{"ID":5438718,"CreatedAt":"2026-07-01T01:17:58.482524686Z","UpdatedAt":"2026-07-03T07:34:59.203171219Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.31310","arxiv_id":"2606.31310","title":"LOPA: Enhancing Spoken Language Assessment via Latent Ordinal Prototype Alignment","abstract":"Fueled by increasing model scale and multimodal inputs, Multimodal Large Language Models (MLLMs) have emerged as a promising paradigm for Spoken Language Assessment (SLA). While effective, this paradigm often overlooks the intrinsic ordinal structure of language acquisition. This paper works around the necessity of large-scale MLLMs by introducing Latent Ordinal Prototype Alignment (LOPA) for SLA, a prototype-based regularizer that enforces an ordinal geometric prior directly on the latent space. Coupled with Semantic-Anchored Layer Routing (SALR), which adaptively harvests multi-depth representations from a frozen Whisper encoder, our framework achieves an RMSE of 0.361. This performance rivals billion-parameter systems without the need for LLM-based fine-tuning. Further analysis reveals that SALR's synergy with LOPA offers interpretable, criterion-aligned preferences, thereby supporting an efficient and ordinal-aware modeling alternative to current scaling-centric models for SLA.","short_abstract":"Fueled by increasing model scale and multimodal inputs, Multimodal Large Language Models (MLLMs) have emerged as a promising paradigm for Spoken Language Assessment (SLA). While effective, this paradigm often overlooks the intrinsic ordinal structure of language acquisition. This paper works around the necessity of lar...","url_abs":"https://arxiv.org/abs/2606.31310","url_pdf":"https://arxiv.org/pdf/2606.31310v1","authors":"[\"Hong-Yun Lin\",\"Fu-An Chao\",\"Bi-Cheng Yan\",\"Berlin Chen\"]","published":"2026-06-30T08:19:32Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.MM\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}