mlsanityData to 14 Oct 2026

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

arXiv 2508.17450 ↗First posted 24 Aug 2025cs.CL cs.CYcited by 13

Not on the map. Why?

Abstract (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.

Key facts. Cited by 13 papers in the map (data through 14 Oct 2026). Builds on 29 of its 48 references that are in the map. First posted on arXiv 24 Aug 2025.

Builds on

29 of 48 references.

References · 29

  1. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  2. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,212
  3. 2024MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmarkcited by 1,848
  4. 2024LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Modelscited by 1,464
  5. 2023Towards Understanding Sycophancy in Language Modelscited by 1,040
  6. 2024How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMscited by 573
  7. 2023Can Generalist Foundation Models Outcompete Special-Purpose Tuning? Case Study in Medicinecited by 329
  8. 2024Large Language Models for Education: A Survey and Outlookcited by 188
  9. 2025X-Teaming: Multi-Turn Jailbreaks and Defenses with Adaptive Multi-Agentscited by 125
  10. 2024Language Models Learn to Mislead Humans via RLHFcited by 124
  11. 2023The Earth is Flat because...: Investigating LLMs' Belief towards Misinformation via Persuasive Conversationcited by 109
  12. 2024Sycophancy in Large Language Models: Causes and Mitigationscited by 101
17 more
  1. 2024Hidden Persuaders: LLMs' Political Leaning and Their Influence on Voterscited by 71
  2. 2023Tricking LLMs into Disobedience: Formalizing, Analyzing, and Detecting Jailbreakscited by 49
  3. 2023Evaluating GPT-3 Generated Explanations for Hateful Content Moderationcited by 46
  4. 2024Persuasion with Large Language Models: A Survey of Empirical Evidence, Study Methodologies, and Ethical Implicationscited by 32
  5. 2025Unmasking Implicit Bias: Evaluating Persona-Prompted LLM Responses in Power-Disparate Social Scenarioscited by 26
  6. 2023How susceptible are LLMs to Logical Fallacies?cited by 23
  7. 2024Teaching Models to Balance Resisting and Accepting Persuasioncited by 19
  8. 2023Exploiting Large Language Models (LLMs) through Deception Techniques and Persuasion Principlescited by 17
  9. 2024Reasoning Like a Doctor: Improving Medical Dialogue Systems via Diagnostic Reasoning Process Alignmentcited by 17
  10. 2025Resolving Conflicting Evidence in Automated Fact-Checking: A Study on Retrieval-Augmented LLMscited by 16
  11. 2025Is LLM an Overconfident Judge? Unveiling the Capabilities of LLMs in Detecting Offensive Language with Annotation Disagreementcited by 14
  12. 2025Persuasion at Play: Understanding Misinformation Dynamics in Demographic-Aware Human-LLM Interactionscited by 11
  13. 2024Moral Persuasion in Large Language Models: Evaluating Susceptibility and Ethical Alignmentcited by 10
  14. 2024Examining the Influence of Political Bias on Large Language Model Performance in Stance Classificationcited by 9
  15. 2023To Tell The Truth: Language of Deception and Language Modelscited by 6
  16. 2024Can a large language model be a gaslighter?cited by 5
  17. 2025Sword and Shield: Uses and Strategies of LLMs in Navigating Disinformationcited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 11.

13 papers.

Sort:

By area:

  1. 2025Accumulating Context Changes the Beliefs of Language Modelscited by 28
  2. 2026When Correct Beliefs Collapse: Epistemic Resilience of LLMs under Clinical Pressurecited by 6
  3. 2025The Imperfect Learner: Incorporating Developmental Trajectories in Memory-based Student Simulationcited by 1
  4. 2026Persuasion Propagation: Does Persuasion Change AI Agent Behavior?cited by 1
  5. 2026AREG: Adversarial Resource Extraction Game for Evaluating Persuasion and Resistance in Large Language Modelscited by 1
  6. 2026Right or Wrong, Models Comply: Directional Blindness in LLM Moral Judgmentcited by 1
  7. 2026Assessing and Explaining the Persuadability of Large Language Models as Legal Decision Toolscited by 0
  8. 2026Psi-Bench: Evaluating Persona-Sensitive Influencing in Persuasive Dialoguescited by 0
  9. 2026Confident but Conflicted: Internal Uncertainty and Cognitive Dissonance Resolution in LLMscited by 0
  10. 2026Bridging Talk and Thought: Understanding Dialogue Dynamics Across Collaborative Problem-Solving Contextscited by 0
  11. 2026CC-Mediation: Evaluating Large Language Models for Cross-Cultural Conflict Mediationcited by 0
  12. 2026Do LLMs Trust the Accuser or the Accusation? Measuring Belief Shifts in Werewolfcited by 0
1 more
  1. 2026AfriSyCo: Measuring Assertive Framing, Verification, and Wording Sensitivity Around African-Language Contentcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025LLM Can be a Dangerous Persuader: Empirical Study of Persuasion Safety in Large Language Models
  2. 2026Benchmarking Factual Robustness of LLMs via Multi-conversation Persuasion
  3. 2026Learning to Persuade Exposes How Easily LLMs Abandon Correct Beliefs
  4. 2025Towards Strategic Persuasion with Language Models
  5. 2025It's the Thought that Counts: Evaluating the Attempts of Frontier LLMs to Persuade on Harmful Topics
  6. 2025Persuasiveness and Bias in LLM: Investigating the Impact of Persuasiveness and Reinforcement of Bias in Language Models
  7. 2025On the Adaptive Psychological Persuasion of Large Language Models
  8. 2025When Persuasion Overrides Truth in Multi-Agent LLM Debates: Introducing a Confidence-Weighted Persuasion Override Rate (CW-POR)