DFKI-MLT at SemEval-2026 TASK 7: Steering Multilingual Models Towards Cultural Knowledge
DFKI-MLT 在 SemEval-2026 任务 7 中:将多语言模型引导至文化知识
Yusser Al Ghussin, Daniil Gurgurov, Yasser Hamidullah, Josef van Genabith, Cristina España-Bonet, Simon Ostermann
机构
*
German Research Center for Artificial Intelligence (DFKI GmbH)(德国人工智能研究中心(DFKI GmbH))
;
Saarland Informatics Campus(萨尔布吕肯信息学校区)
;
Barcelona Supercomputing Center (BSC-CNS)(巴塞罗那超级计算中心(BSC-CNS))
DreamerNLplus: Interpretable Modeling of Mental Health Dynamics from Social Media Timelines using Hybrid Rule-Based and RAG Methods
DreamerNLplus: 使用混合规则和RAG方法从社交媒体时间线进行可解释的心理健康动态建模
Maryia Zhyrko, Daisy Monika Lal, Erik van Mulligen, Lifeng Han
机构
*
Leiden Institute of Advanced Computer Science (LIACS), Leiden University(莱顿高级计算机科学研究所(LIACS),莱顿大学)
;
School of Computing and Communications (SCC), Lancaster University(计算与通信学院(SCC),兰卡斯特大学)
;
Department of Medical Informatics, Erasmus University Medical Center Rotterdam(医学信息学系,埃因霍温医学中心鲁特万分校)
;
Biomedical Data Sciences, Leiden University Medical Center(生物医学数据科学,莱顿大学医学中心)
Multilingual Steering by Design: Multilingual Sparse Autoencoders and Principled Layer Selection
通过设计实现多语言引导:多语言稀疏自编码器与原则性层选择
Yusser Al Ghussin, Daniil Gurgurov, Tanja Baeumel, Josef van Genabith, Patrick Schramowski, Simon Ostermann
机构
*
Saarland University(萨尔兰大学)
;
German Research Center for Artificial Intelligence (DFKI)(德国人工智能研究中心)
;
TU Darmstadt(德累斯顿技术大学)
;
Centre for European Research in Trusted AI (CERTAIN)(欧洲可信AI研究中心)