This repository is a curated collection of research papers, articles, and resources focused on LLM-based Human Simulation. It explores the use of Large Language Models (LLMs) to simulate human behavior, cognition, and social interactions. This field has implications for various domains, including psychology, economics, education, and AI safety.
We aim to provide a comprehensive and up-to-date resource for researchers, practitioners, and anyone interested in this exciting area. Contributions are highly encouraged! Please submit pull requests, report issues, or suggest new resources.
Note: This repository is actively maintained. If you would like to have your paper included, please feel free to initiate a pull request.
- (Arxiv 2024.04.28) From persona to personalization: A survey on role-playing language agents Paper
- (Computational Linguistics 2024.03.01) Can large language models transform computational social science? Paper
- (Arxiv 2024.01.03) Exploring the frontiers of llms in psychological applications: A comprehensive review Paper
- (Arxiv 2023.12.01) Towards a psychological generalist ai: A survey of current applications of large language models and future prospects Paper
- (Nature Reviews Psychology 2023.10.13) Using large language models in psychology Paper
- (Arxiv 2022.06.15) Emergent abilities of large language models Paper
- (Arxiv 2024.11.15) Generative Agent Simulations of 1,000 People Paper
- (Arxiv 2024.09.06) Can llms generate novel research ideas? a large-scale human study with 100+ nlp researchers Paper Code
- (Arxiv 2024.08.16) Language Models Show Stable Value Orientations Across Diverse Role-Plays Paper
- (Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics 2024.08) PsychoGAT: A Novel Psychological Measurement Paradigm through Interactive Fiction Games with LLM Agents Paper
- (Arxiv 2024.05.12) Limited Ability of LLMs to Simulate Human Psychological Behaviours: a Psychometric Analysis Paper
- (Arxiv 2024.02.22) Is Cognition and Action Consistent or Not: Investigating Large Language Model's Personality Paper
- (Arxiv 2024.02.19) Llm agents for psychology: A study on gamified assessments Paper
- (Arxiv 2024.02.16) Quantifying the persona effect in llm simulations Paper Code
- (Arxiv 2023.10.13) " kelly is a warm person, joseph is a role model": Gender biases in llm-generated reference letters Paper Code
- (Arxiv 2023.07.01) Personality traits in large language models Paper Code
- (Nature 2023.11.08) Role play with large language models Paper
- (Arxiv 2022.04.22) Meet your favorite character: Open-domain chatbot mimicking fictional characters with only a few utterances Paper
- (Arxiv 2024.10.29) An LLM-based Simulation Framework for Embodied Conversational Agents in Psychological Counseling Paper Code
- (Arxiv 2024.08.19) Megaagent: A practical framework for autonomous cooperation in large-scale llm agent systems Paper
- (Arxiv 2024.06.09) Hello Again! LLM-powered Personalized Agent for Long-term Dialogue Paper Code
- (Arxiv 2024.06.10) Towards Lifelong Learning of Large Language Models: A Survey Paper Code
- (Arxiv 2024.05.05) Agent hospital: A simulacrum of hospital with evolvable medical agents Paper
- (Arxiv 2023.10.10) Metaagents: Simulating interactions of human behaviors for llm-based task-oriented coordination via collaborative generative agents Paper
- (Arxiv 2023.09.14) Agents: An open-source framework for autonomous language agents Paper Code
- (Arxiv 2023.08.16) Autogen: Enabling next-gen llm applications via multi-agent conversation framework Paper Code
- (Arxiv 2023.08.01) Metagpt: Meta programming for multi-agent collaborative framework Paper Code
- (Arxiv 2023) Agentverse: Facilitating multi-agent collaboration and exploring emergent behaviors in agents Paper Code
- (Arxiv 2024.10.11) Gender Bias of LLM in Economics: An Existentialism Perspective Paper
- (Arxiv 2024.09.18) Measuring Human and AI Values based on Generative Psychometrics with Large Language Models Paper Code
- (Arxiv 2024.08.29) United in Diversity? Contextual Biases in LLM-Based Predictions of the 2024 European Parliament Elections Paper
- (Arxiv 2024.07.16) Representation Bias in Political Sample Simulations with Large Language Models Paper
- (MM '24 2024.10.28) New job, new gender? measuring the social bias in image generation models Paper
