LogicTree: Improving Complex Reasoning of LLMs via Instantiated Multi-step Synthetic Logical Data

NeurIPSSpotlight2025

Authors
Zehao Wang, Lin Yang, Jie Wang, Kehan Wang, Hanzhu Chen, Bin Wang, Jianye HAO, Defu Lian, Bin Li, Enhong Chen
Venue
NeurIPS 2025
Track
Spotlight

TL;DR

Despite their remarkable performance on various tasks, Large Language Models (LLMs) still struggle with logical reasoning, particularly in complex and multi-step reasoning processes…

Opening excerpt from the authors’ abstract. source

Read the paper

Topics

large language model language model reasoning llm

Related NeurIPS papers

← All NeurIPS 2025 Spotlight papers · Browse the whole archive