cs.SDNov 19, 2026

From Attention to Semantics: Detecting and Mitigating Sound Event Hallucinations in Large Audio-Language Models

Authors: Tianyi Sun, Minghao Lv, Chunyang Yu, Shenyue Wang, Mengyue Wu

Organizations: Shanghai Jiao Tong University · Guangdong OPPO Mobile Telecommunications Corp., Ltd.

Abstract

Large Audio-Language Models (LALMs) excel at diverse audio tasks, yet remain prone to hallucinating sound events absent from the input. Prior work links such hallucinations to insufficient audio attention. However, we find that real and hallucinated events can receive comparable audio attention mass while attending to different audio positions. To examine whether the attended representations support the generated events, we adapt LatentLens to retrieve neighboring contextualized text representations. The retrieved contexts reveal semantic support for real events, but a semantic mismatch between hallucinated events and their attended audio representations. Directly masking the corresponding audio regions can suppress hallucinated events at the cost of real content. We are motivated by these findings to introduce an explainable and training-free detect-then-mitigate framework for effectively hallucination detection and mitigation that aggregates semantic support and applies differential audio masking to protect regions associated with events predicted to be supported. Extensive experiments on three LALMs and two datasets demonstrate that our method significantly improves hallucination detection and hallucination mitigation performance.

Figures & tables

Appendix figures & tables13 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

Mar 31, 2026

Audio Hallucination Attacks: Probing the Reliability of Large Audio Language Models

Large Audio Language Models (LALMs) achieve strong performance on audio-language tasks; however, their reliability in real-world settings remains underexplored. We introduce Audio Hallucination Attacks (AHA), an attack suite called AHA-Eval, comprising 6.5K QA pairs designed to test whether LALMs genuinely ground their responses in the audio input. AHA targets two attack surfaces: (i) query-based attacks, which exploit question structure to induce hallucinations about absent sounds, and (ii) audio-based attacks, which inject synthetic speech describing non-existent events into the audio stream. Evaluating state-of-the-art LALMs, including Audio Flamingo 3 and Gemini 3 Pro, we observe high attack success rates of 95.35% and 79.65%, respectively, revealing a reliability gap that is hidden by standard benchmark performance. To mitigate this, we propose a 120K QA post-alignment dataset, AHA-Guard, which successfully reduces attack success rates by up to 49%.
Sep 27, 2026

MISHAP-Bench: A Hallucination Benchmark for Large Audio-Language Models

Large audio-language models (LALMs) produce fluent responses about audio but often hallucinate by making plausible yet ungrounded claims. Existing audio hallucination benchmarks mainly measure response correctness, leaving it unclear whether an LALM hallucinates or simply fails to understand the audio. We challenge correctness-based evaluation by defining two hallucination categories: (i) context, where claims are not grounded in the audio; and (ii) knowledge, where claims about audio-related topics lack support from externally verifiable facts. We introduce MISHAP-Bench, a comprehensive benchmark with 12,000 challenging open-ended question-audio pairs and a rigorous evaluation pipeline covering both categories. To evaluate open-ended responses, we propose a groundedness judge that uses reference rubrics and judge prompts guided by human annotations. We extensively evaluate ten state-of-the-art LALMs and show that hallucination remains substantial. Even a frontier model such as Gemini 3.7 Flash reaches a hallucination rate of 36.5%. We further adapt and benchmark four mitigation methods from multiple domains for LALMs. Despite some improvements, effective hallucination mitigation remains an open challenge. Finally, we call on the community to evaluate hallucination and benchmark mitigation methods with MISHAP-Bench.
Oct 14, 2025

Silence is Golden: Mitigating Hallucinations in Large Audio-Language Models via Layer-Weighted Vector Steering

Large Audio-Language Models (LALMs) excel in Audio QA but often suffer from hallucinations ungrounded in the audio. To our knowledge, we are the first to propose applying vector steering to the audio domain to mitigate this. Unlike text-based steering, our silence-anchored contrastive approach steers the model away from hallucinations by contrasting active audio against a silent baseline. Probing internal states reveals a strong correlation between specific layer representations and output correctness. Leveraging this, we introduce Layer-Weighted Vector Steering (LWVS), a training-free intervention that increases steering strength at influential layers. On the Audio Hallucination QA dataset, LWVS significantly outperforms baselines, boosting Recall on the Gemma model by 15.6% (53.4% to 69.0%). Crucially, MMAU benchmark tests confirm LWVS preserves and even enhances general audio understanding, achieving an 8% relative accuracy increase on the Qwen model (54.8% to 59.2%).