Image de couverture de livre

Causal Tracing of Audio-Text Fusion in Large Audio Language Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Chen, Wei-Chih, Huang, Chien-yu, Lee, Hung-yi
Format:	Preprint
Publié:	2026
Sujets:	Sound Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

When Silence Matters: The Impact of Irrelevant Audio on Text Reasoning in Large Audio-Language Models
par: Li, Chen-An, et autres
Publié: (2025)

SAKURA: On the Multi-hop Reasoning of Large Audio-Language Models Based on Speech and Audio Information
par: Yang, Chih-Kai, et autres
Publié: (2025)

AudioLens: A Closer Look at Auditory Attribute Perception of Large Audio-Language Models
par: Yang, Chih-Kai, et autres
Publié: (2025)

MI-Fuse: Label Fusion for Unsupervised Domain Adaptation with Closed-Source Large-Audio Language Model
par: Huang, Hsiao-Ying, et autres
Publié: (2025)

All That Glitters Is Not Audio: Rethinking Text Priors and Audio Reliance in Audio-Language Evaluation
par: Foo, Leonardo Haw-Yang, et autres
Publié: (2026)

Towards Holistic Evaluation of Large Audio-Language Models: A Comprehensive Survey
par: Yang, Chih-Kai, et autres
Publié: (2025)

Can Large Audio-Language Models Truly Hear? Tackling Hallucinations with Multi-Task Assessment and Stepwise Audio Reasoning
par: Kuan, Chun-Yi, et autres
Publié: (2024)

Hearing the Order: Investigating Position Bias in Large Audio-Language Models
par: Lin, Yu-Xiang, et autres
Publié: (2025)

How Contrastive Decoding Enhances Large Audio Language Models?
par: Lin, Tzu-Quan, et autres
Publié: (2026)

Nudging Hidden States: Training-Free Model Steering for Chain-of-Thought Reasoning in Large Audio-Language Models
par: Ieong, Lok-Lam, et autres
Publié: (2026)

Understanding Sounds, Missing the Questions: The Challenge of Object Hallucination in Large Audio-Language Models
par: Kuan, Chun-Yi, et autres
Publié: (2024)

Teaching Audio-Aware Large Language Models What Does Not Hear: Mitigating Hallucinations through Synthesized Negative Samples
par: Kuan, Chun-Yi, et autres
Publié: (2025)

Walking Through Uncertainty: An Empirical Study of Uncertainty Estimation for Audio-Aware Large Language Models
par: Kuan, Chun-Yi, et autres
Publié: (2026)

AQAScore: Evaluating Semantic Alignment in Text-to-Audio Generation via Audio Question Answering
par: Kuan, Chun-Yi, et autres
Publié: (2026)

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

VIBE: Voice-Induced open-ended Bias Evaluation for Large Audio-Language Models via Real-World Speech
par: Lin, Yi-Cheng, et autres
Publié: (2026)

TASTE-Streaming: Towards Streamable Text-Aligned Speech Tokenization and Embedding for Spoken Language Modeling
par: Tseng, Liang-Hsuan, et autres
Publié: (2026)

A Preliminary Exploration with GPT-4o Voice Mode
par: Lin, Yu-Xiang, et autres
Publié: (2025)

MUGEN: Evaluating and Improving Multi-audio Understanding of Large Audio-Language Models
par: Yang, Chih-Kai, et autres
Publié: (2026)

Investigating Safety Vulnerabilities of Large Audio-Language Models Under Speaker Emotional Variations
par: Feng, Bo-Han, et autres
Publié: (2025)

From Alignment to Advancement: Bootstrapping Audio-Language Alignment with Synthetic Data
par: Kuan, Chun-Yi, et autres
Publié: (2025)

SAKE: Towards Editing Auditory Attribute Knowledge of Large Audio-Language Models
par: Yang, Chih-Kai, et autres
Publié: (2025)

Words at Play: Benchmarking Audio Pun Understanding in Large Audio-Language Models
par: Su, Yuchen, et autres
Publié: (2026)

Audio Jailbreaks in Large Audio-Language Models: Taxonomy, Attack-Defense Analysis, and Cost-Aware Evaluation
par: Feng, Bo-Han, et autres
Publié: (2026)

Omni-Embed-Audio: Leveraging Multimodal LLMs for Robust Audio-Text Retrieval
par: Yoo, HaeJun, et autres
Publié: (2026)

Thinking with Sound: Audio Chain-of-Thought Enables Multimodal Reasoning in Large Audio-Language Models
par: Xiong, Zhen, et autres
Publié: (2025)

SonicBench: Dissecting the Physical Perception Bottleneck in Large Audio Language Models
par: Sun, Yirong, et autres
Publié: (2026)

Speech-Copilot: Leveraging Large Language Models for Speech Processing via Task Decomposition, Modularization, and Program Generation
par: Kuan, Chun-Yi, et autres
Publié: (2024)

AQUA-Bench: Beyond Finding Answers to Knowing When There Are None in Audio Question Answering
par: Kuan, Chun-Yi, et autres
Publié: (2026)

Revealing the Role of Audio Channels in ASR Performance Degradation
par: Huang, Kuan-Tang, et autres
Publié: (2025)

HeadRouter: Dynamic Head-Weight Routing for Task-Adaptive Audio Token Pruning in Large Audio Language Models
par: He, Peize, et autres
Publié: (2026)

AudioBench: A Universal Benchmark for Audio Large Language Models
par: Wang, Bin, et autres
Publié: (2024)

How Auditory Knowledge in LLM Backbones Shapes Audio Language Models: A Holistic Evaluation
par: Lu, Ke-Han, et autres
Publié: (2026)

ToxicTone: A Mandarin Audio Dataset Annotated for Toxicity and Toxic Utterance Tonality
par: Luo, Yu-Xiang, et autres
Publié: (2025)

Audio-CoT: Exploring Chain-of-Thought Reasoning in Large Audio Language Model
par: Ma, Ziyang, et autres
Publié: (2025)

Style Amnesia: Investigating Speaking Style Degradation and Mitigation in Multi-Turn Spoken Language Models
par: Lin, Yu-Xiang, et autres
Publié: (2025)

LLM-Codec: Neural Audio Codec Meets Language Model Objectives
par: Chung, Ho-Lam, et autres
Publié: (2026)

Step-Audio-AQAA: a Fully End-to-End Expressive Large Audio Language Model
par: Huang, Ailin, et autres
Publié: (2025)

Bagpiper: Solving Open-Ended Audio Tasks via Rich Captions
par: Tian, Jinchuan, et autres
Publié: (2026)

Do Prompts Really Prompt? Exploring the Prompt Understanding Capability of Whisper
par: Yang, Chih-Kai, et autres
Publié: (2024)