Meta tag
Language Models
3 articles
LLMs Finally Admit Theyâre Making Things Up
A new arXiv paper treats LLM hallucinations as a classification errorâand builds a gate to block them before they escape.
13 Apr 2026
DIVE: Scaling Diversity
Researchers at arXiv propose a new method called DIVE, which scales diversity in agentic task synthesis for generalizable tool use, addressing a long-standing challenge in AI research.
29 Mar 2026
UMRâs Missing Piece: How Aspect Labels Could Rewrite NLP
A new arXiv dataset introduces aspect labels to UMR, exposing a long-overlooked gap in event temporal annotation.
29 Mar 2026