When audio and text conflict, speech-enabled language models follow the text 10 times more often than when arbitrating between two text sources, even when explicitly instructed to trust the audio. Using ALME, a benchmark of 57,602 controlled audio-text conflict stimuli across 8 languages, we find that Gemini 2.0 Flash exhibits 16.6\% text dominance under audio-text conflict versus 1.6\% under text-text conflict with identical reliability cues. This gap is not explained by audio quality: audio-only accuracy (97.2\%) exceeds cascade accuracy (93.9\%), indicating audio embeddings preserve more information than text transcripts. We propose that text dominance reflects an asymmetry not in information content but in arbitration accessibility: how easily the model can reason over competing representations. This framework explains otherwise puzzling findings. Forcing transcription before answering increases text dominance (19\% to 33\%), sacrificing audio's information advantage without improving accessibility. Framing text as ``deliberately corrupted'' reduces text dominance by 80\%. A fine-tuning ablation provides interventional evidence: training only the audio projection layer increases text dominance (+26.5\%), while LoRA on the language model halves it ($-$23.9\%), localizing text dominance to the LLM's reasoning rather than the audio encoder. Experiments across four state-of-the-art audio-LLMs and 8 languages show consistent trends with substantial cross-linguistic and cross-model variation, establishing modality arbitration as a distinct reliability dimension not captured by standard speech benchmarks.

翻译：当音频与文本信息发生冲突时，具备语音功能的语言模型遵循文本的概率比仲裁两个文本源时高出十倍，即使模型被明确指示信任音频。通过ALME基准测试（包含8种语言共57,602个受控音频-文本冲突刺激），我们发现Gemini 2.0 Flash在音频-文本冲突下表现出16.6%的文本主导性，而在具有相同可靠性线索的文本-文本冲突中仅为1.6%。这种差异无法用音频质量解释：纯音频准确率（97.2%）超过级联系统准确率（93.9%），表明音频嵌入比文本转录保留更多信息。我们认为文本主导性反映的并非信息内容的不对称，而是仲裁可及性的不对称：即模型对竞争表征进行推理的难易程度。该框架解释了其他令人困惑的发现。强制在回答前进行转录会将文本主导性从19%提升至33%，这牺牲了音频的信息优势却未改善可及性。将文本标注为“故意篡改”可使文本主导性降低80%。微调消融实验提供了干预性证据：仅训练音频投影层会使文本主导性增加26.5%，而对语言模型进行LoRA微调可使其降低23.9%，这证明文本主导性定位于LLM的推理过程而非音频编码器。在四个最先进的音频-LLM和8种语言上的实验显示出一致的趋势，同时存在显著的跨语言和跨模型差异，从而确立模态仲裁作为标准语音基准未能捕捉的独立可靠性维度。