MURANO: Design, Run, and Reproduce Mechanistic Interpretability Experiments as Composable Pipelines
MURANO:将机械可解释性实验设计、运行与复现作为可组合流水线
机构 * Technical University of Darmstadt(达姆施塔特工业大学) ; Cluster of Excellence “Reasonable Artificial Intelligence” (RAI)(“合理人工智能”卓越集群) ; National Research Center for Applied Cybersecurity ATHENE(国家应用网络安全研究中心ATHENE) ; Zuse School ELIZA(楚思学校ELIZA) ; Ubiquitous Knowledge Processing (UKP) Lab(普适知识处理实验室)
AI总结 本文提出开源框架Murano,将大语言模型机械可解释性研究的五类操作封装为可组合步骤,可复现相关研究并开展案例分析,解决了多库适配的问题。
Comments Accepted to the EMNLP 2026 System Demonstrations Track. 11 pages, 6 figures, 2 tables