SemField: A Simple, Linear, Continuous, yet Robust Semantic Watermark
Authors: Varun Gumma, Navonil Majumdar, Soujanya Poria | Published: 2026-10-08
Literature Database
Same Outcome, Different Evidence: Intent Recovery in LLM Safety Evaluation
Authors: Haitong Jiang, Chunlin Liu, Sihan Tang, Chan Wu, Xiaoqing Su, Yuhong Feng | Published: 2026-10-08
LTBD: Learnable Trust-Boundary Delimiters for Prompt Injection Defense
Authors: Luman Zhao, Minghui Xu, Yue Zhang, Yijun Yang | Published: 2026-10-08
SoK: Are LLMs Reliable at Source Code Recovery? A Taxonomy and Empirical Evaluation
Authors: Varun Kohli, Lee Bing Cheng, Nur Hazim Ghazali, Gao Yuze, Daryl Poon, Dinil Mon Divakaran | Published: 2026-10-08
Writing for the Reviewer: Defensive Writing in GPT Models
Authors: Junchi Liao | Published: 2026-10-08
Language Modeling is Monotone Compression
Authors: Noam Mazor, Andrew Morgan, Rafael Pass | Published: 2026-10-08
NOMOS: Compiling Written Policies into Statically Verified Tool-Call Gates for LLM Agents
Authors: Min-Young Yu, Tony Kim, Jang Won Choi | Published: 2026-10-08
Open-MMUnlearning: Unifying Methods and Evaluation for MLLM Unlearning
Authors: Junkai Chen, Yuhao He, Qianshan Wei, Junxiang You, Jingwen Shao, Junkai Lin, Zhongkai Yue, Xiaotian Ye, Zhengbo Jiao, Jiali Cheng, Zhijie Deng, Kening Zheng, Ruiqi Liu, Hadi Amiri, Yi Yu, Zhenan Sun, Qi Li, Ka-Ho Chow, Sijia Liu, Liang Wang, Jiaqi Li, Shu Wu | Published: 2026-10-07
SLDR: Defending Against Malicious Fine-tuning via Selective Layers Recovery and Dynamic Routing
Authors: Hui Zhang, Yachao Yuan, Jiayun Wang, Yuanzhuo Li, Hongtao Wang, Yali Yuan | Published: 2026-10-07
On the Reliability of LLM-Based Vulnerability Patching Benchmarks
Authors: Dang K Le, Wenxuan Shi, Xinyu Xing | Published: 2026-10-07