pith. sign in

arxiv: 2409.11022 · v7 · pith:XWCEWSK6new · submitted 2024-09-17 · 💻 cs.CL · cs.AI

DynamicNER: A Dynamic, Multilingual, and Fine-Grained Dataset for LLM-based Named Entity Recognition

Hanjun Luo , Yingbin Jin , Xinfeng Li , Xuecheng Liu , Ruizhe Chen , Tong Shang , Kun Wang , Qingsong Wen
show 1 more author
Zuozhu Liu
This is my paper

Pith reviewed 2026-05-23 20:37 UTC · model grok-4.3

classification 💻 cs.CL cs.AI
keywords named entity recognitionlarge language modelsdynamic datasetmultilingual NERfine-grained entitiesbenchmark datasetCascadeNER
0
0 comments X

The pith

DynamicNER introduces varying entity type lists for identical entities across contexts to benchmark LLM named entity recognition more effectively than fixed datasets.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper claims that existing NER datasets rely on fixed, coarse categories that do not test the contextual understanding and generalization strengths of large language models. It presents DynamicNER as the first dataset built specifically for LLMs, using dynamic categorization so the same entity receives different type lists depending on surrounding text. The resource covers eight languages, 155 entity types, and multiple domains, and is paired with a two-stage method called CascadeNER that uses lightweight LLMs for fine-grained labeling. Experiments position DynamicNER as a benchmark that better reveals LLM performance on NER tasks compared with traditional fixed datasets. If the claim holds, evaluation of LLM-based NER will shift toward dynamic setups that expose capabilities hidden by static labels.

Core claim

DynamicNER is the first NER dataset designed for LLM-based methods with dynamic categorization, introducing various entity types and entity type lists for the same entity in different context, leveraging the generalization of LLM-based NER better. The dataset is multilingual and multi-granular, covering 8 languages and 155 entity types, with corpora spanning a diverse range of domains. CascadeNER, a novel NER method based on a two-stage strategy and lightweight LLMs, achieves higher accuracy on fine-grained tasks while requiring fewer computational resources. Experiments show that DynamicNER serves as a robust and effective benchmark for LLM-based NER methods.

What carries the argument

Dynamic categorization, in which the same entity is assigned different entity type lists depending on context, to better expose LLM generalization and contextual understanding.

If this is right

  • LLM-based NER methods can be evaluated on their ability to handle varying type lists for the same entities.
  • CascadeNER demonstrates that a two-stage lightweight LLM approach can reach higher accuracy on fine-grained NER with lower resource use.
  • Multilingual coverage across eight languages allows direct comparison of LLM NER performance across languages on the same dynamic framework.
  • Analysis of both traditional and LLM methods on DynamicNER reveals differences in how each handles dynamic entity lists.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • Dynamic label sets could be applied to other sequence labeling tasks to test model adaptability beyond NER.
  • Training procedures that explicitly vary entity type lists during fine-tuning might further improve LLM robustness.
  • The dataset design suggests that future benchmarks in information extraction should incorporate context-dependent label variation as a standard feature.

Load-bearing premise

Fixed and coarse-grained entity categories in existing datasets cannot adequately measure how LLMs use context and generalize across entity types.

What would settle it

An experiment in which LLM-based NER systems show no improvement in measured generalization or contextual performance on DynamicNER compared with performance on conventional fixed-category datasets would undermine the claim that dynamic categorization is needed.

Figures

Figures reproduced from arXiv: 2409.11022 by Hanjun Luo, Kun Wang, Qingsong Wen, Ruizhe Chen, Tong Shang, Xinfeng Li, Xuecheng Liu, Yingbin Jin, Zuozhu Liu.

