activity
20242026
collaborators

16 papers

cs.CL2026

Triospect: A Three-Dimensional Framework for Robust Statistical AI-Generated Text Detection Against Diverse Attacks

Guangsheng Bao, Lihua Rong, Yanbin Zhao +3

Existing AI-generated text detectors are vulnerable to attacks that manipulate textual characteristics. In this study, we propose a novel Triospect Detection Framework by using add…

cs.LG2026

FAAST: Forward-Only Associative Learning via Closed-Form Fast Weights for Test-Time Supervised Adaptation

Guangsheng Bao, Hongbo Zhang, Han Cui +4

Adapting pretrained models typically involves a trade-off between the high training costs of backpropagation and the heavy inference overhead of memory-based or in-context learning…

cs.AI2026

Detecting RLVR Training Data via Structural Convergence of Reasoning

Hongbo Zhang, Yue Yang, Jianhao Yan +2

Reinforcement learning with verifiable rewards (RLVR) is central to training modern reasoning models, but the undisclosed training data raises concerns about benchmark contaminatio…

cs.CL2026

Minimizing Mismatch Risk: A Prototype-Based Routing Framework for Zero-shot LLM-generated Text Detection

Ke Sun, Guangsheng Bao, Han Cui +1

Zero-shot methods detect LLM-generated text by computing statistical signatures using a surrogate model. Existing approaches typically employ a fixed surrogate for all inputs regar…

cs.CL2026

When AI Settles Down: Late-Stage Stability as a Signature of AI-Generated Text Detection

Ke Sun, Guangsheng Bao, Han Cui +1

Zero-shot detection methods for AI-generated text typically aggregate token-level statistics across entire sequences, overlooking the temporal dynamics inherent to autoregressive g…

cs.AI2025

UDA: Unsupervised Debiasing Alignment for Pair-wise LLM-as-a-Judge

Yang Zhang, Cunxiang Wang, Lindong Wu +4

Pairwise evaluation of Large Language Models (LLMs) is a common paradigm, but it is prone to preference bias, where judges systematically favor certain outputs, such as their own.…