Work

ToMMeR - Efficient Entity Mention Detection from Large Language Models

Year: 2026

Type: conference-paper

Abstract: 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 (<300K parameters) probing mention detection capabilities from early LLM layers.Across 13 NER benchmarks, ToMMeR achieves 93% recall zero-shot, with an estimated 90% precision under a humancalibrated LLM-judge protocol, showing that ToMMeR rarely produces spurious predictions despite high recall.Cross-model analysis reveals that diverse architectures (14M-15B parameters) converge on similar mention boundaries (DICE >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.

Source: Proceedings of the conference - Association for Computational Linguistics. Meeting

DOI: 10.18653/v1/2026.acl-long.1268

Authors: Victor Morand, Nadi Tomeh, Josiane Mothe, Benjamin Piwowarski