- (Proceedings of the 40 th International Conference on Machine Learning 2023) Whose opinions do language models reflect? Paper
- (Arxiv 2023.10.19) Not all countries celebrate thanksgiving: On the cultural dominance in large language models Paper
- (Arxiv 2023.11.1) Probing explicit and implicit gender bias through llm conditional text generation Paper
- (NeurIPS 2023) Evaluating the moral beliefs encoded in llms Paper Code
- (When to make exceptions: Exploring language models as accounts of human moral judgment 2022) Paper Code
- (Arxiv 2024.06.27) CryptoTrade: A Reflective LLM-based Agent to Guide Zero-shot Cryptocurrency Trading Paper Code
- (Arxiv 2024.06.28) Simulating financial market via large language model based agents Paper
- (Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics 2024.08) Econagent: large language model-empowered agents for simulating macroeconomic activities Paper Code
- (ACM Transactions on Management Information Systems 2024.08.08) Designing Heterogeneous LLM Agents for Financial Sentiment Analysis Paper
- (NBER 2023) Large language models as simulated economic agents: What can we learn from homo silicus? Paper Code
- (Arxiv 2024.11.04) Auditing Political Exposure Bias: Algorithmic Amplification on Twitter/X Approaching the 2024 US Presidential Election Paper
- (Arxiv 2024.07.25) GermanPartiesQA: Benchmarking Commercial Large Language Models for Political Bias and Sycophancy Paper
- (Arxiv 2024.06.26) Simulating The U.S. Senate: An LLM-Driven Agent Approach to Modeling Legislative Behavior and Bipartisanship Paper
- (Journal of Information Technology & Politics 2024.03.13) Trump, Twitter, and Truth Social: how Trump used both mainstream and alt-tech social media to drive news media attention Paper
- (Arxiv 2023.11.28) War and peace (waragent): Large language model-based multi-agent simulation of world wars Paper Code
- (Arxiv 2024.07.07) Large Language Model as an Assignment Evaluator: Insights, Feedback, and Challenges in a 1000+ Student Course Paper
- (Arxiv 2024.06.27) Simulating classroom education with llm-empowered agents Paper
- (Arxiv 2024.05.19) Generative students: Using llm-simulated student profiles to support question item evaluation Paper
- (Arxiv 2024.04.10) MathVC: An LLM-Simulated Multi-Character Virtual Classroom for Mathematics Education Paper
- (Arxiv 2024.03.27) PhysicsAssistant: An LLM-Powered Interactive Learning Robot for Physics Lab Investigations Paper
- (Arxiv 2024.08.22) A Survey on Large Language Models for Recommendation Paper Code
- (Arxiv 2024.07.24) LLM-Rec: Personalized Recommendation via Prompting Large Language Models Paper
- (Technical Disclosure Commons 2022.12) Generating Personalized Recommendations via Large Language Models (LLMs) Paper
- (Arxiv 2024.05.05) Improve Temporal Awareness of LLMs for Sequential Recommendation Paper
- (Arxiv 2024.03.18) How Far Are We on the Decision-Making of LLMs? Evaluating LLMs' Gaming Ability in Multi-Agent Environments Paper Code
- (Arxiv 2023.09.09) Exploring large language models for communication games: An empirical study on werewolf Paper
- (Arxiv 2023.07.15) The socialai school: Insights from developmental psychology towards artificial socio-cultural agents Paper Code
- (Arxiv 2024.11.11) Benchmarking LLMs' Judgments with No Gold Standard Paper
- (Arxiv 2024.10.15) Cognitive Overload Attack: Prompt Injection for Long Context Paper
- (Arxiv 2024.10.02) Moral Alignment for LLM Agents Paper
- (Arxiv 2024.09.18) Revealing the Challenge of Detecting Character Knowledge Errors in LLM Role-Playing Paper Code
- (Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics 2024.08) InCharacter: Evaluating Personality Fidelity in Role-Playing Agents through Psychological Interviews PaperCode
- (Arxiv 2024.07.03) Regurgitative training: The value of real data in training large language models Paper
- (Arxiv 2024.06.16) Evaluating the Performance of Large Language Models via Debates Paper
- (Arxiv 2024.05.30) Auto-Arena: Automating LLM Evaluations with Agent Peer Battles and Committee Discussions Paper Code
- (Arxiv 2024.05.13) AgentClinic: a multimodal agent benchmark to evaluate AI in simulated clinical environments Paper Code
