2025
Evaluating Large Language Models through Role-Guide and Self-Reflection: A Comparative Study
ICLR 2025poster
Large Language Models fine-tuned with Reinforcement Learning from Human Feedback (RLHF-LLMs) can over-rely on aligned preferences without truly gaining self-knowledge, leading to hallucination and biases. If an LLM can better access its knowledge and know what it knows, it can avoid making false or…