Figure 1
Figure 1. Figure 1: The coarse-grained and medium-grained cat [PITH_FULL_IMAGE:figures/full_fig_p003_1.png] view at source ↗
Figure 3
Figure 3. Figure 3: Pipeline of dynamic categorization. Blue [PITH_FULL_IMAGE:figures/full_fig_p004_3.png] view at source ↗
Figure 2
Figure 2. Figure 2: Examples of dynamic categorization. The red [PITH_FULL_IMAGE:figures/full_fig_p004_2.png] view at source ↗
Figure 4
Figure 4. Figure 4: Use a sentence and the multi-granularity categories of DynamicNER as the example. The extractor and [PITH_FULL_IMAGE:figures/full_fig_p006_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Example prompts of classification. In zero-shot scenarios, we use a slightly different prompt. Due to differences in entity categorization across datasets, some entities in one dataset may be overlooked in others. We append the query with If none of them applied, return unknown to handle situations where the extracted entity cannot be classified into the provided categories, enhanc￾ing CascadeNER’s general… view at source ↗
Figure 6
Figure 6. Figure 6: Quantitative categorization metric results for 3 versions DynamicNER in English and Chinese. Generally, [PITH_FULL_IMAGE:figures/full_fig_p008_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: The curves showing visualized precision, re [PITH_FULL_IMAGE:figures/full_fig_p016_7.png] view at source ↗
Figure 9
Figure 9. Figure 9: Examples for the three parts of the prompt for [PITH_FULL_IMAGE:figures/full_fig_p017_9.png] view at source ↗
Figure 10
Figure 10. Figure 10: Quantitative categorization metric results for 3 versions DynamicNER. [PITH_FULL_IMAGE:figures/full_fig_p020_10.png] view at source ↗
read the original abstract

The advancements of Large Language Models (LLMs) have spurred a growing interest in their application to Named Entity Recognition (NER) methods. However, existing datasets are primarily designed for traditional machine learning methods and are inadequate for LLM-based methods, in terms of corpus selection and overall dataset design logic. Moreover, the prevalent fixed and relatively coarse-grained entity categorization in existing datasets fails to adequately assess the superior generalization and contextual understanding capabilities of LLM-based methods, thereby hindering a comprehensive demonstration of their broad application prospects. To address these limitations, we propose DynamicNER, the first NER dataset designed for LLM-based methods with dynamic categorization, introducing various entity types and entity type lists for the same entity in different context, leveraging the generalization of LLM-based NER better. The dataset is also multilingual and multi-granular, covering 8 languages and 155 entity types, with corpora spanning a diverse range of domains. Furthermore, we introduce CascadeNER, a novel NER method based on a two-stage strategy and lightweight LLMs, achieving higher accuracy on fine-grained tasks while requiring fewer computational resources. Experiments show that DynamicNER serves as a robust and effective benchmark for LLM-based NER methods. Furthermore, we also conduct analysis for traditional methods and LLM-based methods on our dataset. Our code and dataset are openly available at https://github.com/Astarojth/DynamicNER.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 2 minor

Summary. The paper claims that existing NER datasets are inadequate for LLM-based methods due to their fixed, coarse-grained design, which fails to test generalization and contextual understanding. It introduces DynamicNER as the first dataset tailored for LLMs, featuring dynamic categorization (varying entity type lists for the same entity across contexts), multilingual coverage (8 languages), 155 entity types, and diverse domains. It also proposes CascadeNER, a two-stage method using lightweight LLMs that achieves higher accuracy on fine-grained tasks with lower computational cost. Experiments are said to demonstrate that DynamicNER is a robust benchmark, accompanied by analysis comparing traditional and LLM-based methods on the dataset. Code and data are released openly.

Significance. If the dataset construction, validation, and experimental results are sound, DynamicNER could fill a genuine gap by providing a benchmark that better evaluates LLM generalization in NER, moving beyond the limitations of fixed datasets. The open release of code and dataset is a clear strength that supports reproducibility and community use.

