She had Cobalt Blue Eyes: Prompt Testing to Create Aligned and Sustainable Language Models
This work addresses the risk of LLM misuse for society by providing a method to enhance model alignment, though it appears incremental as it builds on existing prompting techniques.
The paper tackles the problem of ensuring large language models (LLMs) are aligned with societal ethical standards by introducing a test suite of prompts to evaluate and improve model fairness, safety, and robustness, showing that prompting at all development stages leads to more responsible models and highlighting a gap between societal alignment and current LLM capabilities.
As the use of large language models (LLMs) increases within society, as does the risk of their misuse. Appropriate safeguards must be in place to ensure LLM outputs uphold the ethical standards of society, highlighting the positive role that artificial intelligence technologies can have. Recent events indicate ethical concerns around conventionally trained LLMs, leading to overall unsafe user experiences. This motivates our research question: how do we ensure LLM alignment? In this work, we introduce a test suite of unique prompts to foster the development of aligned LLMs that are fair, safe, and robust. We show that prompting LLMs at every step of the development pipeline, including data curation, pre-training, and fine-tuning, will result in an overall more responsible model. Our test suite evaluates outputs from four state-of-the-art language models: GPT-3.5, GPT-4, OPT, and LLaMA-2. The assessment presented in this paper highlights a gap between societal alignment and the capabilities of current LLMs. Additionally, implementing a test suite such as ours lowers the environmental overhead of making models safe and fair.