# Typological Feature Prediction with Large Language Models: An In-Context Learning Approach

arXiv: https://arxiv.org/abs/2609.03775 · HTML: https://mlsanity.com/paper/2609.03775/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 34 references that are in the map.
- First posted on arXiv 3 Sep 2026.

## Builds on (most cited first, 19 of 19)

- [Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting](https://mlsanity.com/paper/2305.04388/) (2023)
- [Choosing Transfer Languages for Cross-Lingual Learning](https://mlsanity.com/paper/1905.12688/) (2019)
- [UDapter: Language Adaptation for Truly Universal Dependency Parsing](https://mlsanity.com/paper/2004.14327/) (2020)
- [A Benchmark for Learning to Translate a New Language from One Grammar Book](https://mlsanity.com/paper/2309.16575/) (2023)
- [Modeling Language Variation and Universals: A Survey on Typological Linguistics for Natural Language Processing](https://mlsanity.com/paper/1807.00914/) (2018)
- [Predicting Performance for Natural Language Processing Tasks](https://mlsanity.com/paper/2005.00870/) (2020)
- [Learning Language Representations for Typology Prediction](https://mlsanity.com/paper/1707.09569/) (2017)
- [Can LLMs Really Learn to Translate a Low-Resource Language from One Grammar Book?](https://mlsanity.com/paper/2409.19151/) (2024)
- [URIEL+: Enhancing Linguistic Inclusion and Usability in a Typological and Multilingual Knowledge Base](https://mlsanity.com/paper/2409.18472/) (2024)
- [ProxyLM: Predicting Language Model Performance on Multilingual Tasks via Proxy Models](https://mlsanity.com/paper/2406.09334/) (2024)
- [SIGTYP 2020 Shared Task: Prediction of Typological Features](https://mlsanity.com/paper/2010.08246/) (2020)
- [Language Embeddings Sometimes Contain Typological Generalizations](https://mlsanity.com/paper/2301.08115/) (2023)
- [Predicting Typological Features in WALS using Language Embeddings and Conditional Probabilities: 'UFAL Submission to the SIGTYP 2020 Shared Task](https://mlsanity.com/paper/2010.03920/) (2020)
- [LingGym: How Far Are LLMs from Thinking Like Field Linguists?](https://mlsanity.com/paper/2511.00343/) (2025)
- [Parameter sharing between dependency parsers for related languages](https://mlsanity.com/paper/1808.09055/) (2018)
- [data2lang2vec: Data Driven Typological Features Completion](https://mlsanity.com/paper/2409.17373/) (2024)
- [Modality Matching Matters: Calibrating Language Distances for Cross-Lingual Transfer in URIEL+](https://mlsanity.com/paper/2510.19217/) (2025)
- [Simple Additions, Substantial Gains: Expanding Scripts, Languages, and Lineage Coverage in URIEL+](https://mlsanity.com/paper/2510.27183/) (2025)
- [Assessing the Impact of Typological Features on Multilingual Machine Translation in the Age of Large Language Models](https://mlsanity.com/paper/2602.03551/) (2026)

## Abstract (arXiv)

Typological features are widely used in multilingual NLP, and the prediction of such features holds downstream utility. However, existing methods to predict missing values lack interpretable justifications for predictions, while their performance across resource levels and feature types remains underexplored. Given LLMs' abilities in meta-linguistic reasoning and in providing rationales, we investigate LLMs' performance in typological feature prediction via an in-context learning approach with linguistic data from URIEL+ and Glottolog. We find that zero-shot prompting is insufficient, but when given phylogenetic and geographic neighbour evidence, LLMs substantially outperform all baselines without disadvantaging low-resource languages. We further find that most LLM rationales are consistent with the provided evidence, offering a step toward explainable typological feature prediction.