Description: A UniNER-7B model trained from LLama-7B using the
Pile-NER-type data without human-labeled data. The data was collected by prompting gpt-3.5-turbo-0301 to label entities from passages and provide entity tags. The data collection prompt is as follows:
Check our
paper for more information. Check our
repo about how to use the model.
The UniNER-7B-type model excels when handling entity tags. It performs better on the Universal NER benchmark, which consists of 43 academic datasets across 9 domains. In contrast, UniNER-7B-definition performs better at processing entity types defined in short sentences and is more robust to type paraphrasing.
This model and its associated data are released under the
CC BY-NC 4.0 license. They are primarily used for research purposes.
1@article{zhou2023universalner,
2 title={UniversalNER: Targeted Distillation from Large Language Models for Open Named Entity Recognition},
3 author={Wenxuan Zhou and Sheng Zhang and Yu Gu and Muhao Chen and Hoifung Poon},
4 year={2023},
5 eprint={2308.03279},
6 archivePrefix={arXiv},
7 primaryClass={cs.CL}
8}
