Process for Adapting Language Models to Society (PALMS) with Values-Targeted Datasets

Understand

Language models can generate harmful and biased outputs and exhibit undesirable behavior according to a given cultural context.

• We propose a Process for Adapting Language Models to Society (PALMS) with Values-Targeted Datasets, an iterative process to significantly change model behavior by crafting and fine-tuning on a dataset that reflects a predetermined set of target values.
• We evaluate our process using three metrics: quantitative metrics with human evaluations that score output adherence to a target value, toxicity scoring on outputs; and qualitative metrics analyzing the most common word associated with a given social category.
• Through each iteration, we add additional training dataset examples based on observed shortcomings from evaluations.