作者位次 #4/8ACL 2026Findings· Findings of ACL
CL a S -Bench: A Cross-Lingual Alignment and Steering Benchmark
Daniil Gurgurov · Yusser Al Ghussin · Tanja Baeumel · Cheng-Ting Chou · Patrick Schramowski · Marius Mosbach · Josef van Genabith · Simon Ostermann
摘要
Understanding and controlling the behavior of large language models (LLMs) is an increasingly important topic in multilingual NLP. Beyond prompting or fine-tuning, \textit{language steering} , i.e., manipulating internal representations during inference, has emerged as a more efficient and interp...