Graph of Thoughts: Solving Elaborate Problems with Large Language Models
This work addresses the limitation of existing prompting paradigms for LLMs, offering a more flexible and efficient approach for solving elaborate problems, though it is incremental as it builds on prior methods like Chain-of-Thought and Tree of Thoughts.
The authors tackled the problem of enhancing prompting capabilities in large language models by introducing Graph of Thoughts (GoT), a framework that models LLM-generated information as a graph to combine thoughts synergistically, resulting in a 62% increase in sorting quality over Tree of Thoughts and a cost reduction of over 31%.
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.