arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2603.09232cs.SDcs.CLeess.AS
收藏

对比解码如何增强大型音频语言模型?

How Contrastive Decoding Enhances Large Audio Language Models

Tzu-Quan Lin, Wei-Ping Huang, Yi-Cheng Lin, Hung-yi Lee

AI总结:

本研究通过对比解码策略评估,发现音频感知解码和音频对比解码在不同模型中效果各异,揭示了CD在纠正特定错误类型上的有效性及局限性。

摘要:

尽管对比解码(CD)已被证明在增强大型音频语言模型(LALMs)方面非常有效,但驱动其成功的核心机制以及不同策略的相对有效性仍不明确。本研究系统评估了四种不同的CD策略,适用于多样化的LALM架构。我们发现音频感知解码和音频对比解码是效果最好的方法。然而,其影响因模型而异。为了解释这种差异性,我们引入了过渡矩阵框架,用于映射推理过程中错误模式的转移。我们的分析表明,CD能够可靠地纠正那些模型错误地声称不存在音频或依赖不确定性驱动猜测的错误。相反,它无法纠正错误推理或自信的错误断言。最终,这些发现为根据基线错误配置确定最适合CD增强的LALM架构提供了清晰的指导。

英文摘要:

While Contrastive Decoding (CD) has been proposed to enhance Large Audio Language Models (LALMs), it has not been evaluated at scale, and the underlying mechanisms driving its success remain unclear. This study systematically evaluates four distinct CD strategies across diverse LALM architectures. We identify Audio-Aware Decoding and Audio Contrastive Decoding as the most effective methods. However, their impact varies significantly across models. To explain this variability, we profile the baseline error composition of each model and measure how readily contrastive decoding corrects each error type. Our analysis demonstrates that CD reliably rectifies errors in which models falsely claim an absence of audio or resort to uncertainty-driven guessing, but is relatively poor at correcting flawed reasoning or confident misassertions. Crucially, CD's benefit closely tracks the composition of a model's baseline error profile: when errors caused by audio ignorance or uncertainty-driven guessing constitute only a small fraction of a model's errors, gains are marginal or even negative. A token-level analysis reveals the underlying mechanism: when the amateur's output is dominated by hesitation markers, CD's suppression naturally targets uncertainty-driven errors while having limited effect on confident misassertions.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