arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2502.05615cs.CVcs.AI
收藏

XiHeFusion:利用大型语言模型实现核聚变科学传播

XiHeFusion: Harnessing Large Language Models for Science Communication in Nuclear Fusion

Anhui University(安徽大学);Institute of Plasma Physics, Chinese Academy of Sciences(中国科学院等离子体物理研究所);Tsinghua University(清华大学)

Xiao Wang, Qingquan Yang, Fuling Wang, Qiang Chen, Wentao Wu, Yu Jin, Jingtao Jiang, Liye Jin, Bo Jiang, Dengdi Sun, Wanli Lv, Meiwen Chen, Zehua Chen, Guosheng Xu, Jin Tang

AI总结:

本文提出核聚变领域首个大模型XiHeFusion,基于Qwen2.5-14B监督微调,融合多源核聚变知识并通过思维链增强推理,经180+问题测试表现优异,模型已开源。

摘要:

核聚变是人类获取无限能源最具前景的方式之一。当前,随着人工智能的快速发展,核聚变任务也进入了发展关键期。如何让更多人了解核聚变并参与其研究,是加速核聚变落地的有效手段之一。本文提出核聚变领域首个大型模型XiHeFusion,它基于开源大模型Qwen2.5-14B通过监督微调得到。我们收集了多源核聚变任务知识以支持模型训练,包括通用爬虫数据、电子书、arXiv论文、学位论文等。在模型掌握核聚变领域知识后,我们进一步利用思维链(Chain of Thought)增强其逻辑推理能力,使XiHeFusion能提供更准确、更具逻辑性的答案。此外,我们提出包含180多个问题的测试问卷,以评估该科普大模型的对话能力。大量实验结果表明,我们的核聚变对话模型XiHeFusion在科普知识问答方面表现优异。预训练的XiHeFusion模型已在https://github.com/Event-AHU/XiHeFusion发布。

英文摘要:

Nuclear fusion is one of the most promising ways for humans to obtain infinite energy. Currently, with the rapid development of artificial intelligence, the mission of nuclear fusion has also entered a critical period of its development. How to let more people to understand nuclear fusion and join in its research is one of the effective means to accelerate the implementation of fusion. This paper proposes the first large model in the field of nuclear fusion, XiHeFusion, which is obtained through supervised fine-tuning based on the open-source large model Qwen2.5-14B. We have collected multi-source knowledge about nuclear fusion tasks to support the training of this model, including the common crawl, eBooks, arXiv, dissertation, etc. After the model has mastered the knowledge of the nuclear fusion field, we further used the chain of thought to enhance its logical reasoning ability, making XiHeFusion able to provide more accurate and logical answers. In addition, we propose a test questionnaire containing 180+ questions to assess the conversational ability of this science popularization large model. Extensive experimental results show that our nuclear fusion dialogue model, XiHeFusion, can perform well in answering science popularization knowledge. The pre-trained XiHeFusion model is released on https://github.com/Event-AHU/XiHeFusion.

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。

↑