ToMMeR - Efficient Entity Mention Detection from Large Language Models
Victor Morand, Nadi Tomeh Université Sorbonne Paris Nord, Josiane Mothe Univ. Toulouse, Benjamin Piwowarski CNRS / ISIR, Sorbonne Université and CNRS
原文摘要
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 human-calibrated 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.
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表