@inproceedings{tan-etal-2025-persuasion,
    title = "Persuasion Dynamics in {LLM}s: Investigating Robustness and Adaptability in Knowledge and Safety with {D}u{ET}-{PD}",
    author = "Tan, Bryan Chen Zhengyu  and
      Chin, Daniel Wai Kit  and
      Liu, Zhengyuan  and
      Chen, Nancy F.  and
      Lee, Roy Ka-Wei",
    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.81/",
    pages = "1550--1575",
    ISBN = "979-8-89176-332-6",
    abstract = "Large Language Models (LLMs) can struggle to balance gullibility to misinformation and resistance to valid corrections in persuasive dialogues, a critical challenge for reliable deployment. We introduce **DuET-PD** (**Du**al **E**valuation for **T**rust in **P**ersuasive **D**ialogues), a framework evaluating multi-turn stance-change dynamics across dual dimensions: persuasion type (corrective/misleading) and domain (knowledge via MMLU-Pro, and safety via SALAD-Bench). We find that even a state-of-the-art model like GPT-4o achieves only 27.32{\%} accuracy in MMLU-Pro under sustained misleading persuasions. Moreover, results reveal a concerning trend of increasing sycophancy in newer open-source models. To address this, we introduce Holistic DPO, a training approach balancing positive and negative persuasion examples. Unlike prompting or resist-only training, Holistic DPO enhances both robustness to misinformation and receptiveness to corrections, improving Llama-3.1-8B-Instruct{'}s accuracy under misleading persuasion in safety contexts from 4.21{\%} to 76.54{\%}. These contributions offer a pathway to developing more reliable and adaptable LLMs for multi-turn dialogue. Code is available at https://github.com/Social-AI-Studio/DuET-PD."
}