# Assessment of L2 Oral Proficiency using Speech Large Language Models

arXiv: https://arxiv.org/abs/2505.21148 · HTML: https://mlsanity.com/paper/2505.21148/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 32 references that are in the map.
- First posted on arXiv 27 May 2025.

## Builds on (most cited first, 15 of 15)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [Emergent Abilities of Large Language Models](https://mlsanity.com/paper/2206.07682/) (2022)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models](https://mlsanity.com/paper/2311.07919/) (2023)
- [Qwen2-Audio Technical Report](https://mlsanity.com/paper/2407.10759/) (2024)
- [SALMONN: Towards Generic Hearing Abilities for Large Language Models](https://mlsanity.com/paper/2310.13289/) (2023)
- [Automatic Pronunciation Assessment using Self-Supervised Speech Representation Learning](https://mlsanity.com/paper/2204.03863/) (2022)
- [Proficiency assessment of L2 spoken English using wav2vec 2.0](https://mlsanity.com/paper/2210.13168/) (2022)
- [Can GPT-4 do L2 analytic assessment?](https://mlsanity.com/paper/2404.18557/) (2024)
- [Speak & Improve Corpus 2025: an L2 English Speech Corpus for Language Assessment and Feedback](https://mlsanity.com/paper/2412.11986/) (2024)
- [Speak & Improve Challenge 2025: Tasks and Baseline Systems](https://mlsanity.com/paper/2412.11985/) (2024)
- [Mitigating Word Bias in Zero-shot Prompt-based Classifiers](https://mlsanity.com/paper/2309.04992/) (2023)
- [Pronunciation Assessment with Multi-modal Large Language Models](https://mlsanity.com/paper/2407.09209/) (2024)

## Built on by (most cited first, 14 of 14)

- [Opportunities and Challenges of LLMs in Education: An NLP Perspective](https://mlsanity.com/paper/2507.22753/) (2025)
- [Bias in the Ear of the Listener: Assessing Sensitivity in Audio Language Models Across Linguistic, Demographic, and Positional Variations](https://mlsanity.com/paper/2602.01030/) (2026)
- [Session-Level Spoken Language Assessment with a Multimodal Foundation Model via Multi-Target Learning](https://mlsanity.com/paper/2509.16025/) (2025)
- [Zero-Shot Speech LLMs for Multi-Aspect Evaluation of L2 Speech: Challenges and Opportunities](https://mlsanity.com/paper/2601.16230/) (2026)
- [Fine-Tuning Large Multimodal Models for Automatic Pronunciation Assessment](https://mlsanity.com/paper/2509.15701/) (2025)
- [A Finetuned SpeechLLM for Joint Multi-Granular L2 Assessment and Natural-Language Rationales](https://mlsanity.com/paper/2606.09470/) (2026)
- [Towards Self-Referential Analytic Assessment: A Profile-Based Approach to L2 Writing Evaluation with LLMs](https://mlsanity.com/paper/2605.04298/) (2026)
- [Prior over Evidence: Stereotype-Driven Diagnosis in LLM-Based L2 Pronunciation Feedback](https://mlsanity.com/paper/2606.15325/) (2026)
- [A Survey of Automated Presentation Coaching: Systems, Methods, and Open Challenges](https://mlsanity.com/paper/2606.27380/) (2026)
- [LOPA: Enhancing Spoken Language Assessment via Latent Ordinal Prototype Alignment](https://mlsanity.com/paper/2606.31310/) (2026)
- [Controlling Implicit Shortcut Reliance in L2 Spoken English Auto-markers](https://mlsanity.com/paper/2607.16085/) (2026)
- [Bias Analysis of L2 Speaking Assessment Systems Using Concept Activation Vectors](https://mlsanity.com/paper/2608.06300/) (2026)
- [CASA: Content-Acoustic Speaking Assessment with Speech Encoder and Large Language Model](https://mlsanity.com/paper/2608.13101/) (2026)
- [Interpretable, Fairly Evaluated Automated L2 Speaking Assessment that Beats the Single-Human Ceiling and Why Pause Encoding Does Not Change LLM Fluency Scores](https://mlsanity.com/paper/2608.26137/) (2026)

## Abstract (arXiv)

The growing population of L2 English speakers has increased the demand for developing automatic graders for spoken language assessment (SLA). Historically, statistical models, text encoders, and self-supervised speech models have been utilised for this task. However, cascaded systems suffer from the loss of information, while E2E graders also have limitations. With the recent advancements of multi-modal large language models (LLMs), we aim to explore their potential as L2 oral proficiency graders and overcome these issues. In this work, we compare various training strategies using regression and classification targets. Our results show that speech LLMs outperform all previous competitive baselines, achieving superior performance on two datasets. Furthermore, the trained grader demonstrates strong generalisation capabilities in the cross-part or cross-task evaluation, facilitated by the audio understanding knowledge acquired during LLM pre-training.