SOURCE-LINKED INTELLIGENCE

Swiss-Knife: A Framework for Reconfigurable Externalised Multi-Objective Alignment at Decode Time

arXiv · AI, language, vision and robotics · article · Sep 3, 2026 · UTC

Decode-time alignment methods steer a frozen language model by scoring candidate continuations with an external reward and selecting the maximiser. We argue that this shared design is a single degenerate point in a much larger space. We introduce Swiss-Knife, a framework for externalised multi-objective alignment in which the alignment specification is a first-class runtime object: hot-swappable scoring blades, a batch normaliser, a pairwise aggregation operator, and a selection rule. Six axioms characterise the admissible aggregation operators, and we prove a representation theorem: every ope

Read original source ↗ Open in workspace

recordType

paper

region

Global