Swiss-Knife: A Framework for Reconfigurable Externalised Multi-Objective Alignment at Decode Time
arXiv:2609.22226v1 Announce Type: cross Abstract: 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 Sw…
Read the full story at arXiv stat.ML ↗
Timeline · 1 report
- 2026-09-22 04:00 · arXiv stat.ML
Swiss-Knife: A Framework for Reconfigurable Externalised Multi-Objective Alignment at Decode Time