Adaptive Perturbation Selection for Contrastive Audio Decoding
Quick summary
arXiv:2607.00247v3 Announce Type: replace-cross Abstract: Large audio-language models (LALMs) frequently hallucinate by overriding acoustic evidence with language priors. While contrastive decoding (CD) offers training-free mitigation, existing methods rely on blunt perturbations like masking or noise, leaving structured audio transformations unexplored. We explore this design space by evaluating a diverse library of targeted audio perturbations and adaptively selecting the optimal negative branch for each task and example. First, we improve upon earlier prompt engineering by showing that a si
Key takeaways
- arXiv:2607.00247v3 Announce Type: replace-cross Abstract: Large audio-language models (LALMs) frequently hallucinate by overriding acoustic evidence with language priors.
- While contrastive decoding (CD) offers training-free mitigation, existing methods rely on blunt perturbations like masking or noise, leaving structured audio transformations unexplored.
- We explore this design space by evaluating a diverse library of targeted audio perturbations and adaptively selecting the optimal negative branch for each task and example.
Why it matters
“Adaptive Perturbation Selection for Contrastive Audio Decoding” illustrates how changes in the AI ecosystem can affect products, workflows and user expectations together. Its lasting significance depends on measurable adoption, cost and safety outcomes.
Member comments