Skip to content
conftrace_
2026 EMNLP EMNLP 2026

CAD-Mark: Context-Aware Distributional Watermarking for Robust LLM-Generated Text Detection

AbstractThe increasing prevalence of texts generated by large language models (LLMs) drives a critical demand for reliable LLM text detection, where text watermarking has emerged as a promising proactive solution. Among existing methods, sentence-level watermarking is more robust to semantic-preserving adversarial attacks, but it still faces two key limitations: generation often requires iterative rejection sampling, and detection treats all sentence-level signals as equally reliable. To address these limitations, we propose CAD-Mark, a context-aware distributional sentence-level watermarking framework. During generation, CAD-Mark partitions a batch of candidate sentences with a context-derived adaptive boundary and samples the output sentence from the subset corresponding to the secret bits, embedding multiple bits per sentence without iterative rejection sampling. During detection, it estimates sentence-level reliability from re-sampled candidates and aggregates bit-level signals with a diversity-weighted z-test. Experiments on two benchmarks demonstrate that CAD-Mark consistently outperforms strong baselines in TPR@1%FPR while preserving generation quality with comparable cost.

More from EMNLP 2026

All EMNLP 2026 papers →