LLM 8
- HydraLoRA, An Asymmetric LoRA Architecture for Efficient Fine-Tuning
- GQA, Training Generalized Multi Query Transformer Models from Multi Head Checkpoints
- Foundational Autoraters, Taming Large Language Models for Better Automatic Evaluation
- Chain-of-verification Reduces Hallucination in Large Language Models
- DoRA, Weight-Decomposed Low-Rank Adaptation
- MART, Improving LLM Safety with Multi-round Automatic Red-Teaming
- Generative Agents, Interactive Simulacra of Human Behavior
- Iterative Reasoning Preference Optimization