major comments (2)
  1. [Abstract] Abstract: The central claim that DynamicNER 'serves as a robust and effective benchmark' and that CascadeNER achieves 'higher accuracy' is stated without any quantitative results, baselines, dataset statistics, validation metrics, or error analysis. This absence prevents assessment of whether the dynamic design actually demonstrates the claimed LLM advantages.
  2. [Dataset Construction and Experiments] Dataset construction and experimental sections: No details are provided on how dynamic entity type lists are generated per context, how annotation consistency is ensured across the 155 types and 8 languages, inter-annotator agreement, or the exact experimental setup (train/test splits, baselines, metrics). These elements are load-bearing for the claim that the dataset is superior for assessing LLM capabilities.
minor comments (2)
  1. [Introduction] The motivation section would benefit from a concrete example of dynamic categorization (same entity, different type lists in different contexts) to illustrate the key innovation.
  2. [Dataset Description] Clarify the precise definition of 'multi-granular' and how the 155 types are organized hierarchically or otherwise.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for their thoughtful review and constructive feedback. We address each major comment below and commit to revising the manuscript to strengthen clarity and completeness.

read point-by-point responses

  1. Referee: [Abstract] Abstract: The central claim that DynamicNER 'serves as a robust and effective benchmark' and that CascadeNER achieves 'higher accuracy' is stated without any quantitative results, baselines, dataset statistics, validation metrics, or error analysis. This absence prevents assessment of whether the dynamic design actually demonstrates the claimed LLM advantages.

    Authors: We acknowledge that the abstract, in its current form, presents high-level claims without supporting numbers. While the body of the paper contains quantitative results, baselines, and analysis in the Experiments section, we agree the abstract would be strengthened by including key highlights. In the revision we will incorporate concise quantitative statements (e.g., accuracy gains on fine-grained tasks and basic dataset statistics) into the abstract. revision: yes

  2. Referee: [Dataset Construction and Experiments] Dataset construction and experimental sections: No details are provided on how dynamic entity type lists are generated per context, how annotation consistency is ensured across the 155 types and 8 languages, inter-annotator agreement, or the exact experimental setup (train/test splits, baselines, metrics). These elements are load-bearing for the claim that the dataset is superior for assessing LLM capabilities.

    Authors: We agree these procedural details are essential. The current manuscript provides an overview but lacks sufficient granularity. In the revised version we will expand the Dataset Construction section to explicitly describe the process for generating context-specific dynamic entity type lists, the annotation protocol and quality-control steps used across languages and the 155 types, inter-annotator agreement statistics, and the precise experimental configuration (splits, baselines, metrics, and evaluation protocol). revision: yes

Circularity Check

0 steps flagged

No significant circularity

full rationale

The paper introduces a new dataset (DynamicNER) and method (CascadeNER) for LLM-based NER without any mathematical derivations, parameter fitting, or predictive claims that reduce to inputs by construction. Claims rest on dataset construction details, multilingual coverage, and empirical experiments rather than self-citation chains or self-definitional loops. No load-bearing steps match the enumerated circularity patterns; the work is self-contained as an empirical contribution.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

Dataset and method paper with no mathematical model, no fitted parameters, no invoked axioms, and no new postulated entities beyond standard NER concepts.

pith-pipeline@v0.9.0 · 5801 in / 1004 out tokens · 30109 ms · 2026-05-23T20:37:53.939056+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

58 extracted references · 58 canonical work pages · 9 internal anchors

  1. [1]

    online" 'onlinestring :=

    ENTRY address archivePrefix author booktitle chapter edition editor eid eprint eprinttype howpublished institution journal key month note number organization pages publisher school series title type volume year doi pubmed url lastchecked label extra.label sort.label short.list INTEGERS output.state before.all mid.sentence after.sentence after.block STRING...

    work page

  2. [2]

    write newline

    " write newline "" before.all 'output.state := FUNCTION n.dashify 't := "" t empty not t #1 #1 substring "-" = t #1 #2 substring "--" = not "--" * t #2 global.max substring 't := t #1 #1 substring "-" = "-" * t #2 global.max substring 't := while if t #1 #1 substring * t #2 global.max substring 't := if while FUNCTION word.in bbl.in capitalize " " * FUNCT...

    work page

  3. [3]

    Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al. 2023. Gpt-4 technical report. arXiv preprint arXiv:2303.08774

    work page internal anchor Pith review Pith/arXiv arXiv 2023

  4. [4]

