Papers with KGW
WaterPool: A Language Model Watermark Mitigating Trade-Offs among Imperceptibility, Efficacy and Robustness (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing methods to trace the usage of large language models often face trade-offs between imperceptibility and robustness. |
| Approach: | They propose a key-centered scheme to unify existing methods by decomposing a watermark into two components: a 'key module' and a "mark module". |
| Outcome: | The proposed method can be integrated with existing methods and achieve near-optimal imperceptibility and detection efficacy. |
Watermarking with Low-Entropy POS-Guided Token Partitioning and Z-Score-Driven Dynamic Bias for Large Language Models (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing watermarking methods reduce the fidelity of semantics in LLMs . |
| Approach: | They propose a low-entropy token partitioning mechanism and z-score-driven dynamic bias mechanism to enhance semantics. |
| Outcome: | The proposed framework improves semantic fidelity and robustness against bias sparsity attacks. |
SSG: Logit-Balanced Vocabulary Partitioning for LLM Watermarking (2026.acl-long)
Copied to clipboard
| Challenge: | Large language models can generate highquality, human-like content, but they also pose risks such as infringement of proprietary interests, misuse of outputs, and spread harmful misinformation. |
| Approach: | They propose a method that partitions the vocabulary into two logit-balanced subsets and lifts the lower bound of watermark strength for each token prediction. |
| Outcome: | The proposed method lifts the lower bound of watermark strength for each token prediction, thereby improving watermark detectability. |