stellalisy/HorizonBench download history

stellalisy/HorizonBench is a multiple choice dataset on the Hugging Face Hub. In the last 30 days it was downloaded 1,112 times (367 in the last 7 days), and 4,571 times in total. It ranks #17,854 among datasets by monthly downloads.

HorizonBench Long-Horizon Personalization with Evolving Preferences HorizonBench evaluates whether language models can track user preferences as they evolve across months of interaction. Each benchmark item is a 5-option multiple-choice question embedded within a conversation history aver

Open stellalisy/HorizonBench on Hugging Face

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.