SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2212.01488 · 2022

Event knowledge in large language models: the gap between the impossible and the unlikely

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Word co-occurrence patterns in language corpora contain a surprising amount of conceptual knowledge. Large language models (LLMs), trained to predict words in context, leverage these patterns to achieve impressive performance on diverse semantic tasks requiring world knowledge. An important but understudied question about LLMs' semantic abilities is whether they acquire generalized knowledge of common events. Here, we test whether five pre-trained LLMs (from 2018's BERT to 2023's MPT) assign higher likelihood to plausible descriptions of agent-patient interactions than to minimally different implausible versions of the same event. Using three curated sets of minimal sentence pairs (total n=1,215), we found that pre-trained LLMs possess substantial event knowledge, outperforming other distributional language models. In particular, they almost always assign higher likelihood to possible vs. impossible events (The teacher bought the laptop vs. The laptop bought the teacher). However, LLMs show less consistent preferences for likely vs. unlikely events (The nanny tutored the boy vs. The boy tutored the nanny). In follow-up analyses, we show that (i) LLM scores are driven by both plausibility and surface-level sentence features, (ii) LLM scores generalize well across syntactic variants (active vs. passive constructions) but less well across semantic variants (synonymous sentences), (iii) some LLM errors mirror human judgment ambiguity, and (iv) sentence plausibility serves as an organizing dimension in internal LLM representations. Overall, our results show that important aspects of event knowledge naturally emerge from distributional linguistic patterns, but also highlight a gap between representations of possible/impossible and likely/unlikely events.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2212.01488")
get_code_for_paper("2212.01488")
have("2212.01488")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2212.01488.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2212.01488.svg)](https://syntology.ai/paper/2212.01488)

Connect an agent — have() is free.