Just like how we tend to focus on adding new explanations and ideas, it seems that the English language has a bias towards addition as well. Our language is filled with words that express more and increase, while words that represent subtraction or decrease are less common. This tendency is not only reflected in the frequency of words, but also in the order they appear in expressions. We instinctively say ‘add and subtract’ instead of ‘subtract and add.’ The way we talk about change also leans towards addition, with verbs like ‘improve’ and ‘transform’ having more overlap with addition-related words. The connotations associated with addition are generally positive, while subtraction is often seen as negative. Surprisingly, even advanced language models like GPT-3 exhibit this bias. These findings shed light on cognitive biases and decision-making processes. To explore further about this bias in English language statistics, check out the underlying research!

Abstract
We have evolved to become who we are, at least in part, due to our general drive to create new things and ideas. When seeking to improve our creations, ideas, or situations, we systematically overlook opportunities to perform subtractive changes. For example, when tasked with giving feedback on an academic paper, reviewers will tend to suggest additional explanations and analyses rather than delete existing ones. Here, we show that this addition bias is systematically reflected in English language statistics along several distinct dimensions. First, we show that words associated with an increase in quantity or number (e.g., add, addition, more, most) are more frequent than words associated with a decrease in quantity or number (e.g., subtract, subtraction, less, least). Second, we show that in binomial expressions, addition-related words are mentioned first, that is, add and subtract rather than subtract and add. Third, we show that the distributional semantics of verbs of change, such as to improve and to transform, overlap more with the distributional semantics of add/increase than subtract/decrease, which suggests that change verbs are implicitly biased toward addition. Fourth, addition-related words have more positive connotations than subtraction-related words. Fifth, we demonstrate that state-of-the-art large language models, such as the Generative Pre-trained Transformer (GPT-3), are also biased toward addition. We discuss the implications of our results for research on cognitive biases and decision-making.

Read Full Article (External Site)