Topologies of Reasoning: Demystifying Chains, Trees, and Graphs of Thoughts

arXiv:2401.14295v2 Announce Type: replace-cross
Abstract: The field of natural language processing (NLP) has witnessed significant progress in recent years, with a notable focus on improving large language models' (LLM) performance through innovative prompting techniques. Among these, prompt engineering coupled with structures has emerged as a promising paradigm, with designs such as Chain-of-Thought, Tree of Thoughts, or Graph of Thoughts, in which the overall LLM reasoning is guided by a structure such as a graph. As illustrated with numerous examples, this …

abstract arxiv cs.ai cs.cl cs.lg designs engineering focus graphs improving language language models language processing large language large language models llm natural natural language natural language processing nlp paradigm performance processing progress prompt prompting reasoning thoughts through trees type