paper-with-me

홈 › Papers

Persuasion Dynamics in LLMs: Investigating Robustness and Adaptability in Knowledge and Safety with DuET-PD

2025-08-24 · Bryan Chen Zhengyu Tan, Daniel Wai Kit Chin, Zhengyuan Liu, Nancy F. Chen, Roy Ka-Wei Lee arxiv

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 (Dual Evaluation for Trust in Persuasive Dialogues), 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.

📄 PDF Abstract BibTeX arXiv:2508.17450

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Reasoning or Rambling? Exploring the Effect of Thinking on Agent Persuasion

2025-09-25 · Haodong Zhao, Jidong Li, Zhaomin Wu, Tianjie Ju 외 arxiv

Understanding persuasion is critical for the safety and reliability of multi-agent systems built on large language models (LLMs). This paper studies persuasion dynamics by contrasting general LLMs with Large Reasoning Mo…

Persuade Me if You Can: A Framework for Evaluating Persuasion Effectiveness and Susceptibility Among Large Language Models

2025-03-03 · Nimet Beyza Bozdag, Shuhaib Mehri, Gokhan Tur, Dilek Hakkani-Tür

Large Language Models (LLMs) demonstrate persuasive capabilities that rival human-level persuasion. While these capabilities can be used for social good, they also present risks of potential misuse. Moreover, LLMs' susce…

Misinformation

How Do LLMs Persuade? Linear Probes Can Uncover Persuasion Dynamics in Multi-Turn Conversations

2025-08-07 · Brandon Jaipersaud, David Krueger, Ekdeep Singh Lubana arxiv

Large Language Models (LLMs) have started to demonstrate the ability to persuade humans, yet our understanding of how this dynamic transpires is limited. Recent work has used linear probes, lightweight tools for analyzin…

A Model of Multi-turn Human Persuadability Using Probabilistic Belief Tracing

2026-06-03 · Jared Moore, Noah Goodman, Nick Haber, Max Kleiman-Weiner arxiv

Large language models can shift human beliefs across high-stakes domains, but most persuasion studies rely on pre/post belief change. These endpoint measures identify whether persuasion occurred, yet miss where and how b…

Persuasion at Play: Understanding Misinformation Dynamics in Demographic-Aware Human-LLM Interactions

2025-03-03 · Angana Borah, Rada Mihalcea, Verónica Pérez-Rosas

Existing challenges in misinformation exposure and susceptibility vary across demographic groups, as some populations are more vulnerable to misinformation than others. Large language models (LLMs) introduce new dimensio…

Misinformation