Audio-Language Models Suppress Clear Audio Evidence

Researchers have identified a significant issue in audio-language models where conflicting text inputs override clear audio evidence, leading to incorrect outputs. A study found that in over 64% of conflict cases, the model's preference shifted to favor the audio when text was removed, indicating the audio information was present but suppressed. To address this, a new decoding rule called Gated Audio Counterfactual Logit Correction (GACL) was developed, which improves model faithfulness and can be applied without retraining. AI

影响 Highlights a critical flaw in current audio-language models, potentially impacting their reliability in real-world applications and guiding future research.

排序理由 The cluster contains an academic paper detailing a new finding about the behavior of audio-language models and proposing a method to correct it. [lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CL 阅读 →

• Audio-Language Models
• Gated Audio Counterfactual Logit Correction

• 论文
• 模型发布

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →