通过重排序提升机器翻译质量，用更多计算换更好结果。
Investigating Test-Time Scaling with Reranking for Machine Translation
- 生成多个译文候选，选最优者提升效果。
- 高资源语言上，多候选重排序显著提升翻译质量。
- 小模型用大量候选可媲美大模型，适合算力有限场景。
模型参数扩展已成为提升自然语言处理系统性能的主流方法，但伴随巨大计算成本。测试时扩展（TTS）提供了一种替代方案：在推理阶段增加计算量，通过生成多个翻译候选并选择最佳结果来提升性能。尽管在数学推理等任务中已证明有效，但其在机器翻译（MT）中的系统性研究仍不足。本文首次对机器翻译中的TTS进行系统性探索，采用简单的best-of-N框架，在WMT24基准上评估。实验涵盖六种高资源和一种低资源语言对，五种模型规模（3B-72B），以及多种计算预算（N最高达1024）。结果表明：（a）高资源语言下，TTS显著提升多种神经机器翻译评估指标表现，人工评价也确认了这一优势；（b）小模型配合大N值可达到甚至超越大模型在N=1时的性能，且消耗更多计算资源；（c）在固定计算预算下，大模型通常更高效，而低资源情况下TTS可能因评估指标盲点导致质量下降。
原文摘要 · Abstract (English)
Scaling model parameters has become the de facto strategy for improving NLP systems, but it comes with substantial computational costs. Test-Time Scaling (TTS) offers an alternative by allocating more computation at inference: generating multiple candidates and selecting the best. While effective in tasks such as mathematical reasoning, TTS has not been systematically explored for machine translation (MT). In this paper, we present the first systematic study of TTS for MT, investigating a simple but practical best-of-N framework on WMT24 benchmarks. Our experiments cover six high-resource and one low-resource language pairs, five model sizes (3B-72B), and various TTS compute budget (N up to 1024). Our results show that a) For high-resource languages, TTS generally improves translation quality according to multiple neural MT evaluation metrics, and our human evaluation confirms these gains; b) Augmenting smaller models with large $N$ can match or surpass larger models at $N{=}1$ with more compute cost; c) Under fixed compute budgets, larger models are typically more efficient, and TTS can degrade quality due to metric blind spots in low-resource cases.
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。