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

Conversational systems based on Large Language Models (LLMs), such asChatGPT, show exceptional proficiency in context understanding and responsegeneration. However, despite their impressive capabilities, they still possesslimitations, such as providing randomly-guessed answers to ambiguous queries orfailing to refuse users' requests, both of which are considered aspects of aconversational agent's proactivity. This raises the question of whetherLLM-based conversational systems are equipped to handle proactive dialogueproblems. In this work, we conduct a comprehensive analysis of LLM-basedconversational systems, specifically focusing on three aspects of proactivedialogue systems: clarification, target-guided, and non-collaborativedialogues. To trigger the proactivity of LLMs, we propose the ProactiveChain-of-Thought prompting scheme, which augments LLMs with the goal planningcapability over descriptive reasoning chains. Empirical findings are discussedto promote future studies on LLM-based proactive dialogue systems.

Prompting and Evaluating Large Language Models for Proactive Dialogues: Clarification, Target-guided, and Non-collaboration