Human Behavior: Research Area — Prolific Citations Library

Discover 21 peer-reviewed studies in Human Behavior (2021–2025). Explore research findings powered by Prolific's diverse participant panel.

This page lists 21 peer-reviewed papers in the research area of Human Behavior in the Prolific Citations Library, a curated collection of research powered by high-quality human data from Prolific.

Papers (20 of 21)

On the conversational persuasiveness of GPT-4

Authors: F Salvi, M Horta Ribeiro, R Gallotti, R West

Year: 2025

Published in: Nature Human Behaviour, 2025 - nature.com

Institution: EPFL, Fondazione Bruno Kessle, Princeton University

Research Area: Conversational Persuasion of LLM, Human-Computer Interaction (HCI), Behavioral Science, LLM

Discipline: Behavioral Science

GPT-4 can use personalized arguments to be more persuasive in debates, outperforming humans in 64.4% of AI-human comparisons when personalization is applied.

Methods: Preregistered controlled study involving multiround debates with random assignment to conditions focusing on AI-human comparisons, personalization, and opinion strength.

Key Findings: Effectiveness of persuasion by GPT-4, especially when using personalized arguments, compared to humans in debates.

Citations: 65

Sample Size: 900
When AI is Fairer Than Humans: The Role of Egocentrism in Moral and Fairness Judgments of AI and Human Decisions

Authors: K Miazek, K Bocian

Year: 2025

Published in: Computers in Human Behavior Reports, 2025 - Elsevier

Institution: SWPS University

Research Area: Moral and Fairness Judgments of AI, Human Behavior, Egocentrism

Discipline: Social Science, Artificial Intelligence

The study found that egocentric biases influence fairness judgments, favoring decisions beneficial to self-interest, and that this bias is weaker for AI compared to human agents due to reduced perceived mind and liking for AI.

Methods: Three experiments with manipulated self-interest conditions analyzed perceptions of fairness and morality in decisions made by AI versus human agents using Prolific US samples.

Key Findings: Fairness and moral judgments in financial decision-making by AI and human agents, moderated by self-interest and social perceptions.

DOI: https://doi.org/10.1016/j.chbr.2025.100719

Citations: 6

Sample Size: 1880
Persuading voters using human-artificial intelligence dialogues

Authors: H Lin, G Czarnek, B Lewis, JP White, AJ Berinsky

Year: 2025

Published in: Nature, 2025 - nature.com

Institution: Massachusetts Institute of Technology

Research Area: Political Persuasion, Human-AI Dialogue, Electoral Behavior

Discipline: Political Science, Artificial Intelligence

The study shows that AI-driven dialogues can significantly influence voter attitudes and candidate preferences, with persuasion effects surpassing traditional political advertisements, though inaccuracies were more prevalent in content generated by AI models supporting right-wing candidates.

Methods: Pre-registered experiments where participants interacted with AI advocating for one of two candidates or a ballot measure, examining persuasion strategies and effects across three elections.

Key Findings: Influence of AI-generated dialogues on voter attitudes and preferences, including analysis of persuasion strategies and accuracy of presented information.

Citations: 3
Do People Think Fast or Slow When Training AI?

Authors: L S. Treiman, CJ Ho, W Kool

Year: 2025

Published in: Proceedings of the 2025 ACM Conference ..., 2025 - dl.acm.org

Institution: Washington University in St. Louis, National Cheng Kung University

Research Area: Human-AI Interaction, Cognitive Science, Behavioral Research in AI Training

Discipline: Human-Computer Interaction (HCI), Behavioral Science

Participants tend to rely on intuition (fast thinking) rather than deliberation (slow thinking) when training AI agents in the ultimatum game, impacting human-AI collaboration system design.

Methods: Participants trained an AI agent in the ultimatum game to analyze whether their training decisions aligned more with intuitive or deliberative cognitive processes.

Key Findings: The cognitive processes (fast vs. slow thinking) underlying human decision-making during AI training.

DOI: https://dl.acm.org/doi/abs/10.1145/3715275.3732177

Citations: 1
To Mask or to Mirror: Human-AI Alignment in Collective Reasoning

Authors: C Qian, AT Parisi, C Bouleau, V Tsai

Year: 2025

Published in: Proceedings of the ..., 2025 - aclanthology.org

Institution: Google, Google DeepMind

Research Area: Human-AI Alignment, Collective Reasoning, Social Biases, LLM Simulation of Human Behavior, AI Bias

Discipline: Natural Language Processing, Artificial Intelligence, Computational Social Science

This study examines human-AI alignment in collective reasoning using an empirical framework, demonstrating how LLMs either mirror or mask human biases depending on context, cues, and model-specific inductive biases.

