{"id":"2609.00921","title":"VIBE-Bench: Evaluating Personalized Large Language Models When Profiles Don't Mean Preferences","url":"https://codeofpaper.com/paper/2609.00921","arxiv_url":"https://arxiv.org/abs/2609.00921","published":"2026-09-01","code":"none","best":null,"most_starred_community":null,"implementations":[],"possible_matches":3}