2026/07/10 by Kwan Soo Shin, In Seok Kang, Yunkyung Min +1
Computer Science · #cs.AI #cs.CL #cs.HC #cs.LG
Substantially revised and narrowed version with a new title and estimand-centred analysis. Comparisons are now reported at three output resolutions, and the reproducibility package has been rebuilt. The author list was changed with the approval of all authors listed on v1-v2; previous versions remain publicly available. 17 pages, 3 figures, 3 tables
arxiv created 2026/07/30 · arxiv updated 2026/07/31
Behavioural auditing asks whether a language model behaves as it claims, but detection scores are reported without separating two targets: whether a reply was produced under a behaviour-inducing condition (exposure) and whether the behaviour surfaced in it (manifestation). Scoring a compact 146-million-parameter auditor's frozen-representation read-out and a frontier judge against each label on the identical 720 replies, the gap between the instruments moves by roughly 0.2 AUROC when the target changes. Under the judge's deployed interface, a single verdict, the ranking reverses: the auditor leads on exposure, 0.804 against 0.718, and trails on manifestation, 0.690 against 0.811. Matching the output resolution from either direction, by asking the judge a target-specific question answered with a continuous confidence score or by thresholding the auditor's read-out, removes the reversal but not the interaction, which excludes zero at all three resolutions (0.207, 0.237 and 0.169). The target governs how far apart the instruments are; the interface governs whether that distance changes their order. The auditor's hyperbolic geometry confers no advantage here. A single behavioural-detection AUROC is under-specified: such claims are comparable only when they state the estimand, the evaluator, and its output interface.