Papers by Gonzalo Ariel Meyoyan
A BERTology View of LLM Orchestrations: Token- and Layer-Selective Probes for Efficient Single-Pass Classification (2026.acl-long)
Copied to clipboard
| Challenge: | Modern LLM deployments are rarely a single model in isolation. |
| Approach: | They propose a model that reuses computation already paid for by the serving LLM . they instantiate a template with pooling, a scoring-attention gate, and a downcast multi-head self-attention probe . |
| Outcome: | The proposed model improves safety and sentiment benchmarks on dense and mixture-of-experts architectures while preserving near-serving latency. |