Algorithmic Impact Reveals the Hidden Social Choice Structure of Alignment
cs.AI
Submitted: 2026-08-25
Updated: 2026-08-25
Code: https://github.com/michelleeesi/hiddenstructure
Terminology
Sources
- Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
- MaxMin-RLHF: Alignment with Diverse Human Preferences
- Direct Preference Optimization With Unobserved Preference Heterogeneity: The Necessity of Ternary Preferences
- Social Choice Should Guide AI Alignment in Dealing with Diverse Human Feedback
- Mapping Social Choice Theory to RLHF
- Distortion Under Public-Spirited Voting
- Distortion of AI Alignment: Does Preference Optimization Optimize for Preferences?
- Pairwise Calibrated Rewards for Pluralistic Alignment
- Personalized Language Modeling from Personalized Human Feedback
- RLHF from Heterogeneous Feedback via Personalization and Preference Aggregation
- Direct Alignment with Heterogeneous Preferences
- Distributional Preference Learning: Understanding and Accounting for Hidden Context in RLHF
- Mechanism Design for LLM Fine-tuning with Multiple Reward Models
- From Weights to Words: Expressing and Editing Preference Model Inferences in Natural Language
- Cultivating Pluralism In Algorithmic Monoculture: The Community Alignment Dataset
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection