D comprises 52.6k question-answer pairs from 16 countries/regions,

LLMs excel at few-shot in-context learning (ICL) - learning from a few input-output examples ("shots") provided in context at inference, without any weight updates.

However, progress is limited by a lack of standardized datasets and comparison metrics, causing methods to be compared in an ad hoc manner.

In reinforcement learning (RL), a recurring goal is to find a diverse set of high-valued state-action trajectories according to a reward function.

Panacea trains a single model capable of adapting online and Pareto-optimally to diverse sets of preferences without the need for further tuning.