作者位次 #4/4NeurIPS 2026Poster
Geometrically Disentangling Concept Learning from the Language Modeling Loss
Yupei Wang · Neil R Mallinar · Misha Belkin · Alex Warstadt
首次获取该候选人的完整档案及 StartLux 评估共 20 积分；每位用户单独解锁，之后查看免费。主动刷新 20 积分。
实时查找电子邮箱，费用不超过20积分；未找到邮箱不扣费。
Yupei Wang · Neil R Mallinar · Misha Belkin · Alex Warstadt
Kevin Du · Clara Kümpel · Michelle Wastl · Alex Warstadt
Users frequently express their beliefs to large language models (LLMs). In some situations, the LLM should accept these contextual beliefs as true. In others, they should stick to their prior knowledge. Notably, users’ expressions of belief (EoBs) can take linguistically diverse forms—using presu...
Aditya Yadavalli · Tiago Pimentel · Tamar I Regev · Ethan Gotlieb Wilcox · Alex Warstadt
Prosody—the melody of speech—conveys critical information often not captured by the words or text of a message.In this paper, we propose an information-theoretic approach to quantify how much is conveyed by prosody that is not recoverable from text alone, and, crucially, what prosody conveys.Our...
Tatsuki Kuribayashi · Alex Warstadt · Yohei Oseki · Ethan Gotlieb Wilcox
A recent study (CITATION) has shown that human sentence processing behavior, typically measured on syntactically unchallenging constructions, can be effectively modeled using surprisal from early layers of large language models (LLMs). This raises the question of whether such advantages of intern...