AI RESEARCH
Causal Drawbridges: Characterizing Gradient Blocking of Syntactic Islands in Transformer LMs
arXiv CS.CL
•
ArXi:2604.13950v1 Announce Type: new We show how causal interventions in Transformer models provide insights into English syntax by focusing on a long-standing challenge for syntactic theory: syntactic islands. Extraction from coordinated verb phrases is often degraded, yet acceptability varies gradiently with lexical content (e.g., "I know what he hates art and loves" vs. "I know what he looked down and saw"). We show that modern Transformer language models replicate human judgments across this gradient.