Search papers, labs, and topics across Lattice.
Yale University
2
0
4
23
Editing continuous features like "verb bias" in LLM steering vectors can predictably shift downstream syntactic preferences, but the link to in-context learning remains elusive.
Automating the detection of subtle grammatical structures in child-directed speech finally lets us quantify the precise linguistic input children receive, potentially settling long-standing debates about innate knowledge vs. distributional learning.
