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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

The latest advancements in AI and deep learning have led to a breakthrough inlarge language model (LLM)-based agents such as GPT-4. However, many commercialconversational agent development tools are pipeline-based and have limitationsin holding a human-like conversation. This paper investigates the capabilitiesof LLMs to enhance pipeline-based conversational agents during two phases: 1)in the design and development phase and 2) during operations. In 1) LLMs canaid in generating training data, extracting entities and synonyms,localization, and persona design. In 2) LLMs can assist in contextualization,intent classification to prevent conversational breakdown and handleout-of-scope questions, auto-correcting utterances, rephrasing responses,formulating disambiguation questions, summarization, and enabling closedquestion-answering capabilities. We conducted informal experiments with GPT-4in the private banking domain to demonstrate the scenarios above with apractical example. Companies may be hesitant to replace their pipeline-basedagents with LLMs entirely due to privacy concerns and the need for deepintegration within their existing ecosystems. A hybrid approach in which LLMs'are integrated into the pipeline-based agents allows them to save time andcosts of building and running agents by capitalizing on the capabilities ofLLMs while retaining the integration and privacy safeguards of their existingsystems.

Enhancing Pipeline-Based Conversational Agents with Large Language Models