LOPA: Enhancing Spoken Language Assessment via Latent Ordinal Prototype Alignment

Hong-Yun Lin Fu-An Chao Bi-Cheng Yan Berlin Chen

Jun 2026 · arXiv.org · Vol abs/2606.31310 · 0 citations · 21 references

Computer Science

TL;DR

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.

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.

DOI arXiv Semantic Scholar

View source

Similar papers

Preprint Jul 2026

Alignment Is All You Need: Instruction-Free Training for General Audio-Language Models

The results suggest that competitive MLLM can emerge from alignment alone, reducing multimodal extension to a lightweight projector-training problem that generalizes across modalities and adapts rapidly to each new LLM release.

Xuanru Zhou, Yiwen Shao, Jiahong Li et al. · 1 citation

Jul 2026

LLM-Based Generative Retrieval for Snapchat Content Recommendation

The design and launch of SnapLGR, an LLM-based generative retrieval system for short-video recommendation at Snapchat shows that successful production SnapLGR requires joint design across representation learning, vocabulary grounding, and efficient training and serving.

Liam Collins, Jiwen Ren, Donald Loveland et al. · arXiv.org · 0 citations

Aug 2026

GLA-LoRA: Parameter-efficient LLM fine-tuning with global-local knowledge alignment.

GLA-LoRA establishes a unified learning strategy that synergistically integrates multi-granular contrastive learning with knowledge distillation and establishes that explicit global-local knowledge alignment is essential for achieving high-fidelity, parameter-efficient fine-tuning across diverse language tasks.

Hao Wu, Jian-Qi Gao, Xiangfeng Luo · Neural Networks · 0 citations

Preprint Aug 2026

Towards More Expressive Spoken LLMs: Fine-Grained Intent Benchmarking and Acoustic-Lexical Decoupled Policy Optimization

ParaIntent is introduced, a Chinese benchmark comprising 14 intent categories with balanced explicit and implicit samples, together with a multidimensional evaluation protocol covering intent fulfillment, response quality, and emotional expression, which improves over standard GRPO on most automatic metrics and achieve...

Xiangning Lin, Tian-Hao Zhang, Chunfeng Wang et al. · 1 citation

Preprint Jul 2026

Progressive Multimodal Alignment for Continual Instruction Tuning

This work introduces Progressive Multimodal Alignment (PMA), a framework that enables the projector to adapt continually while preserving previously learned alignment, and scales across diverse MLLM backbones, demonstrating robust and broadly applicable MCIT performance.

Duzhen Zhang, Yahan Yu, Qiaoyi Su et al. · 0 citations

Preprint Aug 2026

Interpreting Language Model Hidden States at Scale

OmniLens is presented, which applies a single lens family to any model-width activation, whether residual stream, attention, or MLP, and combines two independent scaling techniques, which reproduces key published results at substantially lower cost.

Jordan Pettyjohn, Mansi Sakarvadia, Nathaniel Hudson et al. · 0 citations