arXiv:2605.28543v3 Announce Type: replace Abstract: LLMs often default to equal treatment across cultural groups, even though context warrants differentiation: this is a lack of difference awareness. Using mechanistic interpretability and a factorial design on the N4 cultural appropriation benchmark from Wang et al. (2025), we identify 2-3 mid-layer attention heads per model that contribute causally to cultural binding across eight models (base and instruct versions of four architectures). Cultural binding is the process of associating a cultural item with its related identity. Knockout of the identity-to-item edges on these heads lowers the binding strength by 9-23%. The identified heads transfer from instruct to base models, suggesting that cultural binding is created during pre-training. An $\alpha$-scaling shows a graded dose-response. Moderate amplification steering at generation ($\alpha = 2-3$) increases cultural differentiation accuracy by 1-3 pp while leaving reasoning on culturally neutral questions mostly intact. A knowledge probing task shows that models know 3-6 times more than they act upon, indicating that the bottleneck lies in routing and not knowledge.

arXiv:2603.22973v1 Announce Type: new Abstract: Computational methods applied to legal scholarship hold the promise of analyzing law at scale. We start from a simple question: how often do courts implicitly apply statutory rules? This requires distinguishing legal reasoning from semantic similarity. We focus on implicit citation of the French Civil Code in first-instance court decisions and introduce a benchmark of 1,015 passage-article pairs annotated by three legal experts. We show that expert disagreement predicts model failures. Inter-annotator agreement is moderate ($\kappa$ = 0.33) with 43% of disagreements involving the boundary between factual description and legal reasoning. Our supervised ensemble achieves F1 = 0.70 (77% accuracy), but this figure conceals an asymmetry: 68% of false positives fall on the 33% of cases where the annotators disagreed. Despite these limits, reframing the task as top-k ranking and leveraging multi-model consensus yields 76% precision at k = 200 in an unsupervised setting. Moreover, the remaining false positives tend to surface legally ambiguous applications rather than obvious errors.