Beyond Co-existence: Measuring Attribute Binding Hallucinations in Audio-Language Models
- 3 August 2026
- book chapter
- Published by Springer Nature
- p. 383-396
Abstract
No abstract availableKeywords
This publication has 23 references indexed in Scilit:
- Stable Audio Open2025
- Can Large Audio-Language Models Truly Hear? Tackling Hallucinations with Multi-Task Assessment and Stepwise Audio Reasoning2025
- Hallusionbench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language Models2024
- Detecting and Preventing Hallucinations in Large Vision Language ModelsProceedings of the AAAI Conference on Artificial Intelligence, 2024
- CLAP Learning Audio Concepts from Natural Language Supervision2023
- Large-Scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation2023
- Evaluating Object Hallucination in Large Vision-Language Models2023
- FSD50K: An Open Dataset of Human-Labeled Sound EventsIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2021
- Clotho: an Audio Captioning Dataset2020
- CIDEr: Consensus-based image description evaluation2015