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

2026-09-22

AI Summary

本文提出REVE方法，利用已计算的编码器状态来校正大音频-语言模型中的幻觉事件，无需二次音频编码，有效减少了92.9%的标签不支持的提及。

Abstract

Large audio-language models may mention acoustic events that are absent from the input. A separate audio event detector can verify these mentions, but doing so requires a second audio encoder and a separate forward pass. We propose Reused Encoder States for Verifying Events (REVE), a lightweight method that uses states already computed by the target model. One readout summarizes class scores across audio frames, while another uses pooled states from four consecutive frame intervals. Class-aware score fusion combines their outputs to verify generated event mentions without encoding the audio again. On AudioSet, REVE removes 92.9% of label-unsupported mentions under a faithful-mention recall constraint. With fewer added parameters and no second audio-encoding pass, REVE achieves a reduction comparable to those of CED-Tiny and CED-Base. Its complete verification latency is about 1/18 of the CED-Base path. Results on controlled DESED mixtures and different target-model architectures further confirm the effectiveness of encoder-state reuse.

Problem

• audio-language models
• hallucination correction
• acoustic events

Innovation

• Reused Encoder States
• Class-aware Score Fusion
• Lightweight Method
• Efficient Hallucination Correction