arXiv 2503.192572025-03-25cs.CLcs.DL

SCI-IDEA：基于令牌和句子嵌入的上下文感知科学构思

SCI-IDEA: Context-Aware Scientific Ideation Using Token and Sentence Embeddings

TIB—Leibniz Information Centre for Science and Technology（莱布尼茨科学与技术信息中心）；L3S Research Center, Leibniz University Hannover（汉诺威莱布尼茨大学L3S研究中心）

Farhana Keya, Gollam Rabby, Prasenjit Mitra, Sahar Vahdati, Sören Auer, Yaser Jaradeh

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

SCI-IDEA框架利用LLM提示策略和“啊哈时刻”检测，从研究出版物中提取关键要素，迭代优化并评估科学想法，实验证明其在新颖性、兴奋度、可行性和有效性上均取得高分，兼顾伦理考量。

摘要：

每一项科学发现都始于一个由先前工作、跨学科概念和新出现的挑战所激发的想法。近年来，在科学语料库上训练的大型语言模型（LLM）的进步推动了人们对人工智能辅助想法生成的兴趣。然而，生成上下文感知、高质量且创新的想法仍然具有挑战性。我们引入了SCI-IDEA，这是一个利用LLM提示策略和“啊哈时刻”检测进行迭代想法优化的框架。SCI-IDEA从研究出版物中提取关键要素，评估生成想法的新颖性、兴奋度、可行性和有效性。综合实验验证了SCI-IDEA的有效性，在新颖性、兴奋度、可行性和有效性方面分别获得了6.84、6.86、6.89和6.84的平均得分（1-10分制）。评估采用了GPT-4o、GPT-4.5、DeepSeek-32B（每种均在2次提示下）和DeepSeek-70B（3次提示下），并使用令牌级嵌入进行“啊哈时刻”检测。同样，使用GPT-4o在5次提示下、GPT-4.5在3次提示下、DeepSeek-32B在零样本思维链提示下以及DeepSeek-70B在5次提示下，采用句子级嵌入，它分别获得了6.87、6.86、6.83和6.87的得分。我们还讨论了伦理考量，如知识信用、潜在滥用以及平衡人类创造力与AI驱动的构思。我们的结果凸显了SCI-IDEA在促进上下文感知科学想法的结构化灵活探索方面的潜力，在支持创新的同时保持伦理标准。

英文摘要：

Every scientific discovery starts with an idea inspired by prior work, interdisciplinary concepts, and emerging challenges. Recent advancements in large language models (LLMs) trained on scientific corpora have driven interest in AI-supported idea generation. However, generating context-aware, high-quality, and innovative ideas remains challenging. We introduce SCI-IDEA, a framework that uses LLM prompting strategies and Aha Moment detection for iterative idea refinement. SCI-IDEA extracts essential facets from research publications, assessing generated ideas on novelty, excitement, feasibility, and effectiveness. Comprehensive experiments validate SCI-IDEA's effectiveness, achieving average scores of 6.84, 6.86, 6.89, and 6.84 (on a 1-10 scale) across novelty, excitement, feasibility, and effectiveness, respectively. Evaluations employed GPT-4o, GPT-4.5, DeepSeek-32B (each under 2-shot prompting), and DeepSeek-70B (3-shot prompting), with token-level embeddings used for Aha Moment detection. Similarly, it achieves scores of 6.87, 6.86, 6.83, and 6.87 using GPT-4o under 5-shot prompting, GPT-4.5 under 3-shot prompting, DeepSeek-32B under zero-shot chain-of-thought prompting, and DeepSeek-70B under 5-shot prompting with sentence-level embeddings. We also address ethical considerations such as intellectual credit, potential misuse, and balancing human creativity with AI-driven ideation. Our results highlight SCI-IDEA's potential to facilitate the structured and flexible exploration of context-aware scientific ideas, supporting innovation while maintaining ethical standards.

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。