Combinatorial Reasoning: Selecting Reasons in Generative AI Pipelines via Combinatorial Optimization

Recent Large Language Models (LLMs) have demonstrated impressive capabilities at tasks that require human intelligence and are a significant step towards human-like artificial intelligence (AI). Yet the performance of LLMs at reasoning tasks have been subpar and the reasoning capability of LLMs is a...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2024-06
Hauptverfasser:	Esencan, Mert, Kumar, Tarun Advaith, Ata Akbari Asanjan, Lott, P Aaron, Mohseni, Masoud, Unlu, Can, Venturelli, Davide, Ho, Alan
Format:	Artikel
Sprache:	eng
Schlagworte:	Combinatorial analysis Generative artificial intelligence Large language models Optimization Pipelines Reasoning Solvers
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!