Effective and Efficient Conversation Retrieval for Dialogue State Tracking with Implicit Text Summaries

arXiv:2402.13043v1 Announce Type: new
Abstract: 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 …

abstract arxiv context conversation cs.cl dialogue examples few-shot keys language language models large language large language models llm prompt prompt learning queries raw retrieval search state text tracking type