MAS-Bai：面向布文白语的 linguistically informed 自适应多智能体翻译框架

MAS-Bai: Linguistically Informed Adaptive Multi-Agent Translation for Bowen-Script Bai

AI 导读

MAS-Bai 是一个面向布文（Bowen）白语—汉语翻译的自适应多智能体框架，通过轻量检索翻译路径与含词源、句法智能体的深度语文学路径动态路由，并用轻量反向翻译器的循环一致性作为推理时可靠性信号。

正文 · 原文

Abstract:Large Language Models (LLMs) remain unreliable for extremely low-resource languages whose writing systems conflict with high-resource pretraining priors. We study Bai-Chinese translation in the Bowen script, where Chinese characters are frequently borrowed phonetically rather than semantically, causing severe literal-translation hallucinations. We propose MAS-Bai, a linguistically informed adaptive multi-agent framework for Bowen-script Bai-Chinese translation. MAS-Bai routes each input through either a lightweight retrieval-translation path or a deeper philological path with etymological and syntactic agents, and uses cycle-consistency with a lightweight reverse translator as an inference-time reliability signal. We construct a 6,536-sentence Bai-Chinese corpus and evaluate on a 1,536-sentence test set. MAS-Bai achieves 16.23 BLEU and 62.15 COMET, improving over Standard RAG by 8.11 BLEU and 6.85 COMET. Forward LoRA, expert ablations and controlled routing experiments distinguish the roles of supervised adaptation, Bai-specific expertise and conditional routing. The largest gains occur on Bowen phonetic loans and divergent Bai word order, while human evaluation and reverse-verifier analyses support the automatic results.

Comments:	14 pages, 3 figures, Findings of EMNLP 2026
Subjects:	Computation and Language (cs.CL)
Cite as:	arXiv:2610.23205 [cs.CL]
	(or arXiv:2610.23205v1 [cs.CL] for this version)
	https://doi.org/10.48550/arXiv.2610.23205 arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Jingting Zheng [view email]
[v1] Fri, 16 Oct 2026 09:43:32 UTC (5,796 KB)

来源：arXiv cs.CL · arxiv.org