Do People Trust AI Assistants Even When They Are Consistently Wrong?
cs.HC, cs.CL
Submitted: 2026-11-10
Updated: 2026-11-10
Terminology
Sources
- Concrete Problems in AI Safety
- International AI Safety Report 2026
- Sabotage Evaluations for Frontier Models
- Artificial Influence: An Analysis Of AI-Driven Persuasion
- A Mechanism-Based Approach to Mitigating Harms from Persuasive Generative AI
- Generative Language Models and Automated Influence Operations: Emerging Threats and Potential Mitigations
- AI out-persuades expert humans in text-based dialogue
- When Large Language Models are More PersuasiveThan Incentivized Humans, and Why
- Debate Helps Supervise Unreliable Experts
- Persuasion with Large Language Models: A Survey of Empirical Evidence, Study Methodologies, and Ethical Implications
- Evaluating Frontier Models for Dangerous Capabilities
- GPQA: A Graduate-Level Google-Proof Q&A Benchmark
- Who's in Charge? Disempowerment Patterns in Real-World LLM Usage
- Experimental Evidence That Conversational Artificial Intelligence Can Steer Consumer Behavior Without Detection
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