20 papers
State-Dependent Safety Failures in Multi-Turn Language Model Interaction
Pengcheng Li, Jie Zhang, Tianwei Zhang +5
Safety alignment in large language models is typically evaluated under isolated queries, yet real-world use is inherently multi-turn. Although multi-turn jailbreaks are empirically…
DECEIVE-AFC: Adversarial Claim Attacks against Search-Enabled LLM-based Fact-Checking Systems
Haoran Ou, Kangjie Chen, Gelei Deng +4
Fact-checking systems with search-enabled large language models (LLMs) have shown strong potential for verifying claims by dynamically retrieving external evidence. However, the ro…
Unifying Watermarking via Dimension-Aware Mapping
Jiale Meng, Runyi Hu, Jie Zhang +3
Deep watermarking methods often share similar encoder-decoder architectures, yet differ substantially in their functional behaviors. We propose DiM, a new multi-dimensional waterma…
Inference-time Alignment via Sparse Junction Steering
Runyi Hu, Jie Zhang, Shiqian Zhao +7
Token-level steering has emerged as a pivotal approach for inference-time alignment, enabling fine grained control over large language models by modulating their output distributio…
Character as a Latent Variable in Large Language Models: A Mechanistic Account of Emergent Misalignment and Conditional Safety Failures
Yanghao Su, Wenbo Zhou, Tianwei Zhang +4
Emergent Misalignment refers to a failure mode in which fine-tuning large language models (LLMs) on narrowly scoped data induces broadly misaligned behavior. Prior explanations mai…
Visible Yet Unreadable: A Systematic Blind Spot of Vision Language Models Across Writing Systems
Jie Zhang, Ting Xu, Gelei Deng +5
Writing is a universal cultural technology that reuses vision for symbolic communication. Humans display striking resilience: we readily recognize words even when characters are fr…