CLAIJun 13

PACUTE: Phonology-, Affix-, and Character-level Understanding of Tokens for Filipino

arXiv:2606.1514419.0
Predicted impact top 45% in CL · last 90 daysOriginality Incremental advance
AI Analysis

For NLP researchers working on morphologically rich languages, this benchmark reveals that current LLMs struggle with productive morphological composition beyond character access.

PACUTE is a diagnostic benchmark of 4,600 tasks evaluating morphological understanding in Filipino. Open-weight LLMs perform near chance on morpheme decomposition, while frontier models recover affixes but remain far below character-level ceilings on compositional tasks, identifying productive morphological composition as the persistent bottleneck.

Large language models (LLMs) process text as sequences of subword tokens, which can obscure the character-level and morphological structure that underlies word formation. This limitation is most acute for languages with non-concatenative morphology, where standard tokenizers systematically misalign token boundaries with morpheme boundaries. We introduce PACUTE, a diagnostic benchmark of 4,600 tasks designed to evaluate morphological understanding in Filipino, a language characterized by productive infixation, reduplication, and diacritic-driven lexical distinctions that are typically absent from written text. PACUTE includes a hierarchical diagnostic framework of six compositional levels that localizes where morphological understanding breaks down. Evaluating open-weight LLMs and frontier commercial models, we find that open-weight models perform near chance on morpheme decomposition regardless of scale. Frontier models perform much better, often recovering individual affixes under contains-match scoring, but remain far below their character-level ceilings on compositional tasks of morpheme transformations and syllabification. These results identify productive morphological composition, rather than character access alone, as the persistent bottleneck for Filipino word-structure understanding.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes