AutoCAP: 面向零样本思维链的自动跨语言对齐规划
AutoCAP: Towards Automatic Cross-lingual Alignment Planning for Zero-shot Chain-of-Thought
AI总结：
针对跨语言思维链现有方法依赖人工选语言、静态均等分配权重的问题，提出含自动语言选择与权重分配提示的AutoCAP框架，在多个基准上实现零样本跨语言推理的最优性能。
摘要：
跨语言思维链可有效完成跨语言推理任务，受到越来越多的关注。当前主流方法通过整合不同语言的推理知识来提升跨语言对齐能力，尽管取得了优异性能，但仍存在两大主要挑战：（1）人工指定语言：仍高度依赖人工选择待整合的语言，严重影响其泛化性；（2）静态权重分配：现有方法简单地对所有语言进行均等整合，而实际上不同语言的推理路径应具有不同权重，以实现更好的互补与整合。基于此，我们提出了用于零样本思维链的自动跨语言对齐规划（AutoCAP）以解决上述挑战。AutoCAP的核心由两个组件构成：（1）自动语言选择提示（Automatic Language Selection Prompting），用于引导大语言模型（LLMs）选择合适的语言；（2）自动权重分配提示（Automatic Weight Allocation Prompting），用于为每条推理路径自动分配对齐权重分数。在多个基准上的大量实验表明，AutoCAP取得了当前最优（state-of-the-art）性能，超越了以往需要人工操作的方法。
英文摘要：
Cross-lingual chain-of-thought can effectively complete reasoning tasks across languages, which gains increasing attention. Recently, dominant approaches in the literature improve cross-lingual alignment capabilities by integrating reasoning knowledge from different languages. Despite achieving excellent performance, current methods still have two main challenges: (1) Manual language specification: They still highly rely on manually selecting the languages to integrate, severely affecting their generalizability; (2) Static weight allocation: Current methods simply integrate all languages equally. In fact, different language reasoning paths should have different weights to achieve better complementation and integration. Motivated by this, we introduce an Automatic Cross-lingual Alignment Planning (AutoCAP) for zero-shot chain-of-thought to address the above challenges. The core of AutoCAP consists of two components: (1) Automatic Language Selection Prompting to guide LLMs to select appropriate languages and (2) Automatic Weight Allocation Prompting to automatically allocate alignment weight scores to each reasoning path. Extensive experiments on several benchmarks reveal that AutoCAP achieves state-of-the-art performance, surpassing previous methods that required manual effort.
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。
