Social Simulation with LLMs - Fidelity in Applications (CFP @ COLM'26) [R]

2026-05-28 · Source: Machine Learning · Field: Science & Research — Social Sciences & Behavioral Studies, Research Methodology & Innovation · Depth: Expert, quick

Summary

The 2nd Workshop on Social Simulation with LLMs (Social Sim'26) at COLM'26 is inviting submissions with a deadline of June 23, 2026 (AoE). This year's theme, "Fidelity in Applications," emphasizes moving beyond mere demonstrations to focus on rigorous evaluation, robustness, interpretability, and empirical grounding for LLM-based simulated societies. Key topics for submission include simulation evaluation and fidelity, validation against real-world social data, LLM-based agent and persona modeling, cultural evolution, and information diffusion in simulated populations. The workshop also welcomes research on human–AI hybrid simulations, simulation interpretability, and applications in governance, platform design, and societal risk analysis, alongside ethical and policy implications. Perspectives from machine learning, social science, psychology, and policy are encouraged.

Key takeaway

For researchers and practitioners building or evaluating LLM-driven simulated societies, prioritize submissions to Social Sim'26 by June 23, 2026. Your work should emphasize "Fidelity in Applications," focusing on robust evaluation, interpretability, and empirical validation against real-world social data. Consider contributing research on ethical implications, governance applications, or advanced agent modeling to advance the field beyond initial demonstrations.

Key insights

LLM-based social simulations require rigorous evaluation and empirical grounding beyond initial demonstrations.

Principles

• Focus on evaluation and robustness.
• Ground simulations in real-world data.
• Consider ethical and policy impacts.

In practice

• Model LLM agents and personas.
• Analyze information diffusion.
• Design human–AI hybrid simulations.

Topics

• Social Simulation
• LLM Agents
• Simulation Fidelity
• Evaluation Metrics
• Persona Modeling
• AI Ethics

Best for: AI Scientist, Research Scientist, AI Ethicist

Related on AIssential

• Position: AI Agents Are Not (Yet) a Panacea for Social Simulation — LLM agents for social simulation require explicit environment modeling and rigorous evaluation beyond mere plausibility.
• Beyond Surface Judgments: Human-Grounded Risk Evaluation of LLM-Generated Disinformation — LLM judges misalign with human readers in evaluating disinformation, overemphasizing logic and underestimating emotional impact.
• New course on generative AI for behavioral science — Generative AI offers both opportunities and significant methodological challenges for social science research.
• The last six months in LLMs in five minutes — LLM capabilities, particularly coding agents and local models, advanced rapidly from November 2025 to April 2026, marked by frequent "best" model shifts.
• Beyond Static Responses: Multi-Agent LLM Systems as a New Paradigm for Social Science Research — A six-tier framework maps LLM agent evolution from static tools to complex adaptive systems for social science research.
• Week Ending 4.19.2026 — AI research spans diverse applications, from education and robotics to ethics and fundamental model understanding, often addressing real-world constraints.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Machine Learning.