Persuasion in Language Models

Follow this topic Ask about this topic

Persuasion in language models covers both models’ ability to change people’s beliefs or actions and their susceptibility to arguments from users or other agents. Researchers study this with controlled human experiments, multi-turn dialogue and negotiation benchmarks, belief-update simulations, and analyses of rhetoric, personalization, authority, and framing. Work also tests defenses such as factual verification, adversarial training, user warnings, and alignment constraints, alongside constructive uses like debunking and behavior-change support. Results depend on the model, topic, interaction, and whether success means sounding convincing, changing stated views, or changing real behavior; a central challenge is resisting manipulation without suppressing useful, truthful persuasion.

Latest papers

79 papers15 papers in the last four weeks, up 36% on the four weeks before. 0.1% of all new papers.

Implicit Beliefs as Scalable Process Rewards for Strategic Persuasion
Oct 24, 2026Minqian Liu, Yuexi Shen, Heajun An +5Persuasion in Language Models Process Reward Models
Virginia Tech · UC Santa Barbara · STIR Lab +1
To Manipulate or Not: Opinion Dynamics in LLM Interactions
Oct 20, 2026Mohammad Siahkamari, Phuoc Dat Nguyen, Stephen MacNeilPersuasion in Language Models Belief Updating in LLMs
Temple University, Philadelphia, PA, USA
When LLMs Manipulate: Measuring Behavioral, Social, and Temporal Effects
Oct 20, 2026Sadia Asif, Israel Antonio Rosales Laguan, Shumaila Asif +3Language Model Safety Evaluation Persuasion in Language Models
Rensselaer Polytechnic Institute, USA · Independent Researcher, Colombia · National University of Sciences and Technology, Pakistan +1
A Cue's Hidden Price: Auditing Seller Influence on AI Shoppers
Oct 19, 2026Felix Buecheler, Gerardo Berbeglia, Mingyu GuoAI Agent Auditing Generative Engine Optimization
Adelaide University, Adelaide, Australia · Melbourne Business School, Melbourne, Australia
A Thousand Faces: A Persuasion Benchmark with Experience-Grounded Persuadees Informed by Psychology and Pragmatics
Oct 18, 2026Ziqing Zhuang, Dingyi Zhang, Deyu ZhouPersuasion in Language Models Pragmatic Reasoning in Language Models
Southeast University
PerSo: Investigating Facets of LLMs' Social Intelligence in Real-World Persuasion Scenarios
Oct 14, 2026Ali Zamani, Soroush Esfahanian, Erfan Shahabi +3LLM Evaluation Persuasion in Language Models
School of Electrical and Computer Engineering, College of Engineering, University of Tehran, Tehran, Iran · Cardiff University, United Kingdom · Institute for Research in Fundamental Sciences (IPM), Tehran, Iran +1
Receiver Decides Agent-to-Agent Negotiations
Oct 13, 2026Fardeen Sadab, Alif Hasnain, Afsana Shehrin +2Multi-Agent Negotiation Persuasion in Language Models
Department of Computer Science and Engineering, Islamic University of Technology, Dhaka, Bangladesh
Understanding and Reducing Misalignment in Persuasion Optimization
Oct 12, 2026Boyi Wei, Ruta Desai, Peter Henderson +1LLM Alignment Emergent Misalignment in Language Models
Microsoft Research · Princeton University
UkrMeme: Multimodal Explainable Persuasion Detection in Ukrainian Memes
Oct 9, 2026Nazar Andrushko, Vera Schmitt, Veronika SolopovaVLM Evaluation VLM Interpretability
Ukrainian Catholic University, Lviv, Ukraine · Johannes Gutenberg University Mainz, Mainz, Germany · German Research Center for Artificial Intelligence (DFKI), Berlin, Germany +1
The AI's Poker Face: Contrasting Persuasion and Sycophancy in Voice-Based Multi-Turn Conversations
Oct 9, 2026Ilia Frantzi, Bernie Hogan, Max M. Lang +1Persuasion in Language Models LLM Sycophancy
University of Munich, Germany · University of Oxford, UK · GESIS - Leibniz-Institute for the Social Sciences, Germany
LLM Persuasion Is in the Eye of the Evaluation
Oct 7, 2026Kamile Dementaviciute, Julija Vaitonyte, Tijl De BiePersuasion in Language Models LLM Evaluation
Ghent University · Tilburg University, Department of Computational Cognitive Science · ISM University of Management and Economics
Successive Training Stages and Large Language Model Persuasion: Effects of Misalignment, Supervised Fine-Tuning, and Preference Optimization
Oct 7, 2026Antony Dalmiere, Pascal Marchand, Guillaume Auriol +1Persuasion in Language Models LLM Post-Training
LAAS-TRUST · LAAS-TRUST, INSA Toulouse · LAAS-TSF, LAAS
Peer Influence across Heterogeneous AI Models
