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

arXiv: https://arxiv.org/abs/2608.00538 · HTML: https://mlsanity.com/paper/2608.00538/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 22 references that are in the map.
- First posted on arXiv 1 Aug 2026.

## Builds on (most cited first, 9 of 9)

- [CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society](https://mlsanity.com/paper/2303.17760/) (2023)
- [Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate](https://mlsanity.com/paper/2305.19118/) (2023)
- [InstructUIE: Multi-task Instruction Tuning for Unified Information Extraction](https://mlsanity.com/paper/2304.08085/) (2023)
- [Template-Based Named Entity Recognition Using BART](https://mlsanity.com/paper/2106.01760/) (2021)
- [GeneGPT: Augmenting Large Language Models with Domain Tools for Improved Access to Biomedical Information](https://mlsanity.com/paper/2304.09667/) (2023)
- [STaR-GATE: Teaching Language Models to Ask Clarifying Questions](https://mlsanity.com/paper/2403.19154/) (2024)
- [BOND: BERT-Assisted Open-Domain Named Entity Recognition with Distant Supervision](https://mlsanity.com/paper/2006.15509/) (2020)
- [LLMaAA: Making Large Language Models as Active Annotators](https://mlsanity.com/paper/2310.19596/) (2023)
- [Prompt-Learning for Fine-Grained Entity Typing](https://mlsanity.com/paper/2108.10604/) (2021)

## Abstract (arXiv)

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.