English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Recently, the development of large language models (LLMs) has beensignificantly enhanced the question answering and dialogue generation, andmakes them become increasingly popular in current practical scenarios. Whileunlike the general dialogue system which emphasizes the semantic performance,the task-oriented dialogue (ToD) systems aim to achieve the dialogue goalefficiently and successfully in multiple turns. Unfortunately, existingLLM-induced ToD systems lack the direct reward toward the final goal and do nottake account of the dialogue proactivity that can strengthen the dialogueefficiency. To fill these gaps, we introduce the ProToD (ProactivelyGoal-Driven LLM-Induced ToD) approach, which anticipates the future dialogueactions and incorporates the goal-oriented reward signal to enhance ToDsystems. Additionally, we present a novel evaluation method that assesses ToDsystems based on goal-driven dialogue simulations. This method allows us togauge user satisfaction, system efficiency and successful rate while overcomingthe limitations of current Information and Success metrics. Empiricalexperiments conducted on the MultiWoZ 2.1 dataset demonstrate that our modelcan achieve superior performance using only 10% of the data compared toprevious end-to-end fully supervised models. This improvement is accompanied byenhanced user satisfaction and efficiency.

Enhancing Large Language Model Induced Task-Oriented Dialogue Systems Through Look-Forward Motivated Goals