7 papers
RedCoder: Automated Multi-Turn Red Teaming for Code LLMs
Wenjie Jacky Mo, Qin Liu, Xiaofei Wen +5
Large Language Models (LLMs) for code generation (i.e., Code LLMs) have demonstrated impressive capabilities in AI-assisted software development and testing. However, recent studie…
SafeLens: Deliberate and Efficient Video Guardrails with Fast-and-Slow Screening
Shahriar Kabir Nahin, Hadi Askari, Muhao Chen +1
The rapid growth of online video platforms and AI-generated content has made reliable video guardrails a key challenge for safety and real-world deployment. While most videos can b…
Less Diverse, Less Safe: The Indirect But Pervasive Risk of Test-Time Scaling in Large Language Models
Shahriar Kabir Nahin, Hadi Askari, Muhao Chen +1
Test-Time Scaling (TTS) improves LLM reasoning by exploring multiple candidate responses and then operating over this set to find the best output. A tacit premise behind TTS is tha…
FRIEDA: Benchmarking Multi-Step Cartographic Reasoning in Vision-Language Models
Jiyoon Pyo, Yuankun Jiao, Dongwon Jung +11
Cartographic reasoning is the skill of interpreting geographic relationships by aligning legends, map scales, compass directions, map texts, and geometries across one or more map i…
LayerIF: Estimating Layer Quality for Large Language Models using Influence Functions
Hadi Askari, Shivanshu Gupta, Fei Wang +2
Pretrained Large Language Models (LLMs) achieve strong performance across a wide range of tasks, yet exhibit substantial variability in the various layers' training quality with re…
Unraveling Indirect In-Context Learning Using Influence Functions
Hadi Askari, Shivanshu Gupta, Terry Tong +3
In this work, we introduce a novel paradigm for generalized In-Context Learning (ICL), termed Indirect In-Context Learning. In Indirect ICL, we explore demonstration selection stra…