发表机构
RMIT University; Faculty of Computer Science and Engineering, Ho Chi Minh City University of Technology (HCMUT), VNU-HCM（皇家墨尔本理工大学; 胡志明市理工大学计算机科学与工程学院，越南胡志明市国家大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究如何在低资源下将多语言编码器适应新语言和任务，提出DeltaMergeLowRes方法，分别学习语言和任务增量并通过多种规则组合。实验表明跨轴TIES能提升摘要任务表现，稀疏感知合并可降低分类ECE，组合规则影响模型特性。
AI 中文摘要
在自然语言处理中，将多语言编码器适应新语言和新任务，同时仅有几百个标注示例，这是常见的低资源设置。然而，通常通过昂贵的语言 - 任务微调来融合两者。本文提出能否分别训练并在权重空间中重新组合。DeltaMergeLowRes从无标注单语文本学习语言增量ΔL，从标注英语数据学习任务增量ΔT，在推理时通过加法、激活引导、稀疏感知和新的跨轴TIES这四种规则组合它们。在四个任务族和四种非洲语言上进行实验，结果表明跨轴TIES在3/4的语言上的摘要任务中表现出色，提升了问答任务的F1和EM，稀疏感知合并在相同宏观F1下将分类ECE降低了36%。组合规则显著改变了合并模型保留、抑制和校准的内容。最后还发布了所有JSON跟踪和声明账本。
英文摘要
Adapting a multilingual encoder to a new language \emph{and} a new task with only a few hundred gold examples is a common low-resource NLP setting, yet the two axes are usually fused via an expensive language--task fine-tuning run. We ask whether they can instead be trained separately and recombined in weight space. \DeltaMergeLowRes{} learns a language delta $Δ_L$ from unlabeled monolingual text and a task delta $Δ_T$ from labeled English data, then composes them at inference under one of four rules: additive, activation-guided, sparsity-aware, and a novel \emph{cross-axis TIES}. The new rule adapts the TIES-Merging steps of trimming, sign election, and merging to the language and task axes rather than to two task axes. Holding $(Δ_L,Δ_T)$ fixed across rules on four task families and four African languages ($158$ evaluated cells, $10{,}000$-sample paired bootstrap per cell), we find: (i) cross-axis TIES wins summarisation on $3/4$ languages by $+4$ to $+7$ chrF (chrF $18.59$ vs.\ $13.80$ task-only); (ii) it improves QA F1 by $+2.32$ and EM by $+2.91$; and (iii) sparsity-aware merging cuts classification ECE by $36\%$ at parity macro-F1. The composition rule materially changes what the merged model preserves, suppresses, and calibrates. We release all JSON traces and a claim ledger.
