Few-shot dialogue state tracking (DST) with Large Language Models (LLM) relies on an effective and efficient conversation retriever to find similar in-context examples for prompt learning. Previous works use raw dialogue context as search keys and queries, and a retriever is fine-tuned with annotated dialogues to achieve superior performance. However, the approach is less suited for scaling to new domains or new annotation languages, where fine-tuning data is unavailable. To address this problem, we handle the task of conversation retrieval based on text summaries of the conversations. A LLM-based conversation summarizer is adopted for query and key generation, which enables effective maximum inner product search. To avoid the extra inference cost brought by LLM-based conversation summarization, we further distill a light-weight conversation encoder which produces query embeddings without decoding summaries for test conversations. We validate our retrieval approach on MultiWOZ datasets with GPT-Neo-2.7B and LLaMA-7B/30B. The experimental results show a significant improvement over relevant baselines in real few-shot DST settings.

翻译：少样本对话状态追踪（DST）结合大型语言模型（LLM）依赖于一种有效且高效的对话检索器，以寻找相似的上下文内示例进行提示学习。以往研究采用原始对话上下文作为搜索键和查询，并通过人工标注的对话对检索器进行微调以实现卓越性能。然而，这种方法难以扩展到新领域或新标注语言，因为微调数据不可用。为解决此问题，本文基于对话的文本摘要处理对话检索任务。采用基于LLM的对话摘要器进行查询和键的生成，从而实现有效的最大内积搜索。为避免基于LLM的对话摘要带来的额外推理成本，我们进一步蒸馏出一个轻量级对话编码器，该编码器可在不解码测试对话摘要的情况下生成查询嵌入。我们在MultiWOZ数据集上使用GPT-Neo-2.7B和LLaMA-7B/30B验证了检索方法。实验结果表明，在真实少样本DST场景中，该方法相较于相关基准线有显著改进。