How much of a measured AI preference is the model, and how much is the instrument?

arXiv cs.AIAugust 26, 2026en

arXiv cs.AI

AI Global Wire

arXiv:2608.23641v1 Announce Type: new Abstract: Model welfare research infers what a model prefers from the answers returned to prompts written to elicit preferences. Keeling et al. (2024), Mazeika et al. (2025), Mikaelson et al. (2025), Tagliabue and Dung (2025) and Trhlik et al. (2026) have built four instruments for that purpose, and their findings disagree. The disagreement cannot be attributed to a single cause, because no two of these studies have held the (1) set of outcomes, (2) set of models and (3) instrument fixed simultaneously. This study holds the outcomes and the models fixed and varies the instrument alone. A total of 15 outcomes bearing on model welfare, among them (a) shutd

This is a short summary published by AI Global Wire. The full article is owned and hosted by arXiv cs.AI — open it there to read it in full.

• Forskning