Papers by Zongqi Wang

5 papers
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

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.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations