Stayin' Aligned Over Time: Towards Longitudinal Human-LLM Alignment via Contextual Reflection and Privacy-Preserving Behavioral Data
cs.HC
Submitted: 2026-05-05
Updated: 2026-11-03
Terminology
Sources
- Concrete Problems in AI Safety
- Same Performance, Hidden Bias: Evaluating Hypothesis- and Recommendation-Driven AI
- AI-Wrapped: Participatory, Privacy-Preserving Measurement of Longitudinal LLM Use In-the-Wild
- AI safety via debate
- Lessons from Real-World Deployment of a Cognition-Preserving Writing Tool: Students Actively Engage with Critical Thinking and Planning Affordances
- Editrail: Understanding AI Usage by Visualizing Student-AI Interaction in Code
- WildChat: 1M ChatGPT Interaction Logs in the Wild
- Fine-Tuning Language Models from Human Preferences
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
- Reconstruction and Reflection of Positive Experiences through Resurfacing Laughter-indexed Everyday Moments
- LLM-Assisted Reranking to Operationalize Nuanced Objectives in Recommender Systems
- Explainable Iterative Data Visualization Refinement via an LLM Agent