Recent language models, such as GPT -3+ [Brown et al., 2020, Achiam et al., 2023], have demonstrated Recent attempts to understand in-context learning have focused on various aspects. On the practical side, research has investigated the impact of different factors on in-context learning.

Despite significant progress inthisarea, anessential factor often remains overlooked:geo-diversity. Recognizing and incorporating geographical variations [41, 40, 4, 10, 31, 6] in safety principles is crucial in the global landscape of LLM safety. Cultural norms and legal frameworks vary widely, resulting in diverse definitions of safe and acceptable behavior. As shown in Figure 1, while giving a green hatasagift might bebenign inmanycultures, itisconsidered offensiveinChina.

In table 3, we demonstrate the prompt for textualized recaptioning.

Transformers learn to approximate second-order optimization methods for ICL.

We further design an expert-wise training strategy to alleviate the impact of unhelpful demonstrations when optimizing the retriever model.

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.

Visual In-Context Learning (VICL) is a prevailing way to transfer visual foundation models to new tasks by leveraging contextual information contained in in-context examples to enhance learning and prediction of query samples.