内在自我纠正何时有效？一项任务敏感分析
When Does Intrinsic Self-Correction Help? A Task-Sensitive Analysis
AI总结：
本研究采用任务敏感视角分析内在自我纠正（SC），发现当任务结构支持验证约束、重新审视推理或提供第二意见时，SC能带来一致性能提升，表明其有效性取决于任务类型。
摘要：
内在自我纠正（SC）旨在通过提示模型在没有外部反馈的情况下重新审视其初始答案来改进大型语言模型的输出。最近的研究质疑了这种方法的可靠性，表明模型通常难以判断其初始响应是否正确。在这项工作中，我们对SC采取了任务敏感的视角。我们不问它是否普遍有效，而是考察SC可能通过不同机制运作的设置：验证显式约束、重新审视复杂推理过程，或在文字游戏任务中为竞争策略提供第二意见。在多个基准和模型上，我们发现当底层任务结构促进这些修订模式时，SC可以带来一致的性能提升。这些结果表明，SC最好被理解为一种任务依赖的推理时策略，其有用性取决于修订阶段在给定任务中能发挥的作用，而不是作为一种统一可靠的方法来改进初始模型输出。
英文摘要：
Intrinsic self-correction (SC) aims to improve large language model outputs by prompting a model to revisit its own initial answer without external feedback. Recent studies have questioned the reliability of this approach, showing that models often struggle to judge whether their initial responses are correct. In this work, we take a task-sensitive view of SC. Rather than asking whether it works in general, we examine settings where SC may operate through different mechanisms: verifying explicit constraints, revisiting a complex reasoning process, or providing a second opinion over competing strategies in word-game tasks. Across multiple benchmarks and models, we find that SC can yield consistent performance gains when the underlying task structure facilitates these modes of revision. These results suggest that SC is best understood as a task-dependent inference-time strategy whose usefulness depends on the role the revision stage can play in a given task, rather than as a uniformly reliable method for improving initial model outputs.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
