Graph of Thoughts: Solving Elaborate Problems with Large Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Besta, Maciej, Blach, Nils, Kubicek, Ales, Gerstenberger, Robert, Podstawski, Michal, Gianinazzi, Lukas, Gajda, Joanna, Lehmann, Tomasz, Niewiadomski, Hubert, Nyczyk, Piotr, Hoefler, Torsten
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909158445416448
author Besta, Maciej
Blach, Nils
Kubicek, Ales
Gerstenberger, Robert
Podstawski, Michal
Gianinazzi, Lukas
Gajda, Joanna
Lehmann, Tomasz
Niewiadomski, Hubert
Nyczyk, Piotr
Hoefler, Torsten
author_facet Besta, Maciej
Blach, Nils
Kubicek, Ales
Gerstenberger, Robert
Podstawski, Michal
Gianinazzi, Lukas
Gajda, Joanna
Lehmann, Tomasz
Niewiadomski, Hubert
Nyczyk, Piotr
Hoefler, Torsten
contents We introduce Graph of Thoughts (GoT): a framework that advances prompting capabilities in large language models (LLMs) beyond those offered by paradigms such as Chain-of-Thought or Tree of Thoughts (ToT). The key idea and primary advantage of GoT is the ability to model the information generated by an LLM as an arbitrary graph, where units of information ("LLM thoughts") are vertices, and edges correspond to dependencies between these vertices. This approach enables combining arbitrary LLM thoughts into synergistic outcomes, distilling the essence of whole networks of thoughts, or enhancing thoughts using feedback loops. We illustrate that GoT offers advantages over state of the art on different tasks, for example increasing the quality of sorting by 62% over ToT, while simultaneously reducing costs by >31%. We ensure that GoT is extensible with new thought transformations and thus can be used to spearhead new prompting schemes. This work brings the LLM reasoning closer to human thinking or brain mechanisms such as recurrence, both of which form complex networks.
format Preprint
id arxiv_https___arxiv_org_abs_2308_09687
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Graph of Thoughts: Solving Elaborate Problems with Large Language Models
Besta, Maciej
Blach, Nils
Kubicek, Ales
Gerstenberger, Robert
Podstawski, Michal
Gianinazzi, Lukas
Gajda, Joanna
Lehmann, Tomasz
Niewiadomski, Hubert
Nyczyk, Piotr
Hoefler, Torsten
Computation and Language
Artificial Intelligence
Machine Learning
We introduce Graph of Thoughts (GoT): a framework that advances prompting capabilities in large language models (LLMs) beyond those offered by paradigms such as Chain-of-Thought or Tree of Thoughts (ToT). The key idea and primary advantage of GoT is the ability to model the information generated by an LLM as an arbitrary graph, where units of information ("LLM thoughts") are vertices, and edges correspond to dependencies between these vertices. This approach enables combining arbitrary LLM thoughts into synergistic outcomes, distilling the essence of whole networks of thoughts, or enhancing thoughts using feedback loops. We illustrate that GoT offers advantages over state of the art on different tasks, for example increasing the quality of sorting by 62% over ToT, while simultaneously reducing costs by >31%. We ensure that GoT is extensible with new thought transformations and thus can be used to spearhead new prompting schemes. This work brings the LLM reasoning closer to human thinking or brain mechanisms such as recurrence, both of which form complex networks.
title Graph of Thoughts: Solving Elaborate Problems with Large Language Models
topic Computation and Language
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2308.09687