Aligning Language Models with Selective Prediction

Large language models (LLMs) are increasingly deployed as critical decision-making components in high-stakes real-world AI systems, rendering LLM reliability a foremost practical concern.

Large language models (LLMs) are increasingly deployed as critical decision-making components in high-stakes real-world AI systems, rendering LLM reliability a foremost practical concern. In this paper, we focus on enhancing LLM reliability through selective prediction (SP), a…