# In-context Language Learning for Endangered Languages in Speech Recognition

arXiv: https://arxiv.org/abs/2505.20445 · HTML: https://mlsanity.com/paper/2505.20445/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 21 references that are in the map.
- First posted on arXiv 26 May 2025.

## Builds on (most cited first, 12 of 12)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Scaling Speech Technology to 1,000+ Languages](https://mlsanity.com/paper/2305.13516/) (2023)
- [In-Context Learning with Long-Context Models: An In-Depth Exploration](https://mlsanity.com/paper/2405.00200/) (2024)
- [SONAR: Sentence-Level Multimodal and Language-Agnostic Representations](https://mlsanity.com/paper/2308.11466/) (2023)
- [BUFFET: Benchmarking Large Language Models for Few-shot Cross-lingual Transfer](https://mlsanity.com/paper/2305.14857/) (2023)
- [LLMs Are Few-Shot In-Context Low-Resource Language Learners](https://mlsanity.com/paper/2403.16512/) (2024)
- [One Country, 700+ Languages: NLP Challenges for Underrepresented Languages and Dialects in Indonesia](https://mlsanity.com/paper/2203.13357/) (2022)
- [Multilingual Large Language Models Are Not (Yet) Code-Switchers](https://mlsanity.com/paper/2305.14235/) (2023)
- [Towards Robust Speech Representation Learning for Thousands of Languages](https://mlsanity.com/paper/2407.00837/) (2024)
- [Can we teach language models to gloss endangered languages?](https://mlsanity.com/paper/2406.18895/) (2024)
- [A Very Low Resource Language Speech Corpus for Computational Language Documentation Experiments](https://mlsanity.com/paper/1710.03501/) (2017)
- [Killkan: The Automatic Speech Recognition Dataset for Kichwa with Morphosyntactic Information](https://mlsanity.com/paper/2404.15501/) (2024)

## Built on by (most cited first, 2 of 2)

- [Multimodal In-context Learning for ASR of Low-resource Languages](https://mlsanity.com/paper/2601.05707/) (2026)
- [Hard to Be Heard: Phoneme-Level ASR Analysis of Phonologically Complex, Low-Resource Endangered Languages](https://mlsanity.com/paper/2604.18204/) (2026)

## Abstract (arXiv)

With approximately 7,000 languages spoken worldwide, current large language models (LLMs) support only a small subset. Prior research indicates LLMs can learn new languages for certain tasks without supervised data. We extend this investigation to speech recognition, investigating whether LLMs can learn unseen, low-resource languages through in-context learning (ICL). With experiments on four diverse endangered languages that LLMs have not been trained on, we find that providing more relevant text samples enhances performance in both language modelling and Automatic Speech Recognition (ASR) tasks. Furthermore, we show that the probability-based approach outperforms the traditional instruction-based approach in language learning. Lastly, we show ICL enables LLMs to achieve ASR performance that is comparable to or even surpasses dedicated language models trained specifically for these languages, while preserving the original capabilities of the LLMs. Our code is publicly available.