Year: 2026
Type: conference-paper
Abstract: Inspired by linguistic Olympiads, extremely low-resource language reasoning presents a unique challenge that enables models to solve problems without prior knowledge.This task mirrors the Rosetta Stone decipherment process, where the goal is to induce and apply linguistic rules from minimal context.Existing methods mainly rely on naive in-context learning that fails to handle the complexity and diversity of language rules.To mitigate this issue, we propose a framework that combines dynamic knowledge construction with task-aware evidence augmentation.First, we use large language models (LLMs) to generate a diverse set of task-specific examples that instantiate potential linguistic rules for the target low-resource language.Second, we apply a semantic retrieval mechanism to select the most relevant examples as evidence for each test query, preventing context overload and ensuring focused, analogical reasoning.Our method shifts from learning language distributions to dynamically discovering and applying rules.Experimental results on the LINGOLY and Linguini benchmark show that our approach achieves competitive performance across various LLMs, outperforming existing baselines.More importantly, our framework advances extremely lowresource reasoning and provides a generalizable framework for rule induction under knowledge constraints.CONTEXT QUERY ANSWER Ainu is an indigenous language of Japan that is unrelated to Japanese.... PREAMBLE i. Sentence Translation Fill in blanks with the corresponding numerals, written out either in Roon or in digits as appropriate, taking into account the year.# 1855 1955 2012 3 (e) (f) kior ... 98 (t) (u) (v) This problem investigates Roon numerals as they were spoken in 1855, 1955, and 2012.# 1855 1955\2012 2 nuru nuru nuru 10 onemerim safur safur 7 onemenuru rimenuru fik ... (e): ŋokor (f): iŋokor [...
Authors: Xiaoyu Zhu, Long Yuan, Rui Qi, Jinan Xu
Institution: Beijing Jiaotong University
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W7166803607