Self-Consistency via Marginal Sharpening 事件

Self-Consistency via Marginal Sharpening arXiv:2605.28142v1 Announce Type: cross Abstract: Inference-time sampling can elicit strong reasoning abilities from language models without additional training. Existing power-sampling methods do so by sharpening the distribution over full generated outputs, favoring completions that are individually likely under the model. We argue that this is the wrong object to target for reasoning: a completion entangles a reasoning trace with a final answer, where