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 2608.04100hep-phhep-exhep-th

用于稀疏SMEFT分析的语言引导假设生成

Language-Guided Hypotheses Generation for Sparse SMEFT Analyses

Ahmed Hammad, Veronica Sanz

首次发表
浏览论文内容

中文总结 AI 辅助

研究解决稀疏SMEFT分析中算符假设选择难题,提出开源llm4smeft框架,结合微调语言模型与检索增强生成,可本地运行且能生成候选算符及费希尔信息。

中文摘要 AI 辅助

标准模型有效场论(SMEFT)的全局拟合面临大量算符带来的挑战,而任何给定数据库仅能约束其中一小部分。因此,选择相关算符假设需要对算符相关性和可观测量灵敏度的理论认知。我们提出llm4smeft,这是一个开源框架,通过将在SMEFT文献上微调的语言模型,与基于SMEFiT包全局拟合的定量摘要的检索增强生成相结合,来解决该问题。给定一组可观测量,该框架会提出候选相关算符及其对应的费希尔信息,同时检索机制确保模型输出在可用时基于现有拟合结果。该框架可交互模式运行,在此模式下,被接受的假设会被存储到不断增长的知识库中。我们公开发布llm4smeft包及微调后的语言模型,整个框架可在本地运行,无需互联网接入或付费云服务。

英文摘要

Global fits of the Standard Model Effective Field Theory are challenged by the large number of operators, while any given database constrains only a small subset. Selecting relevant operator hypotheses therefore requires theoretical insight into operator correlations and the sensitivity of observables. We present llm4smeft, an open source framework that addresses this problem by combining a language model, fine-tuned on the SMEFT literature, with retrieval augmented generation based on quantitative summaries of SMEFiT package global fits. Given a set of observables, the framework proposes candidate relevant operators together with their corresponding Fisher information, while retrieval ensures that model outputs are grounded in existing fit results whenever available. The framework runs in an interactive mode in which accepted hypotheses are stored in a growing knowledge base. We publicly release the llm4smeft package together with the fine-tuned language model, in which the entire framework runs locally, requiring neither internet access nor paid cloud services.

发表机构

  • Center of AI and Natural Sciences, KIAS(韩国高等科学研究院人工智能与自然科学中心)
  • IFIC, Universitat de València-CSIC(巴伦西亚大学-西班牙国家研究委员会联合研究所)

机构由 AI 辅助整理,请以论文原文为准。

补充信息

↑