A Cooperative Multi-Agent Framework for Zero-Shot Named Entity Recognition
Zero-shot named entity recognition (NER) aims to develop entity recognition systems from unannotated text corpora. This task presents substantial challenges due to minimal human intervention. Recent work has adapted large language models (LLMs) for zero-shot NER by crafting specialized prompt templates. And it advances models' self-learning abilities by incorporating self-annotated demonstrations. Two important challenges persist: (i) Correlations between contexts surrounding entities are overlooked, leading to wrong type predictions or entity omissions. (ii) The indiscriminate use of task demonstrations, retrieved through shallow similarity-based strategies, severely misleads LLMs during inference.
Authors
- Maarten de Rijke (ORCID: https://orcid.org/0000-0002-1086-0202)
- Zhumin Chen (ORCID: https://orcid.org/0000-0003-4592-4074)
- Yougang Lyu
- Zihan Wang (ORCID: https://orcid.org/0000-0003-0493-2668)
- Zhaochun Ren (ORCID: https://orcid.org/0000-0002-9076-6565)
- Ziqi Zhao (ORCID: https://orcid.org/0009-0008-3011-5745)
Institutions
- Leiden University (NL)
- Shandong University (CN)
- Amsterdam University of the Arts (NL)
- University of Amsterdam (NL)
Publication Details
- Published
- 2025-04-22
- DOI
- https://doi.org/10.1145/3696410.3714923
- Citations
- 5
- Primary Topic
- Topic Modeling
- Type
- article
- Field-Weighted Citation Impact
- 12.40
Funders
- Shandong University
- European Commission
- National Natural Science Foundation of China
- Nederlandse Organisatie voor Wetenschappelijk Onderzoek
- Natural Science Foundation of Shandong Province
- HORIZON EUROPE Framework Programme