6 papers
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…
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…
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…
Glimpse: Enabling White-Box Methods to Use Proprietary Models for Zero-Shot LLM-Generated Text Detection
Guangsheng Bao, Yanbin Zhao, Juncai He +1
Advanced large language models (LLMs) can generate text almost indistinguishable from human-written text, highlighting the importance of LLM-generated text detection. However, curr…
Fast-DetectGPT: Efficient Zero-Shot Detection of Machine-Generated Text via Conditional Probability Curvature
Guangsheng Bao, Yanbin Zhao, Zhiyang Teng +2
Large language models (LLMs) have shown the ability to produce fluent and cogent content, presenting both productivity opportunities and societal risks. To build trustworthy AI sys…
Logic Agent: Enhancing Validity with Logic Rule Invocation
Hanmeng Liu, Zhiyang Teng, Chaoli Zhang +1
Chain-of-Thought (CoT) prompting has emerged as a pivotal technique for augmenting the inferential capabilities of language models during reasoning tasks. Despite its advancements,…