This article surveys and organizes research works in a new paradigm in natural language
processing, which we dub “prompt-based learning.” Unlike traditional supervised learning …

Large language models (LLMs) have demonstrated remarkable capabilities across a wide
range of tasks in various domains. Despite their impressive performance, they can be …

Abstract Direct Preference Optimization (DPO) is a widely used offline preference
optimization algorithm that reparameterizes reward functions in reinforcement learning from …

Large language models (LLMs) can perform complex reasoning by generating intermediate
reasoning steps. Providing these steps for prompting demonstrations is called chain-of …

Few-shot learning is a challenging task that requires language models to generalize from
limited examples. Large language models like GPT-3 and PaLM have made impressive …

Abstract Language models (LMs) often struggle to pay enough attention to the input context,
and generate texts that are unfaithful or contain hallucinations. To mitigate this issue, we …

Large language models (LMs) are able to in-context learn--perform a new task via inference
alone by conditioning on a few input-label pairs (demonstrations) and making predictions for …

Large language models (LLMs) transfer well to new tasks out-of-the-box simply given a
natural language prompt that demonstrates how to perform the task and no additional …

In-context learning is a recent paradigm in natural language understanding, where a large
pre-trained language model (LM) observes a test instance and a few training examples as …

This paper explores a simple method for improving the zero-shot learning abilities of
language models. We show that instruction tuning--finetuning language models on a …