# GenCNER: A Generative Framework for Continual Named Entity Recognition

arXiv: https://arxiv.org/abs/2510.11444 · HTML: https://mlsanity.com/paper/2510.11444/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 34 references that are in the map.
- First posted on arXiv 13 Oct 2025.

## Builds on (most cited first, 26 of 26)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Pointer Networks](https://mlsanity.com/paper/1506.03134/) (2015)
- [FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labeling](https://mlsanity.com/paper/2110.08263/) (2021)
- [MASS: Masked Sequence to Sequence Pre-training for Language Generation](https://mlsanity.com/paper/1905.02450/) (2019)
- [A Survey on Deep Learning for Named Entity Recognition](https://mlsanity.com/paper/1812.09449/) (2018)
- [FreeMatch: Self-adaptive Thresholding for Semi-supervised Learning](https://mlsanity.com/paper/2205.07246/) (2022)
- [Incorporating Copying Mechanism in Sequence-to-Sequence Learning](https://mlsanity.com/paper/1603.06393/) (2016)
- [Class-Incremental Learning: A Survey](https://mlsanity.com/paper/2302.03648/) (2023)
- [Few-NERD: A Few-Shot Named Entity Recognition Dataset](https://mlsanity.com/paper/2105.07464/) (2021)
- [Named Entity Recognition as Dependency Parsing](https://mlsanity.com/paper/2005.07150/) (2020)
- [A Unified Generative Framework for Various NER Subtasks](https://mlsanity.com/paper/2106.01223/) (2021)
- [Unified Named Entity Recognition as Word-Word Relation Classification](https://mlsanity.com/paper/2112.10070/) (2021)
- [Knowledge Graph Contrastive Learning for Recommendation](https://mlsanity.com/paper/2205.00976/) (2022)
- [Locate and Label: A Two-stage Identifier for Nested Named Entity Recognition](https://mlsanity.com/paper/2105.06804/) (2021)
- [Neural Architectures for Nested NER through Linearization](https://mlsanity.com/paper/1908.06926/) (2019)
- [Improving Entity Linking by Modeling Latent Relations between Mentions](https://mlsanity.com/paper/1804.10637/) (2018)
- [Semi-supervised Relation Extraction via Incremental Meta Self-Training](https://mlsanity.com/paper/2010.16410/) (2020)
- [Continual Named Entity Recognition without Catastrophic Forgetting](https://mlsanity.com/paper/2310.14541/) (2023)
- [Distilling Causal Effect from Miscellaneous Other-Class for Continual Named Entity Recognition](https://mlsanity.com/paper/2210.03980/) (2022)
- [Learning "O" Helps for Learning More: Handling the Concealed Entity Problem for Class-incremental NER](https://mlsanity.com/paper/2210.04676/) (2022)
- [A Neural Span-Based Continual Named Entity Recognition Model](https://mlsanity.com/paper/2302.12200/) (2023)
- [Incremental Sequence Labeling: A Tale of Two Shifts](https://mlsanity.com/paper/2402.10447/) (2024)
- [Concept Extraction to Identify Adverse Drug Reactions in Medical Forums: A Comparison of Algorithms](https://mlsanity.com/paper/1504.06936/) (2015)

## Abstract (arXiv)

Traditional named entity recognition (NER) aims to identify text mentions into pre-defined entity types. Continual Named Entity Recognition (CNER) is introduced since entity categories are continuously increasing in various real-world scenarios. However, existing continual learning (CL) methods for NER face challenges of catastrophic forgetting and semantic shift of non-entity type. In this paper, we propose GenCNER, a simple but effective Generative framework for CNER to mitigate the above drawbacks. Specifically, we skillfully convert the CNER task into sustained entity triplet sequence generation problem and utilize a powerful pre-trained seq2seq model to solve it. Additionally, we design a type-specific confidence-based pseudo labeling strategy along with knowledge distillation (KD) to preserve learned knowledge and alleviate the impact of label noise at the triplet level. Experimental results on two benchmark datasets show that our framework outperforms previous state-of-the-art methods in multiple CNER settings, and achieves the smallest gap compared with non-CL results.