Year: 2026
Type: conference-paper
Abstract: Language is a vehicle for thought, intricately tied to sounds, symbols, and meaning.However, most large language model (LLM) research focuses on meaning (semantics) and symbols (spelling) while largely overlooking sounds.Existing benchmarks on LLMs' phonological abilities are either solvable through rote memorization or intertwined with other abilities, making them inadequate to measure LLMs' genuine ability in phonological understanding.Here, we present Phun-Bench, a purpose-built Chinese benchmark with diverse tasks and settings across three dimensions (Homophony, Rhyme, and Phonetic Similarity), designed to systematically evaluate LLMs' phonological understanding.Our results show that while LLMs excel at recalling correct pronunciations, they generally struggle to leverage phonological knowledge in the flexible and intuitive way that human speakers do.Moreover, through detailed analyses, we propose a hypothesis regarding the underlying mechanism of LLMs' phonological understanding and "perception", highlighting an underexplored frontier for future research.1
Authors: Xing Yue, Yongliang Shen, Weiming Lu
Institution: Zhejiang University
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
Award: G7036249533
OpenAlex ID: W7166828239