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：本研究旨在降低大语言模型（LLM）在命名实体识别（NER）任务中的生成延迟。LLM高延迟的主要根源在于其顺序式解码过程——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，我们提出面向NER的大语言模型并行解码方法（PaDeLLM-NER），该方法能无缝集成至现有生成式模型框架，无需额外模块或架构修改。PaDeLLM-NER支持所有提及内容的同步解码，从而降低生成延迟。实验表明，在英文和中文任务中，PaDeLLM-NER的推理速度较自回归方法提升1.76至10.22倍，同时预测质量保持与当前最优方法相当的水平，这一结论在多数据集上均得到验证。