Steering language models with intermittent implicit trait reinforcements reduces misalignment contagion in multi-agent social dilemma games more effectively than system prompt repetition.
Incharacter: Evaluating personality fidelity in role-playing agents through psychological interviews
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Mitigating Misalignment Contagion by Steering with Implicit Traits
Steering language models with intermittent implicit trait reinforcements reduces misalignment contagion in multi-agent social dilemma games more effectively than system prompt repetition.