-Guard)Improved
X-Guard vs SemStamp downstream qualityX-Guard · QMsum / MultiNews low-resourceWSR: 0.123 -> 0.490 (QMsum)Improved
X-Guard vs SemStamp generation timeX-Guard · relative TTLTgeneration time: x18.0 -> x5.5Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy