Rarely a problem? Language models exhibit inverse scaling in their predictions following few-type quantifiers

Abstract: How well do LLMs deal with quantification? In this study, we focus on 'few'-type quantifiers, as in 'few children like toys', which might pose a particular challenge for LLMs because the sentence components with out the quantifier are likely to co-occur, and 'few'-type quantifiers are rare. We present 960 English sentence stimuli from two human neurolinguistic experiments to 22 autoregressive transformer models of differing sizes. Not only do all the models perform poorly on 'few'-type quantifiers, but overall the larger the model, the worse its performance. This inverse scaling is consistent with previous work suggesting that larger models increasingly reflect online rather than offline human processing, and we argue that the decreasing performance of larger models may challenge uses of LLMs as the basis for natural language systems.