Research

Paper

AI LLM March 16, 2026

Datasets for Verb Alternations across Languages: BLM Templates and Data Augmentation Strategies

Authors

Giuseppe Samo, Paola Merlo

Abstract

Large language models (LLMs) have shown remarkable performance across various sentence-based linguistic phenomena, yet their ability to capture cross-sentence paradigmatic patterns, such as verb alternations, remains underexplored. In this work, we present curated paradigm-based datasets for four languages, designed to probe systematic cross-sentence knowledge of verb alternations (change-of-state and object-drop constructions in English, German and Italian, and Hebrew binyanim). The datasets comprise thousands of the Blackbird Language Matrices (BLMs) problems. The BLM task -- an RPM/ARC-like task devised specifically for language -- is a controlled linguistic puzzle where models must select the sentence that completes a pattern according to syntactic and semantic rules. We introduce three types of templates varying in complexity and apply linguistically-informed data augmentation strategies across synthetic and natural data. We provide simple baseline performance results across English, Italian, German, and Hebrew, that demonstrate the diagnostic usefulness of the datasets.

Metadata

arXiv ID: 2603.15295
Provider: ARXIV
Primary Category: cs.CL
Published: 2026-03-16
Fetched: 2026-03-17 06:02

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.15295v1</id>\n    <title>Datasets for Verb Alternations across Languages: BLM Templates and Data Augmentation Strategies</title>\n    <updated>2026-03-16T13:57:38Z</updated>\n    <link href='https://arxiv.org/abs/2603.15295v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.15295v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Large language models (LLMs) have shown remarkable performance across various sentence-based linguistic phenomena, yet their ability to capture cross-sentence paradigmatic patterns, such as verb alternations, remains underexplored. In this work, we present curated paradigm-based datasets for four languages, designed to probe systematic cross-sentence knowledge of verb alternations (change-of-state and object-drop constructions in English, German and Italian, and Hebrew binyanim). The datasets comprise thousands of the Blackbird Language Matrices (BLMs) problems. The BLM task -- an RPM/ARC-like task devised specifically for language -- is a controlled linguistic puzzle where models must select the sentence that completes a pattern according to syntactic and semantic rules. We introduce three types of templates varying in complexity and apply linguistically-informed data augmentation strategies across synthetic and natural data. We provide simple baseline performance results across English, Italian, German, and Hebrew, that demonstrate the diagnostic usefulness of the datasets.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.CL'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.DB'/>\n    <published>2026-03-16T13:57:38Z</published>\n    <arxiv:comment>9 pages, 16 figures, accepted at LREC 2026</arxiv:comment>\n    <arxiv:primary_category term='cs.CL'/>\n    <author>\n      <name>Giuseppe Samo</name>\n    </author>\n    <author>\n      <name>Paola Merlo</name>\n    </author>\n  </entry>"
}