arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2604.04720cs.CLcs.AI
收藏

什么使多语言推理有效?通过可测量的特征解构推理痕迹

What Makes Good Multilingual Reasoning? Disentangling Traces with Measurable Features

University of Maryland(马里兰大学);Johns Hopkins University(约翰霍普金斯大学)

Dayeon Ki, Kevin Duh, Marine Carpuat

AI总结:

本文通过定义可测量的推理特征,研究多语言环境下有效推理的特征,并发现这些特征在不同语言中的关联强度差异显著,挑战了以英语为中心的奖励设计。

摘要:

大型推理模型(LRMs)在英语和其他语言之间仍存在较大的性能差距,但许多现有工作假设这些差距可以通过使每种语言的推理过程接近英语推理过程来缩小。本文挑战这一假设,探讨有效多语言推理的特征,并评估英语衍生的推理特征在其他语言中的实际帮助程度。我们首先定义了一套涵盖多语言对齐、推理步骤和推理流程的可测量推理特征,并使用逻辑回归量化每个特征与最终答案准确性的关联。我们进一步在多语言痕迹上训练稀疏自编码器,自动发现潜在的推理概念,这些概念实例化或扩展了这些特征。最后,我们使用这些特征作为测试时的选择策略,检验它们是否能引导模型向更强的多语言推理发展。在两个数学推理基准测试、四个LRMs和10种语言上,我们发现大多数特征与准确性正相关,但不同语言中的关联强度差异显著,甚至在某些情况下会反转。我们的发现挑战了以英语为中心的奖励设计,指出了适应性目标,以适应语言特定的推理模式,并为多语言基准和奖励设计提供了具体启示。

英文摘要:

Large Reasoning Models (LRMs) still exhibit large performance gaps between English and other languages, yet much current work assumes these gaps can be closed simply by making reasoning in every language resemble English reasoning. This work challenges this assumption by asking instead: what actually characterizes successful reasoning traces in multilingual settings, and to what extent do English-derived reasoning features genuinely help in other languages? We first define a suite of measurable reasoning features spanning multilingual alignment, reasoning step, and reasoning flow aspects of reasoning traces, and use logistic regression to quantify how each feature associates with final answer accuracy. We further train sparse autoencoders over multilingual traces to automatically discover latent reasoning concepts that instantiate or extend these features. Finally, we use the features to re-rank traces and measure their impact on accuracy at test time. Across two mathematical reasoning benchmarks, four LRMs, and ten languages, we find that most features are positively associated with accuracy, but the strength of association varies considerably across languages and can even reverse in some. Our findings challenge English-centric reward designs and point toward adaptive objectives that accommodate language-specific reasoning patterns, with concrete implications for multilingual benchmark and reward design.

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。

↑