@inproceedings{gu-etal-2026-unsupervised,
    title = "Unsupervised Text Style Transfer for Controllable Intensity",
    author = "Gu, Shuhuan  and
      Tao, Wenbiao  and
      Ma, Xinchen  and
      He, Kangkang  and
      Guo, Ye  and
      Li, Xiang  and
      Lan, Yunshi",
    editor = "Demberg, Vera  and
      Inui, Kentaro  and
      Marquez, Llu{\'i}s",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EACL} 2026",
    month = mar,
    year = "2026",
    address = "Rabat, Morocco",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-eacl/2026.findings-eacl.133/",
    pages = "2570--2584",
    ISBN = "979-8-89176-386-9",
    abstract = "Unsupervised Text Style Transfer (UTST) aims to build a system to transfer the stylistic properties of a given text without parallel text pairs.Compared with text transfer between style polarities, UTST for controllable intensity is more challenging due to the subtle differences in stylistic features across different intensity levels.Faced with the challenges posed by the lack of parallel data and the indistinguishability between adjacent intensity levels, we propose a SFT-then-PPO paradigm to fine-tune an LLM.We first fine-tune the LLM with synthesized parallel data.Then, we further train the LLM with PPO, where the rewards are elaborately designed for distinguishing the stylistic intensity in hierarchical levels.Both the global and local stylistic features are considered to formulate the reward functions.The experiments on two UTST benchmarks showcase that both rewards have their advantages and applying them to LLM fine-tuning can effectively improve the performance of an LLM backbone based on various evaluation metrics.Even for adjacent levels of intensity, we can still observe a noticeable stylistic difference among the generated text across these levels."
}