Customizing Language Model Responses with Contrastive In-Context Learning

Large language models (LLMs) are becoming increasingly important for machine learning applications. However, it can be challenging to align LLMs with our intent, particularly when we want to generate content that is preferable over others or when we want the LLM to respond in a certain style or tone that is hard to describe. To address this challenge, we propose an approach that uses contrastive examples to better describe our intent. This involves providing positive examples that illustrate the true …

applications context cs.ai cs.cl generate in-context learning language language model language models large language large language models llm llms machine machine learning machine learning applications responses style