PaDeLLM-NER: Parallel Decoding in Large Language Models for Named Entity Recognition

In this study, we aim to reduce generation latency for Named Entity Recognition (NER) with Large Language Models (LLMs). The main cause of high latency in LLMs is the sequential decoding process, which autoregressively generates all labels and mentions for NER, significantly increase the sequence length. To this end, we introduce Parallel Decoding in LLM for NER (PaDeLLM-NER), a approach that integrates seamlessly into existing generative model frameworks without necessitating additional modules or architectural modifications. PaDeLLM-NER accelerates decoding by simultaneously generating all mentions at once, i.e., a label-mention pair per sequence. This results in shorter sequences and faster inference. Experiments reveal that PaDeLLM-NER significantly increases inference speed that is 1.76 to 10.22 times faster than the autoregressive approach for both English and Chinese. Concurrently, it maintains the prediction quality as evidenced by the micro F-score that is on par with the state-of-the-art approaches under both zero-shot and supervised setting. All resources are available at https: //github.com/GeorgeLuImmortal/PaDeLLM_NER.