When Language Models Fall in Love: Animacy Processing in Transformer Language Models

TL;DR

This paper investigates how transformer language models process animacy, revealing that they behave similarly to humans with typical entities and adapt to atypical cases, despite limited extralinguistic information.

Contribution

The study demonstrates that transformer LMs can recognize and adapt to animacy cues in language, even when such cues are subtle or atypical, highlighting their nuanced semantic understanding.

Findings

LMs behave like humans with typical animacy entities

LMs adapt to atypical animacy in stories

Even brief context cues influence LM behavior

Abstract

Animacy - whether an entity is alive and sentient - is fundamental to cognitive processing, impacting areas such as memory, vision, and language. However, animacy is not always expressed directly in language: in English it often manifests indirectly, in the form of selectional constraints on verbs and adjectives. This poses a potential issue for transformer language models (LMs): they often train only on text, and thus lack access to extralinguistic information from which humans learn about animacy. We ask: how does this impact LMs' animacy processing - do they still behave as humans do? We answer this question using open-source LMs. Like previous studies, we find that LMs behave much like humans when presented with entities whose animacy is typical. However, we also show that even when presented with stories about atypically animate entities, such as a peanut in love, LMs adapt: they treat these entities as animate, though they do not adapt as well as humans. Even when the context indicating atypical animacy is very short, LMs pick up on subtle clues and change their behavior. We conclude that despite the limited signal through which LMs can learn about animacy, they are indeed sensitive to the relevant lexical semantic nuances available in English.