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) have shown impressive capabilities in variousapplications, but they still face various inconsistency issues. Existing worksprimarily focus on the inconsistency issues within a single LLM, while wecomplementarily explore the inter-consistency among multiple LLMs forcollaboration. To examine whether LLMs can collaborate effectively to achieve aconsensus for a shared goal, we focus on commonsense reasoning, and introduce aformal debate framework (FORD) to conduct a three-stage debate among LLMs withreal-world scenarios alignment: fair debate, mismatched debate, and roundtabledebate. Through extensive experiments on various datasets, LLMs can effectivelycollaborate to reach a consensus despite noticeable inter-inconsistencies, butimbalances in their abilities can lead to domination by superior LLMs.Leveraging a more advanced LLM like GPT-4 as an authoritative judge can boostcollaboration performance. Our work contributes to understanding theinter-consistency among LLMs and lays the foundation for developing futurecollaboration methods. Codes and data are available athttps://github.com/Waste-Wood/FORD

Examining Inter-Consistency of Large Language Models Collaboration: An In-depth Analysis via Debate