Oct 2, 2026Frida Nøhr Laustsen, Marie Haahr Petersen, Victoria Popa +4Persuasion in Language Models Multi-Agent Communication
IT University of Copenhagen, Denmark · University of Pisa, Italy · City St. George’s, University of London, United Kingdom +1
Persona and Persuasive Framing in AI Voice Agents: A $2\times2$ Field Experiment with Children
Sep 30, 2026Thilo Tamme, David Steck, Anton HantelHuman-AI Interaction Framing Effects in Language Models
Technical University of Munich · Massachusetts Institute of Technology
AI Agents are Vulnerable to Radicalization
Sep 29, 2026Ozgur Can Seckin, Shalmoli Ghosh, Alessandro Flammini +3Multi-Agent LLM Systems Belief Updating in LLMs
Observatory on Social Media, Indiana University Bloomington · Emerging Media Studies Division, College of Communication, Boston University
LLMAdBench: A Human Preference Benchmark for Advertising in LLM Responses
Sep 26, 2026Rui Ai, Yuqing Liu, Sitao Qiu +14Language Model Generation Evaluation Human Preference Modeling
Massachusetts Institute of Technology · University of Michigan, Ann Arbor · Shanghai Jiao Tong University +7
Persuaded, Not Informed: Incentive-Misaligned Witnesses Defeat In-Context Grounding
Sep 23, 2026Rahul BalakaviKnowledge Conflicts in Language Models Agent Evaluation
AmpUp Research
Benchmarking Argumentative Behaviour of LLMs: A Study of Defences Against Character Attacks
Sep 23, 2026Ewelina Gajewska, Katarzyna Budzynska, Jaroslaw ChudziakMulti-Agent Debate Computational Argumentation
Warsaw University of Technology
Robust Is Salient: An Informed Adversary Moves the Optimal Signal onto the Salience Pole
Sep 23, 2026Cris HuynhPersuasion in Language Models
Independent researcher
Conduct Under Pressure: What Sixty Language Models Do When a User Pushes
Sep 21, 2026Tapan ParikhLanguage Model Safety Evaluation Persuasion in Language Models
Cornell Tech
Benchmarking Factual Robustness of LLMs via Multi-conversation Persuasion
Sep 15, 2026Zhuoang CaiAdversarial Attacks on LLMs LLM Safety Evaluation
The Hong Kong University of Science and Technology
A Multi-Stage Agentic Framework for Effective Counter-Narrative Generation and Refinement
Sep 12, 2026Carmel Kronfeld, Sharva Gogawale, Tetsuro Kobayashi +1Text Generation Persuasion in Language Models
School of Industrial & Intelligent Systems Engineering, Tel Aviv University · School of Electrical and Computer Engineering, Tel Aviv University · School of Political Science and Economics, Waseda University
When Does Defendant Statement Matter? A Study of Bias and Persuasion in LLM-Simulated Jurors
Sep 9, 2026Cho-Ying WuLegal Judgment Prediction Social Bias in Language Models
Bosch AI Research
PTCG: Persona-guided Tree-based Counterargument Generation
Sep 7, 2026Eunbeen Son, Yohan Jo, Joonsuk Park +1Computational Argumentation Persuasion in Language Models
Sungkyunkwan University · Seoul National University · University of Richmond +1
DIPLOMAT: Dialogue-Span-Aware Direct Preference Optimization for Polite Persuasive Workplace Negotiation Dialogues
Sep 6, 2026Bibhuti Jha, Rishikant Chigrupaatii, Priyanshu Priya +1Automated Negotiation Direct Preference Optimization
Department of Computer Science and Engineering, Indian Institute of Technology Patna, India · GREYC Laboratory, University of Caen Normandy, France
Door-in-the-Face Requests and Refusal Behaviour in Large Language Models
Sep 2, 2026Til JordanPersuasion in Language Models LLM Refusal Behavior
Do LLMs Change Their Minds Like Humans? Diagnosing Human--LLM Divergence in Single-Turn Persuasion Judgments
Aug 30, 2026Lin Chen, Yitong Chen, Yong LiLLM Evaluation Belief Updating in LLMs
1Network Science Institute, Northeastern University · Department of Physics, Northeastern University · Department of Electronic Engineering, BNRist, Tsinghua University
Evaluating the Capabilities of LLMs for Persuasive Dialogue
Aug 30, 2026Jordan Robinson, Angus R. Williams, Katie Atkinson +1LLM Evaluation Multi-Agent Debate
University of Liverpool · 2The Alan Turing Institute · University of Leeds
AI Can Be Easily Persuaded in Clinical Decision Making
Aug 29, 2026Jiayuan Zhu, Jiazhen Pan, Fenglin Liu +2Human-AI Decision Making Persuasion in Language Models
University of Oxford · Stanford University
Belief Cascades Drive Persuasion in LLM Agent Networks
Aug 25, 2026Haoyi Qiu, Genglin Liu, Pranav Narayanan Venkit +4Persuasion in Language Models Multi-Agent LLM Systems
University of California, Los Angeles · Salesforce AI Research

