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

Finding an agreement among diverse opinions is a challenging topic inmultiagent systems. Recently, large language models (LLMs) have shown greatpotential in addressing this challenge due to their remarkable capabilities incomprehending human opinions and generating human-like text. However, theytypically rely on extensive human-annotated data. In this paper, we proposeSelf-Agreement, a novel framework for fine-tuning LLMs to autonomously findagreement using data generated by LLM itself. Specifically, our approachemploys the generative pre-trained transformer-3 (GPT-3) to generate multipleopinions for each question in a question dataset and create several agreementcandidates among these opinions. Then, a bidirectional encoder representationsfrom transformers (BERT)-based model evaluates the agreement score of eachagreement candidate and selects the one with the highest agreement score. Thisprocess yields a dataset of question-opinion-agreements, which we use tofine-tune a pre-trained LLM for discovering agreements among diverse opinions.Remarkably, a pre-trained LLM fine-tuned by our Self-Agreement frameworkachieves comparable performance to GPT-3 with only 1/25 of its parameters,showcasing its ability to identify agreement among various opinions without theneed for human-annotated data.

Self-Agreement: A Framework for Fine-tuning Language Models to Find Agreement among Diverse Opinions