DGoT: Dynamic Graph of Thoughts for Scientific Abstract Generation
This work addresses the problem of efficient and reliable abstract generation for researchers using LLMs, but it is incremental as it builds on existing GoT approaches.
The paper tackles the problem of generating scientific paper abstracts using large language models (LLMs) by addressing the high reasoning costs and hallucination issues of existing multi-round query prompt approaches like Graph of Thoughts (GoT), proposing Dynamic Graph of Thought (DGoT) that dynamically adjusts the graph structure to reduce costs, with experimental results showing cost-effectiveness at 43.7% to 56.4% of other methods.
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 https://github.com/JayceNing/DGoT.