arXiv 2509.219782025-09-26cs.CL

MotivGraph-SoIQ：融合动机知识图谱与苏格拉底式对话以增强大语言模型创意生成

MotivGraph-SoIQ: Integrating Motivational Knowledge Graphs and Socratic Dialogue for Enhanced LLM Ideation

The Key Laboratory of Cognition and Decision Intelligence for Complex Systems（认知与决策智能复杂系统重点实验室）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；Hunan Provincial Key Laboratory of Philosophy and Social Sciences of Artificial Intelligence and Precision International, Hunan Normal University（湖南省人工智能与精准哲学社会科学省级重点实验室，湖南师范大学）；Beijing University of Posts and Telecommunications（北京邮电大学）

Xinping Lei, Tong Zhou, Yubo Chen, Kang Liu, Jun Zhao

备注：: EMNLP2025 Findings

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出 MotivGraph-SoIQ 框架，通过融合动机知识图谱与苏格拉底式对话，为大语言模型学术创意生成提供依据并缓解确认偏误，在 ICLR25 数据集上优于现有方法。

摘要：

大语言模型（LLMs）在加速学术创意生成方面具有巨大潜力，但在为想法提供依据和缓解确认偏误以进行进一步优化方面面临关键挑战。我们提出将动机知识图谱与苏格拉底式对话相结合，以解决增强型大语言模型创意生成（MotivGraph-SoIQ）中的这些局限。该新型框架通过将动机知识图谱（MotivGraph）与问题驱动的苏格拉底式创意生成器（Q-Driven Socratic Ideator）集成，为大语言模型创意生成提供必要依据和实用的想法改进步骤。MotivGraph 结构化存储三种关键节点类型（问题、挑战和解决方案），为大语言模型创意生成过程提供动机依据。创意生成器是一个利用苏格拉底式提问的双智能体系统，有助于进行严格的优化过程，从而缓解确认偏误，并在新颖性、实验严谨性和动机合理性维度上提升想法质量。在 ICLR25 论文主题数据集上，MotivGraph-SoIQ 在基于大语言模型的评分、ELO 排名和人工评估指标方面均展现出优于现有最先进方法的明显优势。

英文摘要：

Large Language Models (LLMs) hold substantial potential for accelerating academic ideation but face critical challenges in grounding ideas and mitigating confirmation bias for further refinement. We propose integrating motivational knowledge graphs and socratic dialogue to address these limitations in enhanced LLM ideation (MotivGraph-SoIQ). This novel framework provides essential grounding and practical idea improvement steps for LLM ideation by integrating a Motivational Knowledge Graph (MotivGraph) with a Q-Driven Socratic Ideator. The MotivGraph structurally stores three key node types(problem, challenge and solution) to offer motivation grounding for the LLM ideation process. The Ideator is a dual-agent system utilizing Socratic questioning, which facilitates a rigorous refinement process that mitigates confirmation bias and improves idea quality across novelty, experimental rigor, and motivational rationality dimensions. On the ICLR25 paper topics dataset, MotivGraph-SoIQ exhibits clear advantages over existing state-of-the-art approaches across LLM-based scoring, ELO ranking, and human evaluation metrics.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。