用多语言联合学习，少数据少推理 tokens 也能提升大模型推理效率。
Less Data Less Tokens: Multilingual Unification Learning for Efficient Test-Time Reasoning in LLMs
- 通过多语言思维链数据联合训练，实现跨语言推理能力互补。
- 仅用少量数据就显著提升模型推理能力，减少 30% 以上推理令牌数。
- 适合资源受限场景下高效部署大模型，尤其对低资源语言友好。
本文研究大语言模型在测试时扩展面临的数据与推理效率挑战。基于初步实验，发现多语言推理存在显著差异，提出新型方法 $L^2$ 多语言统一学习，结合解码干预策略。该方法利用两种多语言数据：全链式思维链标注及分步混合语言数据。通过微调，即使少量数据亦可显著增强推理能力。结果表明，多语言学习在保持相近性能的前提下，同时降低所需数据量与推理令牌数。此外，$L^2$ 与其他数据高效方法正交，强调了多样化数据选择的重要性。该方法为解决大模型数据收集与测试时计算效率问题提供了有效路径。
原文摘要 · Abstract (English)
This paper explores the challenges of test-time scaling of large language models (LLMs), regarding both the data and inference efficiency. We highlight the diversity of multi-lingual reasoning based on our pilot studies, and then introduce a novel approach, \(L^2\) multi-lingual unification learning with a decoding intervention strategy for further investigation. The basic idea of \(L^2\) is that the reasoning process varies across different languages, which may be mutually beneficial to enhance both model performance and efficiency. In specific, there are two types of multi-lingual data: the entire long chain-of-thought annotations in different languages and the step-wise mixture of languages. By further tuning based on them, we show that even small amounts of data can significantly improve reasoning capabilities. Our findings suggest that multilingual learning reduces both the required data and the number of inference tokens while maintaining a comparable performance. Furthermore, \(L^2\) is orthogonal to other data efficient methods. Thus, we also emphasize the importance of diverse data selection. The \(L^2\) method offers a promising solution to the challenges of data collection and test-time compute efficiency in LLMs.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。