arXiv cs.CL· Yuchen Zhang, Haralambos Mouratidis, Ravi Shekhar·· 14 小时前AI 评分27
保留再扩展：面向多语言 LLM 语音识别的源感知适配与模型合并
Preserve to Expand: Source-Aware Adaptation and Model Merging for Multilingual LLM-Based ASR
AI 导读
研究在基于 connector 的 Speech LLM 中扩展多语言 ASR 时如何在不重放源语言数据的前提下保留原有语言能力。单目标扩展中，仅目标语言微调和标准 TIES 合并虽能学会新语言，却造成严重的源语言遗忘，SSU-Wanda+TIES 取得最佳的源语言保留权衡。多目标扩展中，更新合并可稳定保留源语言，而递归扩展在有利顺序下能改善目标适配，但对顺序高度敏感。
正文 · 原文
Abstract:Expanding multilingual ASR systems to new languages is challenging when adaptation must preserve previously supported languages without replaying source-language training data. We study this problem in connector-based Speech LLMs, where a trainable connector maps speech representations into a frozen large language model. We evaluate target-update construction and merging strategies for adapting the connector while preserving source-language performance. In single-target expansion, target-only fine-tuning and standard TIES merging learn new languages but cause severe source-language forgetting, while SSU-Wanda+TIES gives the best source-preserving trade-off. In multi-target expansion, update merging provides stable source retention, whereas recursive expansion can improve target adaptation under favorable orders but is highly order-sensitive. These results show that multilingual ASR expansion requires balancing target acquisition, source retention, and interactions among target-language updates.
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.35846 [cs.CL] |
| (or arXiv:2610.35846v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.35846 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Yuchen Zhang Dr [view email]
[v1]
Mon, 26 Oct 2026 17:56:22 UTC (135 KB)
来源：arXiv cs.CL · arxiv.org