AutoCAP: Towards Automatic Cross-lingual Alignment Planning for Zero-shot Chain-of-Thought

TL;DR

AutoCAP introduces an automated approach for cross-lingual reasoning that dynamically selects languages and allocates weights, significantly improving zero-shot reasoning performance across multiple benchmarks.

Contribution

It proposes a novel automatic planning method for cross-lingual alignment, removing manual language selection and static weighting, enhancing generalizability and effectiveness.

Findings

Achieves state-of-the-art results on several benchmarks.

Outperforms previous manual methods in cross-lingual reasoning.

Demonstrates the effectiveness of automatic language and weight selection.

Abstract

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.