COLM 2025PastLarge language models
First Workshop on Social Simulation with LLMs
Social Sim'25
- Submission deadline
- Jun 28, 2025, 04:00 UTCimported from OpenReview — check the website for extensions
- Submission portal
- OpenReview
- Notes
- Topics were auto-suggested and may be imprecise — edits welcome.
Accepted papers (26)
Fetched from OpenReview (v2) on 2026-06-11.
Agent-to-Agent Theory of Mind: Testing Interlocutor Awareness among Large Language Models
Algorithmic Fidelity of Large Language Models in Generating Synthetic German Public Opinions: A Case Study
All Norms and No Nuance Make LLMs Dull Cultural Simulators
Can LLMs Imitate Social Media Dialogue? Techniques for calibration and BERT-based Turing-Test
Can LLMs Simulate Personas with Reversed Performance? A Systematic Investigation for Counterfactual Instruction Following in Math Reasoning Context
Cooperative Behaviour in LLMs via Cultural Evolution of Norms and Strategies
Deep Binding of Language Model Virtual Personas: a Study on Approximating Political Partisan Misperceptions
Distributional Alignment for Social Simulation with LLMs: A Prompt Mixture Modeling Approach
Do Role-Playing Agents Practice What They Preach? Belief-Behavior Alignment in LLM-Based Simulations of Human Trust
Drawing Reliable Conclusions with Synthetic Simulations from Large Language Models
GOVSIM-ELECT: Elections in AI Societies
Investigating Moral Evolution Via LLM-Based Agent Simulation
Language Model Fine-Tuning on Scaled Survey Data for Predicting Distributions of Public Opinions
Language Models Might Not Understand You: Evaluating Theory of Mind via Story Prompting
LLM Generated Persona is a Promise with a Catch
Morals and Reasoning: Formalizing Moral Influence on Reasoning and AI Systems Alignment
NegotiationGym: Self-Optimizing Agents in a Multi-Agent Social Simulation Environment
NormLens: Massively Multicultural MLLM Reasoning with Fine-Grained Social Awareness
Persona-Assigned Large Language Models Exhibit Human- Like Motivated Reasoning
Poor Alignment and Steerability of Large Language Models: Evidence Using 30,000 College Admissions Essays
SimBench: Benchmarking the Ability of Large Language Models to Simulate Human Behaviors
SocialMaze: A Benchmark for Evaluating Social Reasoning in Large Language Models
SocioSim: A Framework for Rapid, Policy-Relevant Audience Simulation
Twin-2K-500: A dataset for building digital twins of over 2,000 people based on their answers to over 500 questions
WHEN TO ACT, WHEN TO WAIT: Modeling the Intent-Action Alignment Problem in Dialogue
Wisdom of the Machines: Exploring Collective Intelligence in LLM Crowds