Buchumschlag

Can Large Audio-Language Models Truly Hear? Tackling Hallucinations with Multi-Task Assessment and Stepwise Audio Reasoning

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Kuan, Chun-Yi, Lee, Hung-yi
Format:	Preprint
Veröffentlicht:	2024
Schlagworte:	Audio and Speech Processing Computation and Language Sound
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

Teaching Audio-Aware Large Language Models What Does Not Hear: Mitigating Hallucinations through Synthesized Negative Samples
von: Kuan, Chun-Yi, et al.
Veröffentlicht: (2025)

Understanding Sounds, Missing the Questions: The Challenge of Object Hallucination in Large Audio-Language Models
von: Kuan, Chun-Yi, et al.
Veröffentlicht: (2024)

SAKURA: On the Multi-hop Reasoning of Large Audio-Language Models Based on Speech and Audio Information
von: Yang, Chih-Kai, et al.
Veröffentlicht: (2025)

From Alignment to Advancement: Bootstrapping Audio-Language Alignment with Synthetic Data
von: Kuan, Chun-Yi, et al.
Veröffentlicht: (2025)

How Contrastive Decoding Enhances Large Audio Language Models?
von: Lin, Tzu-Quan, et al.
Veröffentlicht: (2026)

Walking Through Uncertainty: An Empirical Study of Uncertainty Estimation for Audio-Aware Large Language Models
von: Kuan, Chun-Yi, et al.
Veröffentlicht: (2026)

MI-Fuse: Label Fusion for Unsupervised Domain Adaptation with Closed-Source Large-Audio Language Model
von: Huang, Hsiao-Ying, et al.
Veröffentlicht: (2025)

AQUA-Bench: Beyond Finding Answers to Knowing When There Are None in Audio Question Answering
von: Kuan, Chun-Yi, et al.
Veröffentlicht: (2026)

AudioLens: A Closer Look at Auditory Attribute Perception of Large Audio-Language Models
von: Yang, Chih-Kai, et al.
Veröffentlicht: (2025)

AQAScore: Evaluating Semantic Alignment in Text-to-Audio Generation via Audio Question Answering
von: Kuan, Chun-Yi, et al.
Veröffentlicht: (2026)

VIBE: Voice-Induced open-ended Bias Evaluation for Large Audio-Language Models via Real-World Speech
von: Lin, Yi-Cheng, et al.
Veröffentlicht: (2026)

Speech-Copilot: Leveraging Large Language Models for Speech Processing via Task Decomposition, Modularization, and Program Generation
von: Kuan, Chun-Yi, et al.
Veröffentlicht: (2024)

Towards Holistic Evaluation of Large Audio-Language Models: A Comprehensive Survey
von: Yang, Chih-Kai, et al.
Veröffentlicht: (2025)

DeSTA2.5-Audio: Toward General-Purpose Large Audio Language Model with Self-Generated Cross-Modal Alignment
von: Lu, Ke-Han, et al.
Veröffentlicht: (2025)

All That Glitters Is Not Audio: Rethinking Text Priors and Audio Reliance in Audio-Language Evaluation
von: Foo, Leonardo Haw-Yang, et al.
Veröffentlicht: (2026)

Nudging Hidden States: Training-Free Model Steering for Chain-of-Thought Reasoning in Large Audio-Language Models
von: Ieong, Lok-Lam, et al.
Veröffentlicht: (2026)

MUGEN: Evaluating and Improving Multi-audio Understanding of Large Audio-Language Models
von: Yang, Chih-Kai, et al.
Veröffentlicht: (2026)

TASTE: Text-Aligned Speech Tokenization and Embedding for Spoken Language Modeling
von: Tseng, Liang-Hsuan, et al.
Veröffentlicht: (2025)

Audio Large Language Models Can Be Descriptive Speech Quality Evaluators
von: Chen, Chen, et al.
Veröffentlicht: (2025)

Audio-CoT: Exploring Chain-of-Thought Reasoning in Large Audio Language Model
von: Ma, Ziyang, et al.
Veröffentlicht: (2025)

Reducing Object Hallucination in Large Audio-Language Models via Audio-Aware Decoding
von: Hsu, Tzu-wen, et al.
Veröffentlicht: (2025)

CodecFake: Enhancing Anti-Spoofing Models Against Deepfake Audios from Codec-Based Speech Synthesis Systems
von: Wu, Haibin, et al.
Veröffentlicht: (2024)

AudioBench: A Universal Benchmark for Audio Large Language Models
von: Wang, Bin, et al.
Veröffentlicht: (2024)

ALLM4ADD: Unlocking the Capabilities of Audio Large Language Models for Audio Deepfake Detection
von: Gu, Hao, et al.
Veröffentlicht: (2025)

Pengi: An Audio Language Model for Audio Tasks
von: Deshmukh, Soham, et al.
Veröffentlicht: (2023)

Enhancing Temporal Understanding in Audio Question Answering for Large Audio Language Models
von: Sridhar, Arvind Krishna, et al.
Veröffentlicht: (2024)

Enhancing Automated Audio Captioning via Large Language Models with Optimized Audio Encoding
von: Liu, Jizhong, et al.
Veröffentlicht: (2024)

Can Large Language Models Understand Spatial Audio?
von: Tang, Changli, et al.
Veröffentlicht: (2024)

Zero Resource Code-switched Speech Benchmark Using Speech Utterance Pairs For Multiple Spoken Languages
von: Huang, Kuan-Po, et al.
Veröffentlicht: (2023)

Step-Audio-AQAA: a Fully End-to-End Expressive Large Audio Language Model
von: Huang, Ailin, et al.
Veröffentlicht: (2025)

Do Prompts Really Prompt? Exploring the Prompt Understanding Capability of Whisper
von: Yang, Chih-Kai, et al.
Veröffentlicht: (2024)

HEAR: Hearing Enhanced Audio Response for Video-grounded Dialogue
von: Yoon, Sunjae, et al.
Veröffentlicht: (2023)

PAM: Prompting Audio-Language Models for Audio Quality Assessment
von: Deshmukh, Soham, et al.
Veröffentlicht: (2024)

How Auditory Knowledge in LLM Backbones Shapes Audio Language Models: A Holistic Evaluation
von: Lu, Ke-Han, et al.
Veröffentlicht: (2026)

MiMo-Audio: Audio Language Models are Few-Shot Learners
von: Core Team, et al.
Veröffentlicht: (2025)

Can Audio Large Language Models Verify Speaker Identity?
von: Ren, Yiming, et al.
Veröffentlicht: (2025)

On the Audio Hallucinations in Large Audio-Video Language Models
von: Nishimura, Taichi, et al.
Veröffentlicht: (2024)

UniAudio 1.5: Large Language Model-driven Audio Codec is A Few-shot Audio Task Learner
von: Yang, Dongchao, et al.
Veröffentlicht: (2024)

SMILE: Speech Meta In-Context Learning for Low-Resource Language Automatic Speech Recognition
von: Hsu, Ming-Hao, et al.
Veröffentlicht: (2024)

ToxicTone: A Mandarin Audio Dataset Annotated for Toxicity and Toxic Utterance Tonality
von: Luo, Yu-Xiang, et al.
Veröffentlicht: (2025)