AI RESEARCH

Gated Tree Cross-Attention for Checkpoint-Compatible Syntax Injection in Decoder-Only LLMs

arXiv CS.CL

ArXi:2602.15846v2 Announce Type: replace Decoder-only large language models achieve strong broad performance but are brittle to minor grammatical perturbations, undermining reliability for downstream reasoning. However, directly injecting explicit syntactic structure into an existing checkpoint can interfere with its pretrained competence. We