DFKI-MLT 在 SemEval-2026 任务 7 中：将多语言模型引导至文化知识
DFKI-MLT at SemEval-2026 TASK 7: Steering Multilingual Models Towards Cultural Knowledge
AI总结：
本研究提出使用从并行 FLORES 数据中提取的语言向量进行激活引导，在推理时调整多语言模型以提升文化知识，并在 SemEval-2026 任务 7 的 MCQ 赛道上取得 86.96% 准确率，排名第 7。
摘要：
大型语言模型（LLMs）越来越多地用于不同的语言和文化背景，但其文化知识在不同地区和语言之间仍然不均匀。我们提出了用于 SemEval-2026 任务 7（文化意识）的 DFKI-MLT 系统，该系统使用从并行 FLORES 数据中提取的语言向量，对多语言 LLMs 应用激活引导。我们的方法通过在选定的 Transformer 层的残差流中添加特定语言的引导向量来进行推理时调整，无需任何参数更新。我们参加了简答题（SAQ）和多项选择题（MCQ）两个赛道；然而，只有我们的 MCQ 提交获得了官方评分。在官方 MCQ 赛道中，我们达到了 86.96% 的准确率，在 17 个队伍中排名第 7。为了更好地理解系统行为，我们对共享任务的 MCQ 和 SAQ 设置进行了事后分析。这些分析表明，激活引导对文化推理产生了适度且异质的改进：增益对层高度敏感，在不同语言-区域对之间差异很大，某些配置甚至降低了性能，并且与提示表述相互作用，比较了通用提示和文化条件提示。我们的发现表明，提示设计和激活引导应联合优化，以实现具有文化意识的多语言推理。
英文摘要：
Large language models (LLMs) are increasingly used across diverse linguistic and cultural contexts, yet their cultural knowledge remains uneven across regions and languages. We present the DFKI-MLT system for SemEval-2026 Task 7 on cultural awareness, where we apply activation steering to multilingual LLMs using language vectors extracted from parallel FLORES data. Our method performs inference-time adaptation by adding language-specific steering vectors to the residual stream at a selected transformer layer, without any parameter updates. We participated in both the short-answer (SAQ) and multiple-choice (MCQ) tracks; however, only our MCQ submission received an official score. In the official MCQ track, we achieved 86.96% accuracy, ranking 7th out of 17 teams. To better understand system behavior, we conduct post-hoc analyses on the shared-task MCQ and SAQ settings. These analyses show that activation steering yields modest and heterogeneous improvements on cultural reasoning: gains are strongly layer-sensitive, vary substantially across language-region pairs, with some configurations even degrading performance, and interact with prompt formulation, comparing generic and culturally conditioned prompts. Our findings suggest that prompt design and activation steering should be jointly optimized for culturally aware multilingual inference.
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。
