SoundMind: RL-Incentivized Logic Reasoning for Audio-Language Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911164508667904 |
|---|---|
| author | Diao, Xingjian Zhang, Chunhui Kong, Keyi Wu, Weiyi Ma, Chiyu Ouyang, Zhongyu Qing, Peijun Vosoughi, Soroush Gui, Jiang |
| author_facet | Diao, Xingjian Zhang, Chunhui Kong, Keyi Wu, Weiyi Ma, Chiyu Ouyang, Zhongyu Qing, Peijun Vosoughi, Soroush Gui, Jiang |
| contents | While large language models have demonstrated impressive reasoning abilities, their extension to the audio modality, particularly within large audio-language models (LALMs), remains underexplored. Addressing this gap requires a systematic approach that involves a capable base model, high-quality reasoning-oriented audio data, and effective training algorithms. In this work, we present a comprehensive solution for audio logical reasoning (ALR) tasks: we introduce SoundMind, a dataset of 6,446 audio-text annotated samples specifically curated to support complex reasoning. Building on this resource, we propose SoundMind-RL, a rule-based reinforcement learning (RL) algorithm designed to equip audio-language models with robust audio-text reasoning capabilities. By fine-tuning Qwen2.5-Omni-7B on the proposed SoundMind dataset using SoundMind-RL, we achieve strong and consistent improvements over state-of-the-art baselines on the SoundMind benchmark. This work highlights the benefit of combining high-quality, reasoning-focused datasets with specialized RL techniques, and contributes to advancing auditory intelligence in language models. The code and dataset introduced in this work are publicly available at https://github.com/xid32/SoundMind. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_12935 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SoundMind: RL-Incentivized Logic Reasoning for Audio-Language Models Diao, Xingjian Zhang, Chunhui Kong, Keyi Wu, Weiyi Ma, Chiyu Ouyang, Zhongyu Qing, Peijun Vosoughi, Soroush Gui, Jiang Computation and Language Multimedia Sound Audio and Speech Processing While large language models have demonstrated impressive reasoning abilities, their extension to the audio modality, particularly within large audio-language models (LALMs), remains underexplored. Addressing this gap requires a systematic approach that involves a capable base model, high-quality reasoning-oriented audio data, and effective training algorithms. In this work, we present a comprehensive solution for audio logical reasoning (ALR) tasks: we introduce SoundMind, a dataset of 6,446 audio-text annotated samples specifically curated to support complex reasoning. Building on this resource, we propose SoundMind-RL, a rule-based reinforcement learning (RL) algorithm designed to equip audio-language models with robust audio-text reasoning capabilities. By fine-tuning Qwen2.5-Omni-7B on the proposed SoundMind dataset using SoundMind-RL, we achieve strong and consistent improvements over state-of-the-art baselines on the SoundMind benchmark. This work highlights the benefit of combining high-quality, reasoning-focused datasets with specialized RL techniques, and contributes to advancing auditory intelligence in language models. The code and dataset introduced in this work are publicly available at https://github.com/xid32/SoundMind. |
| title | SoundMind: RL-Incentivized Logic Reasoning for Audio-Language Models |
| topic | Computation and Language Multimedia Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2506.12935 |