论文研究
arxiv.org ·
REVE：通过复用编码器状态实现大型音频语言模型的高效幻觉纠正
该论文提出 REVE（Reused Encoder States for Verifying Events），一种轻量方法，直接复用目标音频语言模型已计算的编码器状态来验证生成的事件提及，无需第二个音频编码器和额外前向传播。方法包含两个读出：一个汇总音频帧的类别分数，另一个使用四个连续帧区间的池化状态，并通过类别感知分数融合合并输出。在 AudioSet 上，REVE 在忠实提及召回约束下移除 92.9% 无标签支持的提及，参数增量更少且无需二次音频编码，效果与 CED-Tiny、CED-Base 相当，完整验证延迟约为 CED-Base 路径的 1/18；在受控 DESED 混合和不同目标模型架构上的结果进一步支持编码器状态复用的有效性。
AI推荐理由 arXiv 新论文，提出 REVE 方法：复用目标音频语言模型已计算的编码器状态来验证生成的事件提及，无需第二个音频编码器和额外前向传播。摘要给出具体量化结果：在 AudioSet 上于忠实提及召回约束下移除 92.9% 无标签支持的提及，验证延迟约为 CED-Base 路径的 1/18，并在 DESED 混合与不同目标模型架构上验证。属于方法层面的可验证新信息，对多模态幻觉纠正与推理效率有参考价值；局限是仅基于摘要，未见代码与同行评审，效果需独立复现。
72
正文
Computer Science > Sound
arXiv:2609.26028 (cs)
[Submitted on 22 Sep 2026]
Title:REVE: Efficient Hallucination Correction for Large Audio-Language Models via Reused Encoder States
Authors:Hongjin Song, Jiasheng Kuang, Xinyu Yang, Qiuyu Fang, Ziyu Wu, Guowu Tan, Xiang Xie
View a PDF of the paper titled REVE: Efficient Hallucination Correction for Large Audio-Language Models via Reused Encoder States, by Hongjin Song and 6 other authors
View PDF
HTML (experimental)
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.
Subjects:
Sound (cs.SD); Artificial Intelligence (cs.AI)
Cite as:
arXiv:2609.26028 [cs.SD]
(or
arXiv:2609.26028v1 [cs.SD] for this version)
https://doi.org/10.48550/arXiv.2609.26028
Focus to learn more
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Hongjin Song [view email]
[v1]
Tue, 22 Sep 2026 11:32:22 UTC (452 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled REVE: Efficient Hallucination Correction for Large Audio-Language Models via Reused Encoder States, by Hongjin Song and 6 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.SD
new
|
recent
| 2026-09
Change to browse by:
cs
cs.AI
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
export BibTeX citation
Loading...
BibTeX formatted citation
×
loading...
Data provided by:
Bookmark
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? |
Disable MathJax (What is MathJax?)