|
--- |
|
license: llama2 |
|
--- |
|
|
|
SLIMER is an instruction-tuned LLM (LLaMA-2-7B based) for NER. |
|
Instructed on a reduced number of samples, it is designed to tackle never-seen-before named entity tags by leveraging a prompt enriched with a definition and guidelines for the NE to be extracted. |
|
|
|
<img src="https://huggingface.co/expertai/SLIMER/resolve/main/SLIMER_instruction_prompt.png" width="200"> |
|
|
|
SLIMER performs comparably to state-of-the-art approaches in out-of-domain zero-shot NER, while being trained on a reduced tag set. |
|
|
|
<img src="https://huggingface.co/expertai/SLIMER/resolve/main/OOD_evals.png"> |
