Papers by Zongqi Wang
MorphMark: Flexible Adaptive Watermarking for Large Language Models (2025.acl-long)
Copied to clipboard
| Challenge: | Existing methods for tracing text origins struggle with a watermark effectiveness dilemma . weaker watermarks preserve text quality, while stronger ones enhance effectiveness . |
| Approach: | They propose a method that adjusts watermark strength in response to changes in a key factor . they first formalize the problem within a multi-objective trade-off analysis framework . |
| Outcome: | The proposed method improves watermark effectiveness but reduces text quality . the proposed method prioritizes flexibility and time and space efficiency . |
Invisible Entropy: Towards Safe and Efficient Low-Entropy LLM Watermarking (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to watermark low-entropy content are expensive and risky . IE reduces parameter size by 99% while achieving performance on par with state-of-the-art methods . |
| Approach: | They propose a logit-based watermarking paradigm that uses entropy-based features to predict whether the next token is high or low. |
| Outcome: | The proposed method reduces parameter size by 99% while achieving performance on par with state-of-the-art methods. |
Probing the Safety Robustness of LLMs in Latent Space (2026.acl-long)
Copied to clipboard
Tianle Gu, Kexin Huang, Zongqi Wang, Yixu Wang, Jie Li, Xin Wang, Yang Yao, Yujiu Yang, Yan Teng, Yingchun Wang
| Challenge: | Despite substantial progress in safety alignment techniques, aligned large language models can still produce unsafe responses under minor internal perturbations. |
| Approach: | They introduce Activation Steering Attack (ASA) and leverage the Negative Log-Likelihood (NLL) as a diagnostic signal to probe the local sensitivity of safety behaviors in latent space. |
| Outcome: | The proposed method is model-agnostic and supervision-free, enabling a general and reproducible diagnostic metric for analyzing safety robustness. |
SCAN: Structured Capability Assessment and Navigation for LLMs (2026.acl-long)
Copied to clipboard
| Challenge: | Existing research has focused on approximating model rankings, but such benchmarks fail to provide users and developers with a comprehensive and fine-grained understanding of a specific model’s capabilities. |
| Approach: | They propose a framework that enables detailed characterization of LLM capabilities through comprehensive and fine-grained evaluation. |
| Outcome: | The proposed framework enables detailed characterization of large language models through comprehensive and fine-grained evaluation. |
Robust and Minimally Invasive Watermarking for EaaS (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing watermarking methods use a target embedding to create watermarks, but this method results in each embeddable having the same component, making it difficult to remove the watermark. |
| Approach: | They propose to use embedding watermarks to protect EaaS from model extraction attacks . eaas is vulnerable to model extraction, highlighting the need for copyright protection . |
| Outcome: | The proposed method can watermark embeddings against model extraction attacks without sacrificing the quality of the embeddables. |