Methods: The study uses the Lost at Sea social psychology task in a large-scale online experiment, simulating LLM groups conditioned on human decision-making data across varying conditions of visible or pseudonymous demographics.

Key Findings: Alignment of LLM behavior with human social reasoning, focusing on collective decision-making and biases in group interactions.

Citations: 1

Sample Size: 748
Improving annotation quality: empirical insights into bias, human-AI collaboration, and workflow design

Authors: J Beck

Year: 2025

Published in: 2025 - edoc.ub.uni-muenchen.de

Institution: Ludwig-Maximilians-Universität München, University of Bayreuth

Research Area: Annotation Quality, Human-AI Collaboration, Behavioral Science, Human-Computer Interaction (HCI)

Discipline: Human-Computer Interaction (HCI)

The study empirically evaluates annotation bias, proposes strategies to reduce its impact, and explores the use of large language models in automated and hybrid annotation workflows.

Methods: Empirical assessments and experimental evaluations involving annotation workflows and large language models.

Key Findings: Annotation bias, annotation quality, and the effectiveness of hybrid workflows integrating human input and AI models.
Large language model in creative work: The role of collaboration modality and user expertise

Authors: Z Chen, J Chan

Year: 2024

Published in: Management Science, 2024 - pubsonline.informs.org

Institution: University of Texas Dallas

Research Area: Human-AI Interaction, Creative Work, Behavioral Science

Discipline: Social Science

Using large language models (LLMs) as sounding boards improves ad content quality for nonexpert users, while using LLMs as ghostwriters can negatively impact expert users due to anchoring effects.

Methods: An experiment comparing ad copy creation with and without LLM assistance, focusing on two collaboration modalities: ghostwriting and sounding board approaches. Ad performance was measured via social media click rates, supported by textual analysis.

Key Findings: Effectiveness of LLM collaboration modalities (ghostwriting vs. sounding board) on ad quality and business outcomes for expert and nonexpert users.

DOI: https://doi.org/10.1287/mnsc.2023.03014

Citations: 180
Why human-AI relationships need socioaffective alignment

Authors: HR Kirk, I Gabriel, C Summerfield, B Vidgen

Year: 2024

Published in: Humanities and Social ..., 2025 - nature.com

Institution: Oxford Internet Institute, University of Oxford

Research Area: Socioaffective Alignment in Human-AI Relationships, AI Ethics, Behavioral Science

Discipline: Artificial Intelligence, Behavioral Science

The paper emphasizes the need for socioaffective alignment in human-AI relationships to ensure AI systems support human psychological needs rather than exploit them, as interactions with AI transition from transactional to sustained engagement.

Methods: Conceptual analysis of socioaffective dynamics in human-AI interactions, framed through psychological theories and principles.

Key Findings: Exploration of how AI systems impact socioaffective relationships, psychological needs, autonomy, companionship, and human well-being.

DOI: https://doi.org/10.1057/s41599-025-04532-5

Citations: 59
Take caution in using LLMs as human surrogates: Scylla ex machina

Authors: Y Gao, D Lee, G Burtch, S Fazelpour

Year: 2024

Published in: arXiv preprint arXiv:2410.19599, 2024 - arxiv.org

Institution: Boston University, Northeastern University

Research Area: LLMs as Human Surrogates, Social Science Research Methods, Human Behavior Simulation

Discipline: Economics, Artificial Intelligence, Social Science

LLMs fail to accurately replicate human behavior in the 11-20 money request game, cautioning against their use as surrogates for human cognition in social science research.

Methods: The study evaluates the reasoning depth of various advanced LLMs through their performance on the 11-20 money request game, analyzing failure points related to input language, roles, and safeguarding.

Key Findings: The ability of LLMs to replicate human-like behavior and reasoning distribution in the context of social science simulations.

Citations: 25
Utilizing human behavior modeling to manipulate explanations in AI-assisted decision making: the good, the bad, and the scary

Authors: Z Li, M Yin

Year: 2024

Published in: Advances in Neural Information Processing ..., 2024 - proceedings.neurips.cc

Institution: Purdue University

Research Area: Human Behavior Modeling, Explainable AI, Decision Making in AI systems.

