Papers with checkpoint-compatible gated tree cross-attention
Gated Tree Cross-Attention for Checkpoint-Compatible Syntax Injection in Decoder-Only LLMs (2026.acl-long)
Copied to clipboard
| Challenge: | Decoder-only large language models are brittle to minor grammatical perturbations, causing reliability problems. |
| Approach: | They propose a checkpoint-compatible gated tree cross-attention branch that reads constituency chunk memory while keeping the backbone architecture unchanged. |
| Outcome: | The proposed framework strengthens syntactic competence beyond continued training benchmarks and transformer backbones without compromising commonsense reasoning. |