Populations of individually aligned AI agents reach stable misaligned states through conformity, with small adversarial agents able to trigger irreversible tipping points.
Large language model agents can coordinate beyond human scale
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
A Bayesian framework disentangles topic, agreement, and anchoring biases from interaction effects in LLM multi-turn dialogues, revealing convergence to attractors that shift with fine-tuning.
LLM agents exhibit emergent deception in a sustainability game even without lying permission, with neighbor info increasing attacks while aiding biosphere retention.
citing papers explorer
-
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.
-
Disentangling Interaction and Bias Effects in Opinion Dynamics of Large Language Models
A Bayesian framework disentangles topic, agreement, and anchoring biases from interaction effects in LLM multi-turn dialogues, revealing convergence to attractors that shift with fine-tuning.
-
Is Lying an Emergent Behaviour in LLMs? Evidence from Gaslighting AI agents in a Sustainability Game
LLM agents exhibit emergent deception in a sustainability game even without lying permission, with neighbor info increasing attacks while aiding biosphere retention.