作者位次 #4/4ICML 2026Poster· Social Aspects / Fairness
Adaptive Generation of Bias-Eliciting Questions for LLMs
Robin Staab · Jasper Dekoninck · Maximilian Baader · Martin Vechev
社会与人本OpenReview
首次获取该候选人的完整档案及 StartLux 评估共 20 积分；每位用户单独解锁，之后查看免费。主动刷新 20 积分。
实时查找电子邮箱，费用不超过20积分；未找到邮箱不扣费。
Robin Staab · Jasper Dekoninck · Maximilian Baader · Martin Vechev
Alex Thillen · Niels Mündler · Veselin Raychev · Martin Vechev
Ivo Petrov · Jasper Dekoninck · Martin Vechev
Tobias von Arx · Niels Mündler · Mark Vero · Maximilian Baader · Martin Vechev
Hanna Yukhymenko · Anton Alexandrov · Martin Vechev
The reliability of multilingual Large Language Model (LLM) evaluation is currently compromised by the inconsistent quality of translated benchmarks. Existing resources often suffer from semantic drift and context loss, which can lead to misleading performance metrics. In this work, we present a f...