1
Re-Centering Humans in LLM Personalization
别再迷信合成数据，这项研究直指LLM个性化在真实用户场景下的性能短板，呼唤以人为中心的评估。
arXiv:2606.06614v1 Announce Type: cross Abstract: Despite growing interest, most evaluations of large language models' (LLMs') personalization abiliti…