6 papers · 1 filter
DA-Cramming: Enhancing Cost-Effective Language Model Pretraining with Dependency Agreement Integration
Martin Kuo, Jianyi Zhang, Dongting Li +1
Pretraining language models is still a challenge for many researchers due to its substantial computational costs. As such, there is growing interest in developing more affordable p…
T2S-Bench & Structure-of-Thought: Benchmarking and Prompting Comprehensive Text-to-Structure Reasoning
Qinsi Wang, Hancheng Ye, Jinhee Kim +12
Think about how human handles complex reading tasks: marking key points, inferring their relationships, and structuring information to guide understanding and responses. Likewise,…
SafeTy Reasoning Elicitation Alignment for Multi-Turn Dialogues
Martin Kuo, Jianyi Zhang, Aolin Ding +12
Malicious attackers can exploit large language models (LLMs) by engaging them in multi-turn dialogues to achieve harmful objectives, posing significant safety risks to society. To…
Proactive Privacy Amnesia for Large Language Models: Safeguarding PII with Negligible Impact on Model Utility
Martin Kuo, Jingyang Zhang, Jianyi Zhang +9
With the rise of large language models (LLMs), increasing research has recognized their risk of leaking personally identifiable information (PII) under malicious attacks. Although…
H-CoT: Hijacking the Chain-of-Thought Safety Reasoning Mechanism to Jailbreak Large Reasoning Models, Including OpenAI o1/o3, DeepSeek-R1, and Gemini 2.0 Flash Thinking
Martin Kuo, Jianyi Zhang, Aolin Ding +6
Large Reasoning Models (LRMs) have recently extended their powerful reasoning capabilities to safety checks-using chain-of-thought reasoning to decide whether a request should be a…
Min-K%++: Improved Baseline for Detecting Pre-Training Data from Large Language Models
Jingyang Zhang, Jingwei Sun, Eric Yeats +5
The problem of pre-training data detection for large language models (LLMs) has received growing attention due to its implications in critical issues like copyright violation and t…