TY - GEN
T1 - Would LLMs be Good Historical Linguists and Chinese Dialect Learners?
AU - Liu, Yicheng
AU - Shi, Shumin
AU - Zhou, Youchao
AU - Zhang, Xingchen
N1 - Publisher Copyright:
© 2026 Association for Computational Linguistics.
PY - 2026
Y1 - 2026
N2 - Large language models (LLMs) perform well on Standard Chinese but struggle with low-resource Chinese dialects due to substantial phonological divergence. We investigate whether incorporating Middle Chinese, the common historical ancestor of most of the modern Chinese dialects, can improve dialectal pronunciation modeling in a linguistically interpretable manner. We focus on two specific task variants: (1) conditional sound change rule induction (a variant of Sound Law Induction, SLI), where models infer executable phonological transformation rules from Middle Chinese to modern dialects, and (2) sentence-level dialectal pronunciation transcription (a variant of Grapheme-to-Phoneme, G2P), requiring dialect-specific International Phonetic Alphabet (IPA) generation. We construct a multi-source dataset covering Middle Chinese and 12 modern Chinese dialects, including character-level correspondences, rule exemplars, and sentence-level IPA transcription. We adopt a parameter-efficient training framework combining LoRA-based supervised fine-tuning and reinforcement learning via Group Relative Policy Optimization (GRPO) for the first task. Across both tasks and a wide range of dialects and evaluation metrics, our approach achieves overall improvements over strong baselines, including DeepSeek-V3.2 and ChatGPT-5.2, while revealing variation across dialects. These results demonstrate the value of leveraging historical linguistic knowledge for modeling low-resource Chinese dialects.
AB - Large language models (LLMs) perform well on Standard Chinese but struggle with low-resource Chinese dialects due to substantial phonological divergence. We investigate whether incorporating Middle Chinese, the common historical ancestor of most of the modern Chinese dialects, can improve dialectal pronunciation modeling in a linguistically interpretable manner. We focus on two specific task variants: (1) conditional sound change rule induction (a variant of Sound Law Induction, SLI), where models infer executable phonological transformation rules from Middle Chinese to modern dialects, and (2) sentence-level dialectal pronunciation transcription (a variant of Grapheme-to-Phoneme, G2P), requiring dialect-specific International Phonetic Alphabet (IPA) generation. We construct a multi-source dataset covering Middle Chinese and 12 modern Chinese dialects, including character-level correspondences, rule exemplars, and sentence-level IPA transcription. We adopt a parameter-efficient training framework combining LoRA-based supervised fine-tuning and reinforcement learning via Group Relative Policy Optimization (GRPO) for the first task. Across both tasks and a wide range of dialects and evaluation metrics, our approach achieves overall improvements over strong baselines, including DeepSeek-V3.2 and ChatGPT-5.2, while revealing variation across dialects. These results demonstrate the value of leveraging historical linguistic knowledge for modeling low-resource Chinese dialects.
UR - https://www.scopus.com/pages/publications/105053666375
U2 - 10.18653/v1/2026.acl-long.831
DO - 10.18653/v1/2026.acl-long.831
M3 - Conference contribution
AN - SCOPUS:105053666375
T3 - Proceedings of the Annual Meeting of the Association for Computational Linguistics
SP - 18231
EP - 18256
BT - Long Papers
A2 - Liakata, Maria
A2 - Moreira, Viviane P.
A2 - Zhang, Jiajun
A2 - Jurgens, David
PB - Association for Computational Linguistics (ACL)
T2 - 64th Annual Meeting of the Association for Computational Linguistics, ACL 2026
Y2 - 2 July 2026 through 7 July 2026
ER -