# DE-NER : Zero-shot Named Entity Recognition via Dialogue Elicitation of Large Language Models

Source: [DE-NER : Zero-shot Named Entity Recognition via Dialogue Elicitation of Large Language Models](<https://www.sota2.com/research/paper/6a717246bc6f0f0705845cc6>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-08-05T05:00:05.796Z

Authors: Xuankang Zhang, Jiangming Liu

Published: 2026-08-01T08:46:53.000Z

## Abstract

Recent advancements of zero-shot Named Entity Recognition (NER) establish strong baselines by formulating sequence labeling into question answering where Large Language Models (LLMs) can be naturally adopted. However, existing LLM-based zero-shot NER methods suffer from the limitations of prompt and demonstration engineering. To address these issues with minimal human interventions, we introduce DE-NER, a dialogue elicitation framework which elicits the chatting ability of LLMs to fully extract the knowledge encoded in LLMs. Our experiments demonstrate that the proposed method outperform the competitive baselines in zero-shot settings across multiple benchmarks, with an average improvement of 3.75\\% F1 points. Codes are released in https://github.com/kkkenshi/DE-NER.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2608.00538>)

[PDF](<https://arxiv.org/pdf/2608.00538.pdf>)
