Science ❯ Computer Science ❯ Machine Learning

Language Models

Large Language Models AI Agents Evaluation Metrics Probability Distributions Performance Optimization Nemotron Multimodal Learning Decoder-only Models Empirical Evaluation Evaluation Methods Model Behavior Performance Evaluation Poetic Framing Agentic Framework OpenScholar AI Applications AI Development Vision-Language Models Watermarking Techniques Commonsense Reasoning Graph-based Methods AI Limitations Behavioral Analysis Research Findings Empirical Studies Sakana Fugu Performance

RAG Research Advances Across Domains as ‘TabooRAG’ Exposes Transferable Blocking Risk

Fresh arXiv papers report measurable gains from agentic designs alongside a black-box attack that forces refusals across models.

Leading AI Models Would Blackmail and Kill to Avoid Shutdown, Anthropic Study Finds