Rolling the DICE on Idiomaticity: How LLMs Fail to Grasp Context

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F26%3AX3CS2S63" target="_blank" >RIV/00216208:11320/26:X3CS2S63 - isvavai.cz</a>

Result on the web

<a href="https://aclanthology.org/2025.acl-long.362/" target="_blank" >https://aclanthology.org/2025.acl-long.362/</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.18653/v1/2025.acl-long.362" target="_blank" >10.18653/v1/2025.acl-long.362</a>

Result language

angličtina

Original language name

Rolling the DICE on Idiomaticity: How LLMs Fail to Grasp Context

Original language description

Human processing of idioms heavily depends on interpreting the surrounding context in which they appear. While large language models (LLMs) have achieved impressive performance on idiomaticity detection benchmarks, this success may be driven by reasoning shortcuts present in existing datasets. To address this, we introduce a novel, controlled contrastive dataset (DICE) specifically designed to assess whether LLMs can effectively leverage context to disambiguate idiomatic meanings. Furthermore, we investigate the influence of collocational frequency and sentence probability—proxies for human processing known to affect idiom resolution—on model performance. Our results show that LLMs frequently fail to resolve idiomaticity when it depends on contextual understanding, performing better on sentences deemed more likely by the model. Additionally, idiom frequency influences performance but does not guarantee accurate interpretation. Our findings emphasize the limitations of current models in grasping contextual meaning and highlight the need for more context-sensitive evaluation.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

—

Continuities

—

Publication year

2025

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection

Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

ISBN

979-8-89176-251-0

ISSN

—

e-ISSN

—

Number of pages

19

Pages from-to

7314-7332

Publisher name

Association for Computational Linguistics

Place of publication

—

Event location

Vienna, Austria

Event date

Jan 1, 2026

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—