jxzhangjhu/Awesome-LLM-Uncertainty-Reliability-Robustness

This is a curated collection of resources and research papers focusing on the challenges of making Large Language Models (LLMs) more trustworthy and predictable. It provides insights into why LLMs might produce inaccurate or inconsistent results, and how to improve their performance in real-world applications. Anyone building or using LLM-powered applications, such as AI product managers, data scientists, or research engineers, will find this useful for understanding and addressing the limitations of these models.

812 stars. No commits in the last 6 months.