arXiv:2611.08403v1 Announce Type: new
Abstract: Self-consistency (SC) is a widely used decoding strategy for improving chain-of-thought reasoning, but it requires sampling many complete reasoning trajectories with a preset budget. Its efficient variants reduce the cost mainly by stopping full-trajectory sampling early or distributing the number of samples across questions. In this paper, we propose StepBack, a step-level error-localized resampling method for efficient test-time reasoning. Given a small set of draft trajectories, StepBack localizes likely first error positions using lightweight signals and then resamples the detected error step and its suffix, followed by majority answer voting. Empirically, StepBack matches the accuracy of SC on average across seven mathematical reasoning and multi-hop QA benchmarks, while reducing token usage by up to 41.26%. In addition, by nature, StepBack can be combined with adaptive inference methods such as Adaptive Consistency, further improving their inference-time efficiency.
arxiv
StepBack: Step-Level Error-Localized Resampling for Efficient Test-Time Reasoning
StepBack is a new decoding strategy that improves test-time reasoning efficiency by localizing likely first errors in draft reasoning trajectories and resampling only the error step and its suffix, followed by majority voting. It matches the accuracy of standard self-consistency across seven math and multi-hop QA benchmarks while reducing token usage by up to 41.26%. The method can also be combined with adaptive inference methods like Adaptive Consistency for further efficiency gains.
This paper introduces a concrete, novel method with measurable efficiency gains, relevant to researchers and practitioners working on LLM reasoning and inference optimization.
Comments & Questions (0)
No comments yet
Be the first to comment!