A learned per-example router over a 105-perturbation audio library improves contrastive decoding for audio-LLM hallucination, with task-dependent best distortions (e.g., reverse audio for temporal order).
Reducing object hallucination in large audio-language models via audio-aware decoding
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 5roles
background 1polarities
background 1representative citing papers
LIME reduces hallucinations in multimodal LLMs by using LRP to boost perceptual modality contributions through inference-time KV updates.
ASPIRin decouples speaking timing from token content via binary action space projection and applies GRPO with rule-based rewards to optimize interactivity in SLMs without semantic collapse or repetition.
CAAD internalizes contrastive audio-aware decoding into student SLM weights via synchronized teacher-forcing, delivering an 8% relative gain over standard knowledge distillation on Dynamic-SUPERB while reducing linguistic bias on MCR-BENCH.
LLMs operate via learned probabilistic input-output mappings with only derived intentionality, so their outputs are not owned as commitments and sampling does not constitute choice or moral agency.
citing papers explorer
-
Adaptive Perturbation Selection for Contrastive Audio Decoding
A learned per-example router over a 105-perturbation audio library improves contrastive decoding for audio-LLM hallucination, with task-dependent best distortions (e.g., reverse audio for temporal order).
-
Mitigating Multimodal LLMs Hallucinations via Relevance Propagation at Inference Time
LIME reduces hallucinations in multimodal LLMs by using LRP to boost perceptual modality contributions through inference-time KV updates.
-
ASPIRin: Action Space Projection for Interactivity-Optimized Reinforcement Learning in Full-Duplex Speech Language Models
ASPIRin decouples speaking timing from token content via binary action space projection and applies GRPO with rule-based rewards to optimize interactivity in SLMs without semantic collapse or repetition.
-
CAAD: Contrastive Audio-Aware Distillation for Efficient Speech Language Models
CAAD internalizes contrastive audio-aware decoding into student SLM weights via synchronized teacher-forcing, delivering an 8% relative gain over standard knowledge distillation on Dynamic-SUPERB while reducing linguistic bias on MCR-BENCH.
-
Why Sampling Is Not Choosing: Intentionality, Agency, and Moral Responsibility in Large Language Models
LLMs operate via learned probabilistic input-output mappings with only derived intentionality, so their outputs are not owned as commitments and sampling does not constitute choice or moral agency.