Shangzi Xue

Decompose, Analyze and Rethink: Solving Intricate Problems with Human-like Reasoning Cycle

In this paper, we introduce DeAR (_Decompose-Analyze-Rethink_), a framework that iteratively builds a reasoning tree to tackle intricate problems within a single large language model (LLM). Unlike approaches that extend or search for rationales, DeAR is featured by 1) adopting a tree-based question…