作者位次 #2/2ICLR 2026Poster· Theory / Interpretability and Visualization
First is Not Really Better Than Last: Evaluating Layer Choice and Aggregation Strategies in Language Model Data Influence Estimation
Dmytro Vitel · Anshuman Chhabra
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。
Dmytro Vitel · Anshuman Chhabra
Israel Abebe Azime · Tadesse Destaw Belay · Dietrich Klakow · Philipp Slusallek · Anshuman Chhabra
Large language models (LLMs) have demonstrated significant capabilities in solving mathematical problems expressed in natural language. However, multilingual and culturally-grounded mathematical reasoning in low-resource languages lags behind English due to the scarcity of socio-cultural task dat...