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

Large language models (LLMs) are powerful dialogue agents, but specializingthem towards fulfilling a specific function can be challenging. Instructingtuning, i.e. tuning models on instruction and sample responses generated byhumans (Ouyang et al., 2022), has proven as an effective method to do so, yetrequires a number of data samples that a) might not be available or b) costlyto generate. Furthermore, this cost increases when the goal is to make the LLMfollow a specific workflow within a dialogue instead of single instructions.Inspired by the self-play technique in reinforcement learning and the use ofLLMs to simulate human agents, we propose a more effective method for datacollection through LLMs engaging in a conversation in various roles. Thisapproach generates a training data via "self-talk" of LLMs that can be refinedand utilized for supervised fine-tuning. We introduce an automated way tomeasure the (partial) success of a dialogue. This metric is used to filter thegenerated conversational data that is fed back in LLM for training. Based onour automated and human evaluations of conversation quality, we demonstratethat such self-talk data improves results. In addition, we examine the variouscharacteristics that showcase the quality of generated dialogues and how theycan be connected to their potential utility as training data.

Bootstrapping LLM-based Task-Oriented Dialogue Agents via Self-Talk