作者位次 #3/5ACL 2026Findings· Findings of ACL
The Impact of Off-Policy Training Data on Probe Generalisation
Adrians Skapars · Nathalie Maria Kirch · Samuel Dower · Ekdeep Singh Lubana · Dmitrii Krasheninnikov
摘要
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....