Oct 24, 2026J/K move · Enter open · S save

Implicit Beliefs as Scalable Process Rewards for Strategic Persuasion

Minqian Liu, Yuexi Shen, Heajun An, Qi Zhang+4

Virginia Tech · UC Santa Barbara · STIR Lab+1

Persuasion in Language Models Process Reward Models RL for Language Models Large Language Model-Based Social Simulation

Open paper AskPDF arXiv

Training large language models (LLMs) for multi-turn strategic persuasion faces two coupled obstacles: (i) realistic simulation of psychologically grounded persuadees, and (ii) dense, faithful supervision for credit assignment in strategic dialogues. Outcome-only rewards are sparse and uninformative about which conversational moves drove success, while LLM-judge process rewards are expensive and decoupled from the underlying interaction dynamics. We address both challenges with a unified framework. First, we introduce PersuArena, a persuasion simulation environment that produces realistic, non-monotonic trajectories. Second, building directly on this environment, we propose Process Rewards via Online Belief Elicitation for Relative Policy Optimization (Probe-RPO), an online RL framework that converts the persuadee's internal state into dense process rewards. At each turn, three introspective probes are read from the frozen persuadee's logits, yielding a multi-dimensional reward signal that is faithfully aligned with persuasion dynamics. With extensive experiments on PersuArena spanning healthcare, financial advising, workplace management, education, and personal relationships, we demonstrate that our Probe-RPO achieves the full acceptance rate of 52.5%, compared with the 35.8% for the strongest GRPO ablation and 25.8% for the best off-the-shelf LLM. We also conduct comprehensive analyses on the generalization across persuadee models and the persuasion dynamics across conversations. Our work offers a promising paradigm that can provide effective process supervision for strategic dialogue.