Whose Guardrail? User Identity Shapes the Effectiveness of Model Disclaimers in Mitigating LLM Political Persuasion
cs.HC
Submitted: 2026-11-03
Updated: 2026-11-10
Terminology
Sources
- Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned
- Warning labels shift perceptions of sycophantic AI, but not its influence
- Your Brain on ChatGPT: Accumulation of Cognitive Debt when Using an AI Assistant for Essay Writing Task
- NRC VAD Lexicon v2: Norms for Valence, Arousal, and Dominance for over 55k English Terms
- IssueBench: Millions of Realistic Prompts for Measuring Issue Bias in LLM Writing Assistance
- Political Neutrality as Balanced Approval: A Large-Scale Human Evaluation of AI Responses
- Individual-level interventions against sycophantic AI reduce its appeal but not its persuasiveness
Related papers
- EmoPhone: A Multi-Wave Dataset for In-the-Wild Mobile and Wearable Affect Sensing
- Tasteply: Externalizing Stable and Situational Preference as Manipulable Spatial Objects
- Shielded Trajectory Sampling for Personalized Relational Safety in Conversational AI
- From Tasks to Turns: Measuring Human Labor Contributions in Human-Agent Joint Production
- Reconstruction and Reflection of Positive Experiences through Resurfacing Laughter-indexed Everyday Moments
- LLM-Assisted Reranking to Operationalize Nuanced Objectives in Recommender Systems