1
Artificial Aphasias in Lesioned Language Models
模拟脑损伤揭示语言模型内部功能组织，开创性“人工失语症”方法。
arXiv:2605.16222v1 Announce Type: cross Abstract: Aphasias, selective language impairments which can arise from brain damage, reveal the functional or…
2
LLM-based Detection of Manipulative Political Narratives
最新研究：用大语言模型精准识别社交媒体上的操纵性政治叙事，区分合法批评与刻意图谋
arXiv:2605.14354v2 Announce Type: replace Abstract: We present a new computational framework for detecting and structuring manipulative political narr…