BLOOM-WILT: Logit Tilting for Behaviour Elicitation in Automated LLM Auditing
[Sztuczna inteligencja] Autorzy: Adrians Skapars, Edoardo Manino
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 address this shortcoming, we introduce BLOOM-WILT, a full auditing pipeline that elicits natural multi-turn instances of rare behaviours, without training cost or access beyond the target's next-token distribution. On the input side, WILT's auditor model revises its conversational strategy across rounds, learning from previous scored interactions. On the output side, WILT adaptively reweights the target's decoding using the model's own distribution conditioned on an elicitation prompt, so that beha…
- Kategoria arxiv
- cs.AI
- Kategoria
- Sztuczna inteligencja