Saved in:
Bibliographic Details
Main Authors: Bai, Fan, Hassanzadeh, Hamid, Saeedi, Ardavan, Dredze, Mark
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.23722
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911238382944256
author Bai, Fan
Hassanzadeh, Hamid
Saeedi, Ardavan
Dredze, Mark
author_facet Bai, Fan
Hassanzadeh, Hamid
Saeedi, Ardavan
Dredze, Mark
contents In-context learning (ICL) enables large language models (LLMs) to perform new tasks using only a few demonstrations. However, in Named Entity Recognition (NER), existing ICL methods typically rely on task-agnostic semantic similarity for demonstration retrieval, which often yields less relevant examples and leads to inferior results. We introduce DEER, a training-free ICL approach that enables LLMs to make more informed entity predictions through the use of label-grounded statistics. DEER leverages token-level statistics from training labels to identify tokens most informative for entity recognition, enabling entity-focused demonstrations. It further uses these statistics to detect and refine error-prone tokens through a targeted reflection step. Evaluated on five NER datasets across four LLMs, DEER consistently outperforms existing ICL methods and achieves performance comparable to supervised fine-tuning. Further analyses demonstrate that DEER improves example retrieval, remains effective on both seen and unseen entities, and exhibits strong robustness in low-resource settings.
format Preprint
id arxiv_https___arxiv_org_abs_2505_23722
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LLMs are Better Than You Think: Label-Guided In-Context Learning for Named Entity Recognition
Bai, Fan
Hassanzadeh, Hamid
Saeedi, Ardavan
Dredze, Mark
Computation and Language
In-context learning (ICL) enables large language models (LLMs) to perform new tasks using only a few demonstrations. However, in Named Entity Recognition (NER), existing ICL methods typically rely on task-agnostic semantic similarity for demonstration retrieval, which often yields less relevant examples and leads to inferior results. We introduce DEER, a training-free ICL approach that enables LLMs to make more informed entity predictions through the use of label-grounded statistics. DEER leverages token-level statistics from training labels to identify tokens most informative for entity recognition, enabling entity-focused demonstrations. It further uses these statistics to detect and refine error-prone tokens through a targeted reflection step. Evaluated on five NER datasets across four LLMs, DEER consistently outperforms existing ICL methods and achieves performance comparable to supervised fine-tuning. Further analyses demonstrate that DEER improves example retrieval, remains effective on both seen and unseen entities, and exhibits strong robustness in low-resource settings.
title LLMs are Better Than You Think: Label-Guided In-Context Learning for Named Entity Recognition
topic Computation and Language
url https://arxiv.org/abs/2505.23722