# Self-Improvement for Audio Large Language Model using Unlabeled Speech

arXiv: https://arxiv.org/abs/2507.20169 · HTML: https://mlsanity.com/paper/2507.20169/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Jul 2025.

## Built on by (most cited first, 10 of 10)

- [Self-Improvement in Multimodal Large Language Models: A Survey](https://mlsanity.com/paper/2510.02665/) (2025)
- [Advancing Speech Understanding in Speech-Aware Language Models with GRPO](https://mlsanity.com/paper/2509.16990/) (2025)
- [Audio-Zero: Label-Free Self-Evolution for Fine-Grained Audio Reasoning](https://mlsanity.com/paper/2607.20166/) (2026)
- [Learning to Decide with Just Enough: Information-Theoretic Context Summarization for CMDPs](https://mlsanity.com/paper/2510.01620/) (2025)
- [EvoAudio: Recursive Self-Improvement for Audio Understanding](https://mlsanity.com/paper/2609.27389/) (2026)
- [A Multimodal Deep Learning Framework for Early Diagnosis of Liver Cancer via Optimized BiLSTM-AM-VMD Architecture](https://mlsanity.com/paper/2509.01164/) (2025)
- [Bridging What the Model Thinks and How It Speaks: Expressive Speech Generation via Self-Aware Intent-Realization Alignment](https://mlsanity.com/paper/2604.11424/) (2026)
- [Long-Term Memory-Guided Enhancement for Target Perception in Audio-Language Models](https://mlsanity.com/paper/2609.36577/) (2026)
- [AdaLoop: Adaptive-Depth Latent Reasoning for Audio Language Models](https://mlsanity.com/paper/2610.06949/) (2026)
- [SkillFormer: Skill-Decomposed Adaptation for Audio Language Models](https://mlsanity.com/paper/2610.07533/) (2026)

## Abstract (arXiv)

Recent audio LLMs have emerged rapidly, demonstrating strong generalization across various speech tasks. However, given the inherent complexity of speech signals, these models inevitably suffer from performance degradation in specific target domains. To address this, we focus on enhancing audio LLMs in target domains without any labeled data. We propose a self-improvement method called SI-SDA, leveraging the information embedded in large-model decoding to evaluate the quality of generated pseudo labels and then perform domain adaptation based on reinforcement learning optimization. Experimental results show that our method consistently and significantly improves audio LLM performance, outperforming existing baselines in WER and BLEU across multiple public datasets of automatic speech recognition (ASR), spoken question-answering (SQA), and speech-to-text translation (S2TT). Furthermore, our approach exhibits high data efficiency, underscoring its potential for real-world deployment.