Hire a Linguist!: Learning Endangered Languages in LLMs with In-Context Linguistic Descriptions
Kexun Zhang , Yee Choi , Zhenqiao Song, and 3 more authors
In Findings of the Association for Computational Linguistics: ACL 2024, Aug 2024
How can large language models (LLMs) process and translate endangered languages? Many languages lack a large corpus to train a decent LLM; therefore existing LLMs rarely perform well in unseen, endangered languages. On the contrary, we observe that 2000 endangered languages, though without a large corpus, have a grammar book or a dictionary. We propose LingoLLM, a training-free approach to enable an LLM to process unseen languages that hardly occur in its pre-training. Our key insight is to demonstrate linguistic knowledge of an unseen language in an LLM’s prompt, including a dictionary, a grammar book, and morphologically analyzed input text. We implement LingoLLM on top of two models, GPT-4 and Mixtral, and evaluate their performance on 5 tasks across 8 endangered or low-resource languages. Our results show that LingoLLM elevates translation capability from GPT-4’s 0 to 10.5 BLEU for 10 language directions. Our findings demonstrate the tremendous value of linguistic knowledge in the age of LLMs for endangered languages. Our data, code, and model generations will be released to the public. Our data, code, and model generations can be found at \urlhttps://github.com/LLiLab/llm4endangeredlang.
HARDTESTGEN: A High-Quality RL Verifier Generation Pipeline for LLM Algorithimic CodingIn The Fourteenth International Conference on Learning Representations, 2026
CiteGuard: Faithful Citation Attribution for LLMs via Retrieval-Augmented Validation2026