Graph Elicitation for Guiding Multi-Step Reasoning in Large Language Models

arXiv:2311.09762v2 Announce Type: replace
Abstract: Chain-of-Thought (CoT) prompting along with sub-question generation and answering has enhanced multi-step reasoning capabilities of Large Language Models (LLMs). However, prompting the LLMs to directly generate sub-questions is suboptimal since they sometimes generate redundant or irrelevant questions. To deal with them, we propose a GE-Reasoning method, which directs LLMs to generate proper sub-questions and corresponding answers. Concretely, given an input question, we first prompt the LLM to generate knowledge triplets, forming a graph representation of …

abstract arxiv capabilities cs.ai cs.cl cs.lg deal generate graph however language language models large language large language models llms multi prompting question questions reasoning replace them thought type