The method of training language models based on domain datasets has obtained
significant achievements in the task of generating scientific paper abstracts.
However, such models face problems of generalization and expensive training
costs. The use of large language models (LLMs) to solve the task of generating
paper abstracts saves the cost of model training. However, due to the
hallucination problem of LLM, it is often necessary to improve the reliability
of the results through multi-round query prompt approach such as Graph of
Thoughts (GoT), which also brings additional reasoning costs. In this paper, we
propose a Dynamic Graph of Thought (DGoT). It not only inherits the advantages
of the existing GoT prompt approach, but also dynamically adjust the graph
structure according to data characteristics while reducing model reasoning
cost. Experimental results show that our method's cost-effectiveness in
abstract generation tasks is only 43.7% to 56.4% of other multi-round query
prompt approaches. Our code is available at this https URL

我们提出了一种动态思维图 (DGoT) 的方法，它在减少模型推理成本的同时，不仅继承了现有 GoT 提示方法的优点，还根据数据特征动态调整图结构。实验结果表明，我们的方法在摘要生成任务中的性价比仅为其他多轮查询提示方法的 43.7% 至 56.4%。

DGoT：用于科学摘要生成的动态思维图

DGoT: Dynamic Graph of Thoughts for Scientific Abstract Generation

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-ofThought 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.

Graph of Thoughts (GoT) is a framework that advances prompting capabilities in large language models (LLMs) by modeling LLM thoughts as an arbitrary graph, enabling combination, distillation, and enhancement of thoughts, offering advantages over existing paradigms and allowing for extensibility with new thought transformations.

思维图：用大型语言模型解决复杂问题

Graph of Thoughts: Solving Elaborate Problems with Large Language Models

Recent advancements in large-scale models, such as GPT-4, have showcased
remarkable capabilities in addressing standard queries. However, when facing
complex problems that require multi-step logical reasoning, their accuracy
dramatically decreases. Current research has explored the realm of
\textit{prompting engineering} to bolster the inferential capacities of these
models. Our paper unveils a pioneering prompting technique, dubbed
\textit{Graph of Thoughts (GoT)}. Through testing on a trio of escalating
challenges: the 24-point game, resolution of high-degree polynomial equations,
and derivation of formulas for recursive sequences, our method outperformed
GPT-4, achieving accuracy improvements of $89.7\%$, $86\%$, and $56\%$ for each
respective task. Moreover, when juxtaposed with the state-of-the-art (SOTA)
prompting method, \textit{Tree of Thought (ToT)}, our approach registered an
average accuracy boost of $23\%$, $24\%$, and $15\%$.

利用 Graph of Thoughts (GoT) 和 prompting engineering 技术，我们的方法在解决多步骤逻辑推理问题方面超越了 GPT-4，分别获得了 89.7%、86% 和 56% 的准确率提升，并且相较于最先进的 Tree of Thought (ToT) 方法，我们的方法在准确率上平均提升了 23%、24% 和 15%。