arXiv：cs.CL· HyeonSeok Lim, SeungWoo Song, Inho Won, Hoyun Song, Jihyo Kim, KyungTae Lim·· 3 小时前AI 评分35
多语言推理中骨架该说哪种语言？LASEF 框架研究骨架语言选择
Which Language Should a Skeleton Speak? Language Choices in Multilingual Reasoning
AI 导读
研究者提出 Language-Aware Skeleton Exploration Framework（LASEF），研究多语言数学推理中骨架语言的选择问题。结果显示英文骨架平均有轻微正向倾向，在较小模型和低资源语言上最明显，但校正后语言层面的增益很少显著，英文并非普遍最优。研究归纳出方向一致、依赖评测与基准、非对称负面三种骨架语言效应。
正文
Abstract:Skeleton-based reasoning prompting is a promising training-free approach for structuring LLM reasoning, but prior work largely assumes an English-centric setting. We propose the Language-Aware Skeleton Exploration Framework (LASEF) to study skeleton-language choice in multilingual mathematical reasoning. Across math benchmarks, model scales, and languages, we show that English skeletons yield a small positive tendency on average, most visible for smaller models and low-resource languages. However, few language-level gains remain significant after correction, and English is not universally optimal. Combining greedy decoding, multi-rollout evaluation, translation ablation, and cross-benchmark validation, we further find three patterns of skeleton-language effects: directionally consistent, evaluation- and benchmark-dependent, and asymmetric negative. These effects cannot be fully explained by generation quality alone. Overall, skeleton language is a context-dependent design variable that requires multi-level exploration. All resources are released at this https URL.
| Comments: | Accepted to EMNLP 2026 (Findings) |
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.09607 [cs.CL] |
| (or arXiv:2610.09607v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.09607 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Hyeonseok Lim [view email]
[v1]
Wed, 7 Oct 2026 07:53:13 UTC (389 KB)
来源：arXiv：cs.CL · arxiv.org