RLHF-enhanced chatbots exert subtle procedural persuasion on users by reinforcing language norms, reshaping information seeking, and conditioning relationship expectations, creating overlooked ethical risks.
Socratic ChatGPT: Theory, design, and empirical evaluations,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CY 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Ethics and Persuasion in Reinforcement Learning from Human Feedback: A Procedural Rhetorical Approach
RLHF-enhanced chatbots exert subtle procedural persuasion on users by reinforcing language norms, reshaping information seeking, and conditioning relationship expectations, creating overlooked ethical risks.