5 papers
SCAN: Structured Capability Assessment and Navigation for LLMs
Zongqi Wang, Tianle Gu, Chen Gong +3
Evaluating Large Language Models (LLMs) has become increasingly important, with automatic evaluation benchmarks gaining prominence as alternatives to human evaluation. While existi…
S2J: Bridging the Gap Between Solving and Judging Ability in Generative Reward Models
Shaoning Sun, Jiachen Yu, Zongqi Wang +3
With the rapid development of large language models (LLMs), generative reward models (GRMs) have been widely adopted for reward modeling and evaluation. Previous studies have prima…
Probing the Robustness of Large Language Models Safety to Latent Perturbations
Tianle Gu, Kexin Huang, Zongqi Wang +7
Safety alignment is a key requirement for building reliable Artificial General Intelligence. Despite significant advances in safety alignment, we observe that minor latent shifts c…
Invisible Entropy: Towards Safe and Efficient Low-Entropy LLM Watermarking
Tianle Gu, Zongqi Wang, Kexin Huang +4
Logit-based LLM watermarking traces and verifies AI-generated content by maintaining green and red token lists and increasing the likelihood of green tokens during generation. Howe…
MorphMark: Flexible Adaptive Watermarking for Large Language Models
Zongqi Wang, Tianle Gu, Baoyuan Wu +1
Watermarking by altering token sampling probabilities based on red-green list is a promising method for tracing the origin of text generated by large language models (LLMs). Howeve…