通过潜空间干预提升多语言模型回答一致性，不牺牲准确性。
Latent-Space Intervention for Cross-Lingual Factual Consistency: Consistency Improvements without Accuracy Drops
- 在多语言表示空间中训练层特定自编码器，推理时修正事实问答提示。
- 英语与阿拉伯语、俄语间开放问答相关性提升0.16和0.20，多项选择题一致率提高。
- 方法可显著改善跨语言一致性，适合多语言知识系统开发者使用。
大型语言模型在不同语言下对同一事实问题的回答常不一致。本文研究跨语言潜空间干预是否能缓解此问题。通过在平行多语言表示上训练分层自编码器，并在推理阶段对事实问答提示进行修正，发现潜空间干预提升了语言间的几何对齐度。这一改进转化为与英语在开放问答和多项选择题格式下的跨语言一致性显著提升，且未降低事实准确性。在开放问答中，英语与非英语语言的Spearman秩相关系数显著提高，英语-阿拉伯语对提升0.16，英语-俄语对提升0.20。在多项选择题中，答案与英语的一致性在KLAR和mParaRel数据集上均持续提升。消融实验表明，自编码器重建带来稳定增益且无准确率损失，主成分分析投影贡献较小，均值偏移在开放问答中虽提升显著但伴随一定准确率下降。
原文摘要 · Abstract (English)
Large Language Models (LLMs) often answer the same factual question differently across languages. We study whether cross-lingual latent-space intervention can reduce this inconsistency. We train layer-specific autoencoders on parallel multilingual representations and apply inference-time corrections to factual QA prompts. We find that latent intervention improves geometric alignment between languages, and that this improvement translates into consistent gains in cross-lingual consistency with English across both open-ended and multiple-choice QA formats, without degrading factual accuracy. In open-ended QA, Spearman's rank correlation between English and non-English languages improves substantially, with gains of 0.16 for English-Arabic and 0.20 for English-Russian pairs. In multiple-choice QA, answer agreement with English improves consistently across both KLAR and mParaRel. Ablations show that AE reconstruction yields consistent gains at no accuracy cost, while PCA projection contributes marginally, and mean-shift produces substantially larger consistency gains in open-ended QA at the cost of some accuracy.
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。