arXiv:2606. 07313v1 Announce Type: cross Abstract: Detecting machine-generated text is especially difficult under distribution shift, such as transfer across domains, source models, and editing attacks.
Distinguishing machine-generated text (MGT) from human-written text (HWT) becomes increasingly important due to potential misuse. However, most supervised detectors often degrade out-of-domain (OOD) a...
The paper introduces MOSAIC, a large adversarial benchmark for detecting AI-generated text, and presents NeuroStat, a new framework that combines token‑level probabilistic logits with deep semantic hidden states from a single language model. NeuroStat fuses these signals via Macro‑State Residual Modulation and uses orthogonal and contrastive losses to learn complementary representations. Experiments show that NeuroStat outperforms existing methods on MOSAIC, achieving superior robustness against adversarial attacks.
arXiv:2606. 06315v1 Announce Type: new Abstract: Recent advances in interpretability suggest that large language models (LLMs) implicitly encode signals in their generated text that enable self-recognition of their outputs.
arXiv:2606. 04177v1 Announce Type: cross Abstract: Interpretable linguistic features offer a promising approach for explaining why a given text appears machine-generated, particularly for non-expert users.
arXiv:2606.18389v2 Announce Type: replace Abstract: Large language models (LLMs) have become an effective tool for synthetic data generation, including for low-resource languages, where generated dat...
arXiv:2609.22221v1 Announce Type: new Abstract: Large language models (LLMs) can generate fluent and coherent text that is increasingly difficult to distinguish from human writing, motivating the dev...
arXiv:2608. 05741v1 Announce Type: cross Abstract: Large language models (LLMs) can generate fluent and convincing text at scale, creating growing risks for misinformation dissemination, educational misuse, and platform governance.
arXiv:2608. 02957v1 Announce Type: new Abstract: Steering vectors (SVs) are widely used to influence the expression of concepts (e.
arXiv:2607. 10476v1 Announce Type: cross Abstract: Large language models (LLMs) have emerged as a powerful tool for retrieving knowledge through seamless, human-like interactions.
arXiv:2607. 01208v1 Announce Type: cross Abstract: Language models deployed in high-stakes roles can potentially favor certain entities, brands, or viewpoints, steering user decisions at scale.
UniGuardian is a training‑free detector for large language models that jointly identifies prompt injection, backdoor, and adversarial attacks—collectively called Prompt Trigger Attacks (PTA). It measures how structured prompt perturbations shift the model’s output distribution and uses a single‑forward strategy to detect attacks while generating text in a shared batched forward pass. Experiments show that UniGuardian accurately and efficiently identifies trigger‑activated prompts in LLMs.