ACL 2025finding0 citations
Not quite Sherlock Holmes: Language model predictions do not reliably differentiate impossible from improbable events
James A. Michaelov, Reeka Estacio, Zhien Zhang, Ben Bergen
Abstract
Can language models reliably predict that possible events are more likely than merely improbable ones? By teasing apart possibility, typicality, and contextual relatedness, we show that despite the results of previous work, language models’ ability to do this is far from robust. In fact, under certain conditions, all models tested—including Llama 3, Gemma 2, and Mistral NeMo—perform at worse-than-chance level, assigning higher probabilities to impossible sentences such as ‘the car was given a parking ticket by the brake’ than to merely unlikely sentences such as ‘the car was given a parking ticket by the explorer’.
BibTeX
@inproceedings{michaelov-etal-2025-quite,
title = "Not quite Sherlock Holmes: Language model predictions do not reliably differentiate impossible from improbable events",
author = "Michaelov, James A. and
Estacio, Reeka and
Zhang, Zhien and
Bergen, Ben",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-acl.696/",
doi = "10.18653/v1/2025.findings-acl.696",
pages = "13528--13551",
ISBN = "979-8-89176-256-5"
}