%Aigaion2 BibTeX export from Idiap Publications
%Wednesday 22 July 2026 03:38:02 PM

@INPROCEEDINGS{Samo_LREC2026_2026,
                      author = {Samo, Giuseppe and Merlo, Paola},
                    projects = {Idiap},
  additionalresearchprograms = {AI for Everyone},
                       title = {Datasets for Verb Alternations across Languages: BLM Templates and Data Augmentation Strategies},
                   booktitle = {Proceedings of the Fifteenth Language Resources and Evaluation Conference (LREC 2026)},
                        year = {2026},
                         doi = {10.63317/4t48qjruy2ce},
                    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.},
                         pdf = {https://publications.idiap.ch/attachments/papers/2026/Samo_LREC2026_2026.pdf}
}