Similar Items: Learning to Optimize Multi-Objective Alignment Through Dynamic Reward Weighting
- Fine-Grained Reward Optimization for Machine Translation using Error Severity Mappings
- Aligned Probing: Relating Toxic Behavior and Model Internals
- Goal Alignment in LLM-Based User Simulators for Conversational AI
- Beyond the Curriculum: Aligning Critical Thinking Instruction with the Saudi Vision 2030 Human Capability Framework
- PsyMem: Fine-grained Psychological Alignment and Explicit Memory Control for Advanced Role-Playing LLMs
- Multi-scale and cardinality-based backbone: toward learning a general-purpose speaker representation