AI Paper Atlas

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

IACW: Intent-Aware Controllable Watermarking for Scalable Authorial Intent Attribution

Hao Huang, Ruihua Zhou, JiaTang Luo, Yunpeng Li, Yuling Liu

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
add entropy gating (ablation)IACW · IACW-Instruct editingPPL: 89.1 -> 42.1Improved
add entropy gating (ablation)IACW · IACW-Instructintent accuracy: 99.0% -> 99.5%No clear effect
add ECC (ablation)IACW · IACW-Instructintent accuracy: 90.0% -> 99.5%Improved
add confidence-based erasure decoding (ablation)IACW · IACW-Instructintent accuracy: 85.5% -> 99.5%Improved
use entropy-guided skipping instead of random skipping (ablation)IACW · IACW-Instruct clean textTPR: 0.000 -> 1.000Improved
IACW vs Qu et al. under 20% token deletionIACW · IACW-Instructintent accuracy: 90.5% -> 95.0%Improved
IACW vs Qu et al. under paraphrasingIACW · IACW-Instructintent accuracy: 58.0% -> 69.0%Improved
IACW vs Qu et al. under back-translationIACW · IACW-Instructintent accuracy: 36.5% -> 54.5%Improved
IACW entropy gating vs constant-bias Qu et al. on perplexityIACW · IACW-Instruct editingPPL: 90.92 -> 42.10Improved
IACW vs Qu et al. human preference against no watermarkIACW · IACW-Instruct editing (human study)preference rate: 38.7% -> 48.2%Improved
IACW vs Qu et al. annotator watermark detection rateIACW · IACW-Instruct editing (human study)watermark detected by humans: 67.3% -> 52.2%Improved
increase AI-polished content ratio from 10% to 100%IACW · Human-AI mixed documentsintent accuracy: 64.0 -> 99.5Improved

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