发表机构
Tencent Hunyuan; Zhejiang University（腾讯混元; 浙江大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对大型音频-语言模型逻辑推理能力不足，提出X³-OPD跨模态策略蒸馏框架，借助教师模型指导与构建的三层对称语料库训练学生模型，实验证明该方法能提升音频推理及思维链质量，还能保留模型域转移下的能力。
AI 中文摘要
虽然大型音频-语言模型在听觉感知方面取得了显著进展，但在深度逻辑推理方面仍落后于基于文本的大型语言模型，主要原因是高质量音频推理数据稀缺。为弥合这一差距，我们提出了X³-OPD，这是一个跨模态策略蒸馏框架，将推理能力从强大的文本教师模型转移到音频-语言学生模型。训练期间，学生模型根据自身声学感知生成推理轨迹，教师模型使用匹配的文本输入和验证答案提供令牌级指导。我们还构建了一个三层对称语料库。实验表明，X³-OPD显著提高了基于音频的推理和思维链质量，同时在很大程度上保留了模型在域转移下的现有能力。
英文摘要
While large audio-language models have achieved remarkable progress in auditory perception, they still lag behind text-based large language models in deep logical reasoning, primarily due to the scarcity of high-quality audio reasoning data. To bridge this gap, we propose X$^3$-OPD, a cross-modal on-policy distillation framework that transfers reasoning capabilities from a powerful text teacher to an audio-language student. During training, the student generates reasoning trajectories conditioned on its own acoustic perception, while the teacher provides token-level guidance using matched textual inputs and verified answers. We further construct a three-tier symmetric corpus covering textual reasoning rendered into speech, audio-event reasoning grounded in complex acoustic scenes, and spoken-dialogue reasoning involving paralinguistic cues. This design extends cross-modal distillation beyond textually recoverable content to reasoning grounded in non-linguistic events, prosody, and conversational context. Experiments on MMSU, MMAU, BIG Bench Audio, and MMAR demonstrate that X$^3$-OPD substantially improves audio-grounded reasoning and chain-of-thought quality while largely preserving the model's existing capabilities under domain shift.
