S3-DST：在LLM時代的結構化開放領域對話分割與狀態追踪

摘要

傳統的對話狀態追蹤（DST）問題旨在追蹤使用者在使用者-代理對話中的偏好和意圖。雖然對於支持狹窄領域應用的任務導向對話系統已足夠，但基於大型語言模型（LLM）的聊天系統的出現在開放領域對話中引入了許多現實世界的細微差異。這些細微差異表現為在上下文交互作用中增加的複雜性、涵蓋各種主題的延伸對話會話以及更頻繁的上下文轉換。為了應對由演進中的基於LLM的聊天系統引起的這些細微差異，我們提出在開放領域對話系統中每個段落進行聯合對話分割和狀態追蹤。假設一個適用於真正開放領域對話系統的零槍擊設置，我們提出S3-DST，這是一種結構提示技術，利用我們為改善長篇上下文追蹤而設計的一種新穎基礎機制——預先分析回憶。為了展示我們提出的聯合分割和狀態追蹤方法的有效性，我們在一個專有的匿名開放領域對話數據集以及公開可用的DST和分割數據集上評估了S3-DST。在所有數據集和設置中，S3-DST始終優於最先進技術，展示了它在下一代基於LLM的聊天系統中的效力和韌性。

English

The traditional Dialogue State Tracking (DST) problem aims to track user preferences and intents in user-agent conversations. While sufficient for task-oriented dialogue systems supporting narrow domain applications, the advent of Large Language Model (LLM)-based chat systems has introduced many real-world intricacies in open-domain dialogues. These intricacies manifest in the form of increased complexity in contextual interactions, extended dialogue sessions encompassing a diverse array of topics, and more frequent contextual shifts. To handle these intricacies arising from evolving LLM-based chat systems, we propose joint dialogue segmentation and state tracking per segment in open-domain dialogue systems. Assuming a zero-shot setting appropriate to a true open-domain dialogue system, we propose S3-DST, a structured prompting technique that harnesses Pre-Analytical Recollection, a novel grounding mechanism we designed for improving long context tracking. To demonstrate the efficacy of our proposed approach in joint segmentation and state tracking, we evaluate S3-DST on a proprietary anonymized open-domain dialogue dataset, as well as publicly available DST and segmentation datasets. Across all datasets and settings, S3-DST consistently outperforms the state-of-the-art, demonstrating its potency and robustness the next generation of LLM-based chat systems.

S3-DST：在LLM時代的結構化開放領域對話分割與狀態追踪

S3-DST: Structured Open-Domain Dialogue Segmentation and State Tracking in the Era of LLMs

摘要

Summary

Support

Support