对话系统大语言模型时代的零样本槽位填充
Zero-shot Slot Filling in the Age of LLMs for Dialogue Systems
AI总结：
针对对话系统中零样本槽位填充难以直接应用于动态对话数据的问题，提出自动数据标注（含槽位归纳）与黑盒知识蒸馏策略，在内部数据集上F1提升26%，并设计高效架构使相对F1提升34%且低延迟。
摘要：
零样本槽位填充是自然语言理解（NLU）的一项成熟子任务。然而，大多数现有方法主要关注单轮文本数据，忽视了对话特有的复杂性。对话数据具有高度动态性，常包含突然的话题转移、中断和隐式指代，即便大语言模型（LLMs）能力显著，也难以直接应用零样本槽位填充技术。本文通过提出自动数据标注策略（含槽位归纳）及从教师LLM到小模型的黑盒知识蒸馏（KD）应对这些挑战，在内部数据集上较普通LLMs的F1分数实现26%的绝对提升；此外，引入适用于呼叫中心产品场景的高效系统架构，较现成抽取式模型的相对F1分数提升34%，能在保持低延迟的同时对对话流进行近实时推理且准确率更高。
英文摘要：
Zero-shot slot filling is a well-established subtask of Natural Language Understanding (NLU). However, most existing methods primarily focus on single-turn text data, overlooking the unique complexities of conversational dialogue. Conversational data is highly dynamic, often involving abrupt topic shifts, interruptions, and implicit references that make it difficult to directly apply zero-shot slot filling techniques, even with the remarkable capabilities of large language models (LLMs). This paper addresses these challenges by proposing strategies for automatic data annotation with slot induction and black-box knowledge distillation (KD) from a teacher LLM to a smaller model, outperforming vanilla LLMs on internal datasets by 26% absolute increase in F1 score. Additionally, we introduce an efficient system architecture for call center product settings that surpasses off-the-shelf extractive models by 34% relative F1 score, enabling near real-time inference on dialogue streams with higher accuracy, while preserving low latency.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
