3 papers
cs.CR2026
Identifying AI Web Scrapers Using Canary Tokens
Steven Seiden, Triss Ren, Caroline Zhang +3
From pre-training to query-time augmentation, web-scraped data helps to improve the quality and contextual relevancy of content generated by large language models (LLMs). However,…
cs.CV2026
Out of the box age estimation through facial imagery: A Comprehensive Benchmark of Vision-Language Models vs. out-of-the-box Traditional Architectures
Simiao Ren, Xingyu Shen, Ankit Raj +8
Facial age estimation plays a critical role in content moderation, age verification, and deepfake detection. However, no prior benchmark has systematically compared modern vision-l…
cs.CL2026
Reflect: Transparent Principle-Guided Reasoning for Constitutional Alignment at Scale
Henry Bell, Caroline Zhang, Mohammed Mobasserul Haque +3
The constitutional framework of alignment aims to align large language models (LLMs) with value-laden principles written in natural language (such as to avoid using biased language…