SOURCE-LINKED INTELLIGENCE

Inference-Time Nash Alignment

arXiv · AI, language, vision and robotics · article · Sep 8, 2026 · UTC

Preference-based fine-tuning methods such as RLHF and DPO require substantial compute and large preference datasets. They also need direct access to the model parameters which are not provided by many state-of-the art models. Inference-time alignment offers a cost-effective alternative without updating model parameters. However, existing inference-time methods rely on a scalar reward model derived under a Bradley-Terry assumption, which cannot represent general preferences. Following recent work on fine-tuning with generalized preferences, in this work, we initiate the study of inference-time

Read original source ↗ Open in workspace

recordType

paper

region

Global