Swiss-Knife: A Framework for Reconfigurable Externalised Multi-Objective Alignment at Decode Time
Read the original on arXiv Machine Learning →Swiss-Knife is a framework that extends decode‑time alignment for frozen language models by treating the alignment specification as a runtime object. It introduces hot‑swappable scoring blades, a batch normaliser, a pairwise aggregation operator, and a selection rule, and characterises admissible aggregation operators with a representation theorem. In experiments, Swiss‑Knife paired with DPO‑LoRA blades and an uncertainty‑aware pairwise tournament outperforms six existing decode‑time methods, achieving a higher harmonic F1 score, lower refusal rate, and faster objective reconfiguration.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.