REVE: Efficient Hallucination Correction for Large Audio-Language Models via Reused Encoder States

arXiv:2609.26028 · cs.SD, cs.AI · Submitted 2026-09-22 · Read on arXiv

cs.SD, cs.AI

Submitted: 2026-09-22

Updated: 2026-09-22

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Hallucination — 11× in this paper · explained in 3 episodes
• Ontology — 11× in this paper · explained in 2 episodes
• Verification — 10× in this paper · explained in 2 episodes
• Pruning — 4× in this paper · explained in 4 episodes
• Ablation — 3× in this paper · explained in 1 episode
• Benchmark — 2× in this paper · explained in 2 episodes
• Calibration — 2× in this paper · explained in 7 episodes
• Embeddings — 2× in this paper · explained in 2 episodes
• Reused Encoder States for Verifying Events — 2× in this paper
• Steering — 2× in this paper · explained in 2 episodes
• Ablation study — 1× in this paper · explained in 1 episode
• Activation Steering — 1× in this paper · explained in 4 episodes
• Alignment — 1× in this paper · explained in 1 episode
• Distillation — 1× in this paper · explained in 2 episodes
• Feature Extraction — 1× in this paper · explained in 2 episodes
• Hallucination Detection — 1× in this paper · explained in 2 episodes
• Hallucination Mitigation — 1× in this paper · explained in 2 episodes
• Transformer — 1× in this paper · explained in 2 episodes
• Verifier — 1× in this paper · explained in 2 episodes

Sources

• Qwen2-Audio Technical Report
• Silence is Golden: Mitigating Hallucinations in Large Audio-Language Models via Layer-Weighted Vector Steering
• Qwen2.5-Omni Technical Report

Related papers

• Few-Shot Open-Set Audio Classification via Transductive Prototype Refinement and Class Logit Enhancement
• Spectral Masking and Interpolation Attack (SMIA): A Black-box Adversarial Attack against Voice Authentication and Anti-Spoofing Systems
• AVMeme Exam: A Multimodal Multilingual Multicultural Benchmark for LLMs' Contextual and Cultural Knowledge and Thinking
• SoundWeaver: Compositional Warm-Starting for Text-to-Audio Diffusion Serving
• WASIL: In-the-Wild Arabic Spoken Interactions with LLMs
• Efficient Audiovisual Speech Processing via MUTUD: Multimodal Training and Unimodal Deployment