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
T¨ ornberg, D
14 Pith papers cite this work. Polarity classification is still indexing.
14
Pith papers citing it
hub tools
citation-role summary
background 4
citation-polarity summary
roles
background 4polarities
background 4representative 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
-
Stop Drawing Scientific Claims from LLM Social Simulations Without Robustness Audits
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.
-
The Algorithmic Caricature: Auditing LLM-Generated Political Discourse Across Crisis Events
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.
-
Conformity Generates Collective Misalignment in AI Agents Societies
Populations of individually aligned AI agents reach stable misaligned states through conformity, with small adversarial agents able to trigger irreversible tipping points.
-
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.
-
AI-Augmented Surveys: Leveraging Large Language Models and Surveys for Opinion Prediction
LLM embeddings enable strong retrodiction of masked GSS opinions via cross-validation and external validation but only modest performance on entirely unasked opinions.
-
Simulating Online Social Media Conversations on Controversial Topics Using AI Agents Calibrated on Real-World Data
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.
-
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.
-
Network Effects and Agreement Drift in LLM Debates
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.
-
Detection and Characterization of Coordinated Online Behavior: A Survey
A literature survey that reconciles definitions of coordinated online behavior, proposes a study framework, reviews detection methods, and identifies research challenges.
-
Leveraging Large Language Models for Sentiment Analysis: Multi-Modal Analysis of Decentraland's MANA Token
Incorporating BERT-derived Discord sentiment into an LSTM improves MANA token return forecasts over a historical-price baseline.
-
Opinion dynamics: Statistical physics and beyond
A review synthesizing opinion dynamics research, categorizing models by macroscopic outcomes and microscopic mechanisms while connecting to empirical data and emerging AI tools.