    Anthropic. 2023. Claude: An ai assistant by anthropic. https://www.anthropic.com/index/claude. Accessed: [date of access]

    work page 2023

  5. [5]

    Dhananjay Ashok and Zachary C Lipton. 2023. Promptner: Prompting for named entity recognition. arXiv preprint arXiv:2305.15444

    work page arXiv 2023

  6. [6]

    Jinze Bai, Shuai Bai, Yunfei Chu, Zeyu Cui, Kai Dang, Xiaodong Deng, Yang Fan, Wenbin Ge, Yu Han, Fei Huang, et al. 2023. Qwen technical report. arXiv preprint arXiv:2309.16609

    work page internal anchor Pith review Pith/arXiv arXiv 2023

  7. [7]

    Emily M Bender and Batya Friedman. 2018. Data statements for natural language processing: Toward mitigating system bias and enabling better science. Transactions of the Association for Computational Linguistics, 6:587--604

    work page 2018

  8. [8]

    Tom B Brown. 2020. Language models are few-shot learners. arXiv preprint arXiv:2005.14165

    work page internal anchor Pith review Pith/arXiv arXiv 2020

  9. [9]

    Aakanksha Chowdhery, Sharan Narang, Jacob Devlin, Maarten Bosma, Gaurav Mishra, Adam Roberts, Paul Barham, Hyung Won Chung, Charles Sutton, Sebastian Gehrmann, et al. 2023. Palm: Scaling language modeling with pathways. Journal of Machine Learning Research, 24(240):1--113

    work page 2023

  10. [10]

    Alexis Conneau, Kartikay Khandelwal, Naman Goyal, Vishrav Chaudhary, Guillaume Wenzek, Francisco Guzm \'a n, Edouard Grave, Myle Ott, Luke Zettlemoyer, and Veselin Stoyanov. 2020. Unsupervised cross-lingual representation learning at scale. arXiv preprint arXiv:1911.02116

    work page internal anchor Pith review Pith/arXiv arXiv 2020

  11. [11]

    Badhan Chandra Das, M Hadi Amini, and Yanzhao Wu. 2024. Security and privacy challenges of large language models: A survey. ACM Computing Surveys

    work page 2024

  12. [12]

    Jiangyi Deng, Xinfeng Li, Yanjiao Chen, Yijie Bai, Haiqin Weng, Yan Liu, Tao Wei, and Wenyuan Xu. 2025. RACONTEUR : A knowledgeable, insightful, and portable LLM -powered shell command explainer. In Proceedings of the 32nd Annual Network and Distributed System Security Symposium, NDSS

    work page 2025

  13. [13]

    Leon Derczynski, Eric Nichols, Marieke van Erp, and Nut Limsopatham. 2017. Results of the wnut2017 shared task on novel and emerging entity recognition. In Proceedings of the 3rd Workshop on Noisy User-generated Text, pages 140--147

    work page 2017

  14. [14]

    Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805

    work page internal anchor Pith review Pith/arXiv arXiv 2018

  15. [15]

    Ning Ding, Guangwei Xu, Yulin Chen, Xiaobin Wang, Xu Han, Pengjun Xie, Haitao Zheng, Zhiyuan Liu, Juanzi Li, Maosong Sun, and Jing Zhou. 2021. https://doi.org/10.18653/v1/2021.acl-long.491 F ew- NERD : A few-shot named entity recognition dataset . In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th Inter...

    work page doi:10.18653/v1/2021.acl-long.491 2021

  16. [16]

    George R Doddington, Alexis Mitchell, Mark Przybocki, Lance Ramshaw, Stephanie Strassel, and Ralph Weischedel. 2004. The automatic content extraction (ace) program-tasks, data, and evaluation. In LREC, pages 837--840

    work page 2004

  17. [17]

    Besnik Fetahu, Anjie Fang, Oleg Rokhlenko, and Shervin Malmasi. 2022. Dynamic gazetteer integration in multilingual models for cross-lingual and cross-domain named entity recognition. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 2777--2790

    work page 2022

  18. [18]

