一作ACL 2026Poster· Natural Language Processing
A BERT ology View of LLM Orchestrations: Token- and Layer-Selective Probes for Efficient Single-Pass Classification
Gonzalo Ariel Meyoyan · Luciano Del Corro
摘要
Production LLM systems often rely on separate models for safety and other classification-heavy steps, increasing latency, VRAM footprint, and operational complexity. We instead reuse computation already paid for by the serving LLM: we train lightweight probes on its hidden states and predict labe...