Showing cs.SDShow all
3 papers · 1 filter
cs.SD2026
Hallucination Reduction for LLM-Based Audio Understanding via Multimodal Direct Preference Optimization
Bebe Cosgrove, Aaron Isidore Grace, Weiran Wang
Large Audio Language Models (LALMs) are prone to hallucinating and over-relying on text priors when simultaneously presented with audio and text inputs. To mitigate these hallucina…
cs.SD2026
Broadening Uncertainty Estimation for Audio Question Answering Across Methods, Formats, and Inputs
Aaron Isidore Grace, Weiran Wang
Audio-language models can produce confident answers unsupported by the audio, motivating uncertainty estimates that identify unreliable responses. We compare probability-based, sam…
cs.SD2026
Adaptive Perturbation Selection for Contrastive Audio Decoding
Aaron Isidore Grace, Zhouyuan Huo, Weiran Wang
Large audio-language models (LALMs) frequently hallucinate by overriding acoustic evidence with language priors. While contrastive decoding (CD) offers training-free mitigation, ex…