Minor perturbations in persona format, instruction framing, and network structure shift cooperation by up to 76 percentage points and polarization metrics consistently, showing that LLM social simulations require per-claim robustness audits via the new TRAILS taxonomy.
hub Canonical reference
Simulating Social Media Using Large Language Models to Evaluate Alternative News Feed Algorithms
Canonical reference. 100% of citing Pith papers cite this work as background.
14
Pith papers citing it
Background
100% of classified citations
hub tools
citation-role summary
background 5
citation-polarity summary
roles
background 5polarities
background 5representative citing papers
LLM-generated political discourse across crises is fluent yet caricatured: more negative, less emotionally varied, more structurally regular, and lexically abstract than observed online populations.
Populations of individually aligned AI agents reach stable misaligned states through conformity, with small adversarial agents able to trigger irreversible tipping points.
LLMs organize prompted social roles along a dominant, stable, and causally steerable granularity axis in representation space that runs from micro to macro levels.
HotComment is a new multimodal benchmark that quantifies online comment popularity via content quality assessment, interaction-based prediction, and agent-simulated user engagement, accompanied by the StyleCmt stylistic model.
discourse_simulator is an open-source LLM-augmented agent-based modeling framework for simulating attitude diffusion on social networks in response to real-world events such as the 2025 Dublin anti-immigration march.
The paper formalizes three types of pluralistic AI models and three benchmark classes, arguing that current alignment techniques may reduce rather than increase distributional pluralism.
LLM embeddings enable strong retrodiction of masked GSS opinions via cross-validation and external validation but only modest performance on entirely unasked opinions.
LLM agents calibrated on Italian election data produce coherent posts and realistic network structure but show less tone and toxicity variation than real users, with opinion changes resembling traditional mathematical models.
Introduces PAS and FAS task abstractions plus the LLM-S^3 benchmark to evaluate LLMs on generating sociodemographic survey responses across 11 real datasets and multiple models.
LLM agents in controlled network debates show agreement drift toward specific opinion positions, requiring separation of structural effects from LLM biases before using them as human behavioral proxies.
A literature survey that reconciles definitions of coordinated online behavior, proposes a study framework, reviews detection methods, and identifies research challenges.
Incorporating BERT-derived Discord sentiment into an LSTM improves MANA token return forecasts over a historical-price baseline.
A review synthesizing opinion dynamics research, categorizing models by macroscopic outcomes and microscopic mechanisms while connecting to empirical data and emerging AI tools.
citing papers explorer
-
The Granularity Axis: A Micro-to-Macro Latent Direction for Social Roles in Language Models
LLMs organize prompted social roles along a dominant, stable, and causally steerable granularity axis in representation space that runs from micro to macro levels.
-
HotComment: A Benchmark for Evaluating Popularity of Online Comments
HotComment is a new multimodal benchmark that quantifies online comment popularity via content quality assessment, interaction-based prediction, and agent-simulated user engagement, accompanied by the StyleCmt stylistic model.
-
LLM-Agent-based Social Simulation for Attitude Diffusion
discourse_simulator is an open-source LLM-augmented agent-based modeling framework for simulating attitude diffusion on social networks in response to real-world events such as the 2025 Dublin anti-immigration march.
-
A Roadmap to Pluralistic Alignment
The paper formalizes three types of pluralistic AI models and three benchmark classes, arguing that current alignment techniques may reduce rather than increase distributional pluralism.
-
Large Language Models as Virtual Survey Respondents: Evaluating Sociodemographic Response Generation
Introduces PAS and FAS task abstractions plus the LLM-S^3 benchmark to evaluate LLMs on generating sociodemographic survey responses across 11 real datasets and multiple models.