ToMMeR - Efficient Entity Mention Detection from Large Language Models

Identifying which text spans refer to entities -mention detection-is both foundational for information extraction and a known performance bottleneck.We introduce ToMMeR, a lightweight model (75%), confirming that mention detection emerges naturally from language modeling.When extended with span classification heads, ToMMeR achieves competitive NER performance (80-87% F1 on standard benchmarks).Our work provides evidence that structured entity representations exist in early transformer layers and can be efficiently recovered with minimal parameters.