Cover Image

Adaptive vector steering: A training-free, layer-wise intervention for hallucination mitigation in large audio and multimodal models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Lin, Tsung-En, Lee, Kuan-Yi, Lee, Hung-Yi
Format:	Preprint
Published:	2025
Subjects:	Sound Machine Learning Audio and Speech Processing
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Towards audio language modeling -- an overview
by: Wu, Haibin, et al.
Published: (2024)

Codec-SUPERB @ SLT 2024: A lightweight benchmark for neural audio codec models
by: Wu, Haibin, et al.
Published: (2024)

ACAVCaps: Enabling large-scale training for fine-grained and diverse audio understanding
by: Niu, Yadong, et al.
Published: (2026)

Can Large Audio-Language Models Truly Hear? Tackling Hallucinations with Multi-Task Assessment and Stepwise Audio Reasoning
by: Kuan, Chun-Yi, et al.
Published: (2024)

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

EDTC: enhance depth of text comprehension in automated audio captioning
by: Tan, Liwen, et al.
Published: (2024)

DashengTokenizer: One layer is enough for unified audio understanding and generation
by: Dinkel, Heinrich, et al.
Published: (2026)

Toward Fair Speech Technologies: A Comprehensive Survey of Bias and Fairness in Speech AI
by: Lin, Yi-Cheng, et al.
Published: (2026)

FxSearcher: gradient-free text-driven audio transformation
by: Ki, Hojoon, et al.
Published: (2025)

Are audio DeepFake detection models polyglots?
by: Marek, Bartłomiej, et al.
Published: (2024)

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

Music De-limiter Networks via Sample-wise Gain Inversion
by: Jeon, Chang-Bin, et al.
Published: (2023)

EMO-Codec: An In-Depth Look at Emotion Preservation capacity of Legacy and Neural Codec Models With Subjective and Objective Evaluations
by: Ren, Wenze, et al.
Published: (2024)

Synthetic training set generation using text-to-audio models for environmental sound classification
by: Ronchini, Francesca, et al.
Published: (2024)

Scaling up masked audio encoder learning for general audio classification
by: Dinkel, Heinrich, et al.
Published: (2024)

Speaker anonymization using neural audio codec language models
by: Panariello, Michele, et al.
Published: (2023)

Regularized autoregressive modeling and its application to audio signal reconstruction
by: Mokrý, Ondřej, et al.
Published: (2024)

Robustness assessment of large audio language models in multiple-choice evaluation
by: López, Fernando, et al.
Published: (2025)

Hybrid-Sep: Language-queried audio source separation via pre-trained Model Fusion and Adversarial Diffusion Training
by: Feng, Jianyuan, et al.
Published: (2025)

The role of audio-visual integration in the time course of phonetic encoding in self-supervised speech models
by: Wang, Yi, et al.
Published: (2025)

WavJEPA: Semantic learning unlocks robust audio foundation models for raw waveforms
by: Yuksel, Goksenin, et al.
Published: (2025)

ParaCLAP -- Towards a general language-audio model for computational paralinguistic tasks
by: Jing, Xin, et al.
Published: (2024)

LRS-VoxMM: A benchmark for in-the-wild audio-visual speech recognition
by: Kwak, Doyeop, et al.
Published: (2026)

Continual Test-time Adaptation for End-to-end Speech Recognition on Noisy Speech
by: Lin, Guan-Ting, et al.
Published: (2024)

Enhancing spatial hearing with cochlear implants: exploring the role of AI, multimodal interaction and perceptual training
by: Picinali, Lorenzo, et al.
Published: (2026)

Erasing Your Voice Before It's Heard: Training-free Speaker Unlearning for Zero-shot Text-to-Speech
by: Lee, Myungjin, et al.
Published: (2026)

Mitigating Subgroup Disparities in Multi-Label Speech Emotion Recognition: A Pseudo-Labeling and Unsupervised Learning Approach
by: Lin, Yi-Cheng, et al.
Published: (2025)

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

ConSep: a Noise- and Reverberation-Robust Speech Separation Framework by Magnitude Conditioning
by: Ho, Kuan-Hsun, et al.
Published: (2024)

What do neural networks listen to? Exploring the crucial bands in Speech Enhancement using Sinc-convolution
by: Ho, Kuan-Hsun, et al.
Published: (2024)

SIRUP: A diffusion-based virtual upmixer of steering vectors for highly-directive spatialization with first-order ambisonics
by: Picard, Emilio, et al.
Published: (2026)

ASTAR-NTU solution to AudioMOS Challenge 2025 Track1
by: Ritter-Gutierrez, Fabian, et al.
Published: (2025)

AEROMamba: An efficient architecture for audio super-resolution using generative adversarial networks and state space models
by: Abreu, Wallace, et al.
Published: (2024)

Tweaking autoregressive methods for inpainting of gaps in audio signals
by: Mokrý, Ondřej, et al.
Published: (2024)

MBCodec:Thorough disentangle for high-fidelity audio compression
by: Zhang, Ruonan, et al.
Published: (2025)

Real-time implementation of vibrato transfer as an audio effect
by: Hyrkas, Jeremy
Published: (2025)

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

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

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

EMO-SUPERB: An In-depth Look at Speech Emotion Recognition
by: Wu, Haibin, et al.
Published: (2024)