Discipline: Artificial Intelligence, Behavioral Science

DOI: https://doi.org/10.52202/079017-0163

Citations: 7
Generative AI Triggers Welfare-Reducing Decisions in Humans

Authors: Fabian Dvorak, Regina Stumpf, Sebastian Fehrler, Urs Fischbacher

Year: 2024

Published in: ArXiv

Institution: University of Konstanz

Research Area: Generative AI and Human Decision-Making, Behavioral Economics

Discipline: Artificial Intelligence, Behavioral Economics
Motivation Matters: Challenges and Pit-Falls of Crowdsourced Online Studies

Authors: E Becks, V Matkovic, T Weis

Year: 2024

Published in: 2025 IEEE International Conference on ..., 2025 - computer.org

Institution: University of Stuttgart, University of Applied Sciences Offenburg, University of Hohenheim

Research Area: Crowdsourced Online Studies, Human-Computer Interaction (HCI) in AI Systems, Behavioral Research Methodology

Discipline: Human-Computer Interaction (HCI)
Influencing human-AI interaction by priming beliefs about AI can increase perceived trustworthiness, empathy and effectiveness

Authors: P Pataranutaporn, R Liu, E Finn, P Maes

Year: 2023

Published in: Nature Machine Intelligence, 2023 - nature.com

Institution: University of California Irvine

Research Area: Human-AI Interaction, Behavioral Science

Discipline: Human-Computer Interaction (HCI), Artificial Intelligence

DOI: https://doi.org/10.1038/s42256-023-00720-7

Citations: 180
The challenge of using LLMs to simulate human behavior: A causal inference perspective

Authors: G Gui, O Toubia

Year: 2023

Published in: arXiv preprint arXiv:2312.15524, 2023 - arxiv.org

Institution: University of Southern California, Columbia Business School

Research Area: LLMs and Causal Inference in Human Behavior Simulation, LLM

Discipline: Artificial Intelligence (cs.AI), Information Retrieval (cs.IR), Econometrics (econ.EM), Applications (stat.AP)

Citations: 76
Source-credibility information and social norms improve truth discernment and reduce engagement with misinformation online

Authors: T Prike, LH Butler, UKH Ecker

Year: 2023

Published in: Scientific Reports, 2024 - nature.com

Institution: University of Western Australia, University of Exeter, University of Cambridge

Research Area: Social Science, Misinformation, Human Behavior, Media Studies

Discipline: Social Science

DOI: https://doi.org/10.1038/s41598-024-57560-7

Citations: 45
What over 1,000,000 participants tell us about online research protocols

Authors: J Tomczak, A Gordon, J Adams, JS Pickering

Year: 2023

Published in: Frontiers in Human ..., 2023 - frontiersin.org

Institution: Prolific, University of Leeds, Gorilla

Research Area: Online Research Protocols, Human Neuroscience, Behavioral Research

Discipline: Human Neuroscience

Citations: 31
Uncalibrated models can improve human-ai collaboration

Authors: K Vodrahalli, T Gerstenberg

Year: 2022

Published in: Advances in Neural ..., 2022 - proceedings.neurips.cc

Institution: Columbia University, Princeton University, Intel, Stanford University, Massachusetts Institute of Technology

Research Area: Human-AI Collaboration, Human Behavior Modeling, Decision Making

Discipline: Artificial Intelligence

Citations: 70
AITurk: Using ChatGPT for social science research

Authors: X Qin, M Huang, J Ding

Year: 2022

Published in: Available at SSRN 4922861, 2024 - papers.ssrn.com

Institution: Peking University, Tsinghua University, Nankai University

Research Area: AI Social Science, LLM Simulation of Human Behavior, AI Simulation

Discipline: Social Science Research

DOI: https://ssrn.com/abstract=4922861

Citations: 17
Careless participants are essential for our phishing study: Understanding the impact of screening methods

Authors: T Matsuura, AA Hasegawa, M Akiyama

Year: 2021

Published in: Proceedings of the 2021 ..., 2021 - dl.acm.org

Institution: Waseda University

Research Area: Phishing Studies, Human-Computer Interaction (HCI), Behavioral Research Methods

Discipline: Human-Computer Interaction (HCI)

Citations: 25
Large language models and the wisdom of small crowds

Authors: S Trott

Year: 2021

Published in: Open Mind, 2024 - direct.mit.edu

Institution: Stanford University, Microsoft Research

Research Area: LLMs in Social Science Research, Crowdworking, Human Behavior Simulation

Discipline: Artificial Intelligence, Social Science, Information Systems

Citations: 22