BLOOM-WILT: Logit Tilting for Behaviour Elicitation in Automated LLM Auditing
arXiv:2608.31105v2 Announce Type: replace Abstract: Users of a deployed language model routinely encounter behaviours that have never been observed during testing, since deployment puts the model through orders of magnitude more interactions than any evaluation can simulate. Automated auditors can mitigate this issue as they are flexible enough to discover almost any specified behaviour, yet their random sampling approach makes them inefficient. To address this shortcoming, we introduce BLOOM-W…