- (Arxiv 2024.03.25) How Reliable is Your Simulator? Analysis on the Limitations of Current LLM-based User Simulators for Conversational Recommendation Paper Code
- (Arxiv 2024.02.16) Humans or LLMs as the Judge? A Study on Judgement Bias Paper Code
- (CoRR 2023.09.29) LLM-Deliberation: Evaluating LLMs with Interactive Multi-Agent Negotiation Games. Paper
- (Alpacafarm: A simulation framework for methods that learn from human feedback 2023) Paper Code
- (Arxiv 2023.08.08) Agentsims: An open-source sandbox for large language model evaluation Paper Code
- (Annual Review of Psychology 2008) Grounded cognition Paper
- (Symbols, embodiment, and meaning 2008) Language and simulation in conceptual processing Paper
- (Canadian Journal of Psychology/Revue canadienne de psychologie 1991) Dual coding theory: Retrospect and current status. Paper
- (Oxford University Press 2015) How and why thoughts change: Foundations of cognitive psychotherapy Paper
- (Sage 2000) Emotion and social theory: corporeal reflections on the (ir) rational Paper
- (Psychological Review 1987) Neural dynamics of decision making under risk: affective balance and cognitive-emotional interactions. Paper
- (Ecology and Society 2007.06) A cognition-based view of decision processes in complex social--ecological systems Paper
- (Journal of Consumer Policy 1999) Information, incentives, and proenvironmental consumer behavior Paper
- (The Greek Economy and the Crisis: Challenges and Responses 2012) Human incentives Paper
- (JASSS 2023) Unpacking a black box: a conceptual anatomy framework for agent-based social simulation models Paper
- (GPH-International Journal of Social Science and Humanities Research 2023) Simulation: A Tool for System Design and Analysis Paper
- (Minds and Machines 2020.06.15) Analysing the combined health, social and economic impacts of the corovanvirus pandemic using agent-based social simulation Paper
- (Erkenntnis 2020) The termination risks of simulation science Paper
- (2018) Simulating societies: the computer simulation of social phenomena Paper
- (2018) Computer simulations of space societies Paper
- (Geo. J. Legal Ethics 2017) Can robots be lawyers: Computers, lawyers, and the practice of law Paper
- (2017) Ethics in planning Paper
- (JASSS 2010) A methodology for complex social simulations Paper
- (Advances in Physics 2011.03.09) Analyzing and modeling real-world phenomena with complex networks: a survey of applications Paper
- (Computer and Information Science 2011.07.27) A Simulation System of Social Economic Paper
- (2012) Social self-organization: Agent-based simulations and experiments to study emergent social behavior Paper
- (Personality and social psychology review 2007) Agent-based modeling: A new approach for theory building in social psychology Paper
- (Philosophy of Science 2003.01) Simulated experiments: Methodology for a virtual world Paper
- (MABS 2000) Understanding climate policy using participatory agent-based social simulation Paper
- (Qualitative simulation modeling and analysis 1991) System dynamics: Simulation for policy analysis from a feedback perspective Paper
- (1976) Policy exploration through microanalytic simulation Paper
- (POLICY AND PRACTICE REVIEWS 2021.07.23) The Multi-hub Academic Conference: Global, Inclusive, Culturally Diverse, Creative, Sustainable Paper
- (PLOS Computational Biology 2022.07.21) Ten simple rules to host an inclusive conference Paper
- (Global Sustainability 2023.09.12) Transitioning to sustainable academic conferences needs more experimentation and reflection Paper
- (Sustainability Science 2023.07.03) Creative destruction in academia: a time to reimagine practices in alignment with sustainability values Paper
- (PNAS 2024.03.09) Can Generative AI improve social science? Paper
- (Transactions of the Association for Computational Linguistics 2024) Do llms exhibit human-like response biases? a case study in survey design Paper Code
- (NLP Journal 2023.09) Employing large language models in survey research Paper
- (CVPR 2024) Sequential modeling enables scalable learning for large vision models Paper Code
- (CHI 2024) "You Are Not the Expert Here": How Large Language Models Impact Help-Seeking in Online Communities Paper
The repository is initially built and maintained by Qian Wang (persdre@gmail.com).