@inproceedings{chen-etal-2026-aha,
    title = "{AHA}: Aligning Large Audio-Language Models for Reasoning Hallucinations via Counterfactual Hard Negatives",
    author = "Chen, Yanxi  and
      Zhu, Wenhui  and
      Chen, Xiwen  and
      Wang, Zhipeng  and
      Li, Xin  and
      Qiu, Peijie  and
      Wang, Hao  and
      Dong, Xuanzhao  and
      Xiong, Yujian  and
      Schneider, Anderson  and
      Nevmyvaka, Yuriy  and
      Wang, Yalin",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.1464/",
    pages = "29294--29306",
    ISBN = "979-8-89176-395-1",
    abstract = "Although Large Audio-Language Models (LALMs) deliver state-of-the-art (SOTA) performance, they frequently suffer from hallucinations, e.g., generating text not grounded in the audio input. We analyze these grounding failures and identify a distinct taxonomy: Event Omission, False Event Identity, Temporal Relation Error, and Quantitative Temporal Error. To address this, we introduce the AHA (Audio Hallucination Alignment) framework. By leveraging counterfactual hard negative mining, our pipeline constructs a high-quality preference dataset that forces models to distinguish strict acoustic evidence from linguistically plausible fabrications. Additionally, we establish AHA-Eval, a diagnostic benchmark designed to rigorously test these fine-grained reasoning capabilities. We apply this data to align Qwen2.5-Omni. The resulting model, Qwen-Audio-AHA, achieves a 13.7{\%} improvement on AHA-Eval. Crucially, this benefit generalizes beyond our diagnostic set. Our model shows substantial gains on public benchmarks, including 1.3{\%} on MMAU-Test and 1.6{\%} on MMAR, outperforming latest SOTA methods."
}