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

2026-09-03

AI Summary

研究使用大型语言模型通过上下文学习方法预测类型学特征，解决了现有方法缺乏解释性和性能不足的问题。

Abstract

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.

Problem

• Typological Features
• Prediction
• Interpretable Justifications
• Resource Levels
• Feature Types

Innovation

• Large Language Models
• In-Context Learning
• Typological Feature Prediction
• Explainability