@inproceedings{liu-etal-2025-mitigating-hallucinations,
    title = "Mitigating Hallucinations in {LM}-Based {TTS} Models via Distribution Alignment Using {GF}low{N}ets",
    author = "Liu, Chenlin  and
      Fang, Minghui  and
      Zhang, Patrick  and
      Zhou, Wei  and
      Gao, Jie  and
      Han, Jiqing",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-main.976/",
    pages = "19346--19364",
    ISBN = "979-8-89176-332-6",
    abstract = "Language Model (LM)-based Text-to-Speech (TTS) systems often generate hallucinated speech that deviates from input text. Existing mitigation strategies either demand excessive training resources or introduce significant inference latency. In this paper, we propose GFlOwNet-guided distribution AlignmenT (GOAT) for LM-based TTS, a post-training framework that mitigates hallucinations without relying on massive resources or inference cost. Specifically, we first conduct an uncertainty analysis, revealing a strong positive correlation between hallucination and model uncertainty. Based on this, we reformulate TTS generation as a trajectory flow optimization problem and introduce an enhanced Subtrajectory Balance objective together with a sharpened internal reward as target distribution. We further integrate reward temperature decay and learning rate optimization for stability and performance balance. Extensive experiments show that GOAT reduce over 50{\%} character error rates on challenging test cases and lowering uncertainty by up to 58{\%}, demonstrating its strong generalization ability and effectiveness."
}