    Mohammad Aqib Ganaie, Minmin Hu, M I Tanveer, and Ponnuthurai Nagaratnam Suganthan. 2022. Ensemble deep learning: A review. arXiv preprint arXiv:2104.02395

    work page arXiv 2022

  19. [19]

    Andrea Gasparetto, Matteo Marcuzzo, Alessandro Zangari, and Andrea Albarelli. 2022. A survey on text classification algorithms: From text to predictions. Information, 13(2):83

    work page 2022

  20. [20]

    Timnit Gebru, Jamie Morgenstern, Briana Vecchione, Jennifer Wortman Vaughan, Hanna Wallach, Hal Daumé III, and Kate Crawford. 2021. Datasheets for datasets. Communications of the ACM, 64(12):86--92

    work page 2021

  21. [21]

    Corrado Gini. 1921. Measurement of inequality of incomes. The economic journal, 31(121):124--125

    work page 1921

  22. [22]

    Dirk Hovy and Shannon L Spruit. 2016. The social impact of natural language processing. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, pages 591--598

    work page 2016

  23. [23]

    Shengding Hu, Yuge Tu, Xu Han, Chaoqun He, Ganqu Cui, Xiang Long, Zhi Zheng, Yewei Fang, Yuxiang Huang, Weilin Zhao, et al. 2024 a . Minicpm: Unveiling the potential of small language models with scalable training strategies. arXiv preprint arXiv:2404.06395

    work page internal anchor Pith review Pith/arXiv arXiv 2024

  24. [24]

    Yan Hu, Qingyu Chen, Jingcheng Du, Xueqing Peng, Vipina Kuttichi Keloth, Xu Zuo, Yujia Zhou, Zehan Li, Xiaoqian Jiang, Zhiyong Lu, et al. 2024 b . Improving large language models for clinical named entity recognition via prompt engineering. Journal of the American Medical Informatics Association, page ocad259

    work page 2024

  25. [25]

    HuggingFace. 2024. Open source ai year in review 2024. https://huggingface.co/spaces/huggingface/open-source-ai-year-in-review-2024

    work page 2024

  26. [26]

    Vipina K Keloth, Yan Hu, Qianqian Xie, Xueqing Peng, Yan Wang, Andrew Zheng, Melih Selek, Kalpana Raja, Chih Hsuan Wei, Qiao Jin, et al. 2024. Advancing entity recognition in biomedicine via instruction tuning of large language models. Bioinformatics, 40(4):btae163

    work page 2024

  27. [27]

    Jin-Dong Kim, Tomoko Ohta, Yuka Tateisi, and Jun'ichi Tsujii. 2003. Genia corpus—a semantically annotated corpus for bio-textmining. In Bioinformatics, volume 19, pages i180--i182. Oxford University Press

    work page 2003

  28. [28]

    Mingchen Li and Rui Zhang. 2023. How far is language model from 100\ arXiv preprint arXiv:2307.00186

    work page arXiv 2023

  29. [29]

    Xiaoya Li, Jingrong Feng, Yuxian Meng, Qinghong Han, Fei Wu, and Jiwei Li. 2019 a . A unified mrc framework for named entity recognition. arXiv preprint arXiv:1910.11476

    work page arXiv 2019

  30. [30]

    Xiaoya Li, Xiaofei Sun, Yuxian Meng, Junjun Liang, Fei Wu, and Jiwei Li. 2019 b . Dice loss for data-imbalanced nlp tasks. arXiv preprint arXiv:1911.02855

    work page arXiv 2019

  31. [31]

    Xuezhe Li and Xiaodan Sun. 2020. Dice loss for data-imbalanced nlp tasks: Application to named entity recognition. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 4653--4661

    work page 2020

  32. [32]

    Hongbin Liu, Ruixuan Xu, and Wei Xu. 2021. https://doi.org/10.18653/v1/2021.acl-long.385 C ross NER : Evaluating cross-domain named entity recognition . In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 4984--4...

    work page doi:10.18653/v1/2021.acl-long.385 2021

  33. [33]

