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 NE} (PaDeLLM-NER), a approach that integrates seamlessly into existing generative model frameworks without necessitating additional modules or architectural modifications. PaDeLLM-NER allows for the simultaneous decoding of all mentions, thereby reducing generation latency. 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. Simultaneously it maintains the quality of predictions as evidenced by the performance that is on par with the state-of-the-art across various datasets.

翻译：本研究旨在降低基于大语言模型（LLM）进行命名实体识别（NER）时的生成延迟。LLM高延迟的主要原因是其顺序解码过程——该过程自回归地生成NER任务中的所有标签和提及内容，显著增加了序列长度。为此，我们提出PaDeLLM-NER方法，这是一种能够无缝集成到现有生成式模型框架中的并行解码方案，无需额外模块或架构修改。PaDeLLM-NER支持同步解码所有提及内容，从而降低生成延迟。实验表明，在英文和中文任务中，PaDeLLM-NER的推理速度相比自回归方法提升1.76至10.22倍，同时保持预测质量，在多个数据集上的表现与当前最先进方法持平。