Article
StateBench: Testing how language models track state changes over long documents
allenai
• • 18Tony Dzi PRO
TonyDzi
AI & ML interests
AI & ML experiments ˆ_ˆ
Recent Activity
updated a Space 12 minutes ago
PaloAltoAiResearchLab/verbatim-citation-gate published a Space 14 minutes ago
PaloAltoAiResearchLab/verbatim-citation-gate updated a collection 19 minutes ago
Agent reliability: real data & toolsOrganizations
upvoted an article 2 days ago