English

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

Computation and Language 2024-06-25 v2 Artificial Intelligence Machine Learning

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 the question. Unlike conventional knowledge triplets, our approach allows variables as head or tail entities, effectively representing a question as knowledge triplets. Second, for each triplet, the LLM generates a corresponding sub-question and answer along with using knowledge retrieval. If the prediction confidence exceeds a threshold, the sub-question and prediction are incorporated into the prompt for subsequent processing. This approach encourages that sub-questions are grounded in the extracted knowledge triplets, reducing redundancy and irrelevance. Our experiments demonstrate that our approach outperforms previous CoT prompting methods and their variants on multi-hop question answering benchmark datasets.

Keywords

Cite

@article{arxiv.2311.09762,
  title  = {Graph Elicitation for Guiding Multi-Step Reasoning in Large Language Models},
  author = {Jinyoung Park and Ameen Patel and Omar Zia Khan and Hyunwoo J. Kim and Joo-Kyung Kim},
  journal= {arXiv preprint arXiv:2311.09762},
  year   = {2024}
}

Comments

Preprint

R2 v1 2026-06-28T13:23:13.197Z