    Shervin Malmasi, Ning Zhang, Daniella Semedo, Ryan Ip, Aitor Gonzalez Aguirre, Leon Derczynski, and Isabelle Augenstein. 2022. https://aclanthology.org/2022.lrec-1.547 M ulti C o NER : A large-scale multilingual dataset for complex named entity recognition . In Proceedings of the 13th Language Resources and Evaluation Conference, pages 5102--5112. Europea...

    work page 2022

  34. [34]

    Tao Meng, Anjie Fang, Oleg Rokhlenko, and Shervin Malmasi. 2021. https://doi.org/10.18653/v1/2021.naacl-main.118 Gemnet: Effective gated gazetteer representations for recognizing complex entities in low-context input . In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Techn...

    work page doi:10.18653/v1/2021.naacl-main.118 2021

  35. [35]

    Humza Naveed, Asad Ullah Khan, Shi Qiu, Muhammad Saqib, Saeed Anwar, Muhammad Usman, Naveed Akhtar, Nick Barnes, and Ajmal Mian. 2023. A comprehensive overview of large language models. arXiv preprint arXiv:2307.06435

    work page internal anchor Pith review Pith/arXiv arXiv 2023

  36. [36]

    Thien Huu Nguyen and Hung Le Cao. 2010. Nested named entity recognition using maximum entropy models. In Proceedings of the 24th International Conference on Computational Linguistics (COLING), pages 2010--2018. ACL

    work page 2010

  37. [37]

    Rasha Obeidat, Xiaoli Fern, Hamed Shahbazi, and Prasad Tadepalli. 2019. Description-based zero-shot fine-grained entity typing. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 807--814

    work page 2019

  38. [38]

    Xiaoman Pan, Boliang Zhang, Jonathan May, Joel Nothman, Kevin Knight, and Heng Ji. 2017. https://doi.org/10.18653/v1/P17-1178 Cross-lingual name tagging and linking for 282 languages . In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1946--1958, Vancouver, Canada. Association for Com...

    work page doi:10.18653/v1/p17-1178 2017

  39. [39]

    Sameer Pradhan, Alessandro Moschitti, Nianwen Xue, Hwee Tou Ng, Anders Bj \"o rkelund, Olga Uryupina, Yuchen Zhang, and Zhi Zhong. 2013. Towards robust linguistic analysis using OntoNotes . In Proceedings of the Seventeenth Conference on Computational Natural Language Learning, pages 143--152. Association for Computational Linguistics

    work page 2013

  40. [40]

    Xiang Ren, Wenqi He, Meng Qu, Clare R Voss, Heng Ji, and Jiawei Han. 2016. Label noise reduction in entity typing by heterogeneous partial-label embedding. In Proceedings of the 22nd ACM SIGKDD international conference on Knowledge discovery and data mining, pages 1825--1834

    work page 2016

  41. [41]

    Prateek Sancheti, Kamalakar Karlapalem, and Kavita Vemuri. 2024. Llm driven web profile extraction for identical names. In Companion Proceedings of the ACM on Web Conference 2024, pages 1616--1625

    work page 2024

  42. [42]

    Wujun Shao, Yaohua Hu, Pengli Ji, Xiaoran Yan, Dongwei Fan, and Rui Zhang. 2023. Prompt-ner: Zero-shot named entity recognition in astronomy literature via large language models. arXiv preprint arXiv:2310.17892

    work page arXiv 2023

  43. [43]

    Yongliang Shen, Xinyin Ma, Zeqi Tan, Shuai Zhang, Wen Wang, and Weiming Lu. 2021. Locate and label: A two-stage identifier for nested named entity recognition. arXiv preprint arXiv:2105.06804

    work page arXiv 2021

  44. [44]

    Gemma Team, Thomas Mesnard, Cassidy Hardin, Robert Dadashi, Surya Bhupatiraju, Shreya Pathak, Laurent Sifre, Morgane Rivi \`e re, Mihir Sanjay Kale, Juliette Love, et al. 2024. Gemma: Open models based on gemini research and technology. arXiv preprint arXiv:2403.08295

    work page internal anchor Pith review Pith/arXiv arXiv 2024

  45. [45]

