🔥 Trending today
LLMs believe false statements even after explicit warnings that they're false★ 74
Ars Technica AI5d agoPaperA new study describes “Negation Neglect,” where LLMs fine-tuned on documents that explicitly mark claims as false still learn the claims as true. Experiments with fabricated statements found models often absorb entity-event associations more strongly than surrounding warnings or negations. The finding raises concerns for fine-tuning pipelines, misinformation handling, and AI safety datasets that include harmful or false content with disclaimers.
Exploring the context of online images with Backstory★ 75
Google DeepMind Blog221d agoNew ToolGoogle DeepMind 發表全新實驗性 AI 工具「Backstory」，旨在幫助使用者探索網路圖片的脈絡與起源。該工具能分析圖片的傳播歷史、原始出處及可能的修改痕跡，協助使用者在假訊息充斥的網路環境中辨識真偽。這項技術展現了多模態 AI 在提升數位素養與打擊不實資訊方面的潛力。