一作ICLR 2026Poster· Theory / Interpretability and Visualization
Fresh in memory: Training-order recency is linearly encoded in language model activations
Dmitrii Krasheninnikov · Richard E Turner · David Krueger
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。
Dmitrii Krasheninnikov · Richard E Turner · David Krueger
Adrians Skapars · Nathalie Maria Kirch · Samuel Dower · Ekdeep Singh Lubana · Dmitrii Krasheninnikov
Probing has emerged as a promising method for monitoring large language models (LLMs), enabling cheap inference-time detection of concerning behaviours. However, natural examples of many behaviours are rare, forcing researchers to rely on synthetic or off-policy LLM responses for training probes....