    Tjong Kim Sang

    Erik F. Tjong Kim Sang. 2002. https://aclanthology.org/W02-2024 Introduction to the C o NLL -2002 shared task: Language-independent named entity recognition . In Proceedings of the 6th Conference on Natural Language Learning ( C o NLL -2002) , pages 155--158

    work page 2002

  46. [46]

    Tjong Kim Sang and Fien De Meulder

    Erik F. Tjong Kim Sang and Fien De Meulder. 2003. https://aclanthology.org/W03-0419 Introduction to the C o NLL-2003 shared task: Language-independent named entity recognition . In Proceedings of the Seventh Conference on Natural Language Learning at HLT-NAACL 2003 , pages 142--147. Association for Computational Linguistics

    work page 2003

  47. [47]

    Neeraj Varshney and Chitta Baral. 2022. Model cascading: Towards jointly improving efficiency and accuracy of nlp systems. arXiv preprint arXiv:2210.05528

    work page arXiv 2022

  48. [48]

    Christopher Walker, Stephanie Strassel, Julie Medero, and Kazuaki Maeda. 2006. Ace 2005 multilingual training corpus. In Linguistic Data Consortium, Philadelphia

    work page 2006

  49. [49]

    Shuhe Wang, Xiaofei Sun, Xiaoya Li, Rongbin Ouyang, Fei Wu, Tianwei Zhang, Jiwei Li, and Guoyin Wang. 2023. Gpt-ner: Named entity recognition via large language models. arXiv preprint arXiv:2304.10428

    work page arXiv 2023

  50. [50]

    Xinyu Wang, Yong Jiang, Nguyen Bach, Tao Wang, Zhongqiang Huang, Fei Huang, and Kewei Tu. 2020. Automated concatenation of embeddings for structured prediction. arXiv preprint arXiv:2010.05006

    work page arXiv 2020

  51. [51]

    Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, et al. 2022. Chain-of-thought prompting elicits reasoning in large language models. Advances in neural information processing systems, 35:24824--24837

    work page 2022

  52. [52]

    Ralph Weischedel, Sameer Pradhan, Lance Ramshaw, Martha Palmer, Nianwen Xue, Mitchell Marcus, Ann Taylor, Claudette Greenberg, Eduard Hovy, Robert Belvin, et al. 2011. Ontonotes: A large training corpus for enhanced processing. In Handbook of Natural Language Processing and Machine Translation, pages 54--63. Springer

    work page 2011

  53. [53]

    Shuhui Wu, Yongliang Shen, Zeqi Tan, and Weiming Lu. 2022. Propose-and-refine: A two-stage set prediction network for nested named entity recognition. arXiv preprint arXiv:2204.12732

    work page arXiv 2022

  54. [54]

    Le Xiao, Yunfei Xu, and Jing Zhao. 2024. Llm-der: A named entity recognition method based on large language models for chinese coal chemical domain. arXiv preprint arXiv:2409.10077

    work page arXiv 2024

  55. [55]

    Tingyu Xie, Qi Li, Jian Zhang, Yan Zhang, Zuozhu Liu, and Hongwei Wang. 2023. Empirical study of zero-shot ner with chatgpt. arXiv preprint arXiv:2310.10035

    work page arXiv 2023

  56. [56]

    Juntao Yu, Bernd Bohnet, and Massimo Poesio. 2020. Named entity recognition as dependency parsing. arXiv preprint arXiv:2005.07150

    work page arXiv 2020

  57. [57]

    Dawen Zhang, Pamela Finckenberg-Broman, Thong Hoang, Shidong Pan, Zhenchang Xing, Mark Staples, and Xiwei Xu. 2024. Right to be forgotten in the era of large language models: Implications, challenges, and solutions. AI and Ethics, pages 1--10

    work page 2024

  58. [58]

    Zhuosheng Zhang, Aston Zhang, Mu Li, and Alex Smola. 2022. Automatic chain of thought prompting in large language models. arXiv preprint arXiv:2210.03493

    work page internal anchor Pith review Pith/arXiv arXiv 2022