BLOOM-WILT: Logit Tilting for Behaviour Elicitation in Automated LLM Auditing
Users of a deployed language model routinely encounter behaviours that testing almost never surfaces, since deployment puts the model through orders of magnitude more interactions than any evaluation can simulate. Automated auditors make testing cheap to scale and flexible enough to cover almost any specified behaviour, yet their lack of optimisation pressure makes them sample-inefficient. To…
We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.
