Rolling the DICE on Idiomaticity: How LLMs Fail to Grasp Context
This addresses a limitation in LLMs' language understanding for NLP researchers, though it is incremental as it builds on existing idiomaticity detection tasks.
The paper tackled the problem of whether large language models (LLMs) can effectively use contextual sentences to disambiguate idiomatic meaning, revealing that LLMs often fail to resolve idiomaticity when required to attend to context and perform better on sentences with higher likelihood.
Human processing of idioms relies on understanding the contextual sentences in which idioms occur, as well as language-intrinsic features such as frequency and speaker-intrinsic factors like familiarity. While LLMs have shown high performance on idiomaticity detection tasks, this success may be attributed to reasoning shortcuts in existing datasets. To this end, we construct a novel, controlled contrastive dataset designed to test whether LLMs can effectively use context to disambiguate idiomatic meaning. Additionally, we explore how collocational frequency and sentence probability influence model performance. Our findings reveal that LLMs often fail to resolve idiomaticity when it is required to attend to the surrounding context, and that models perform better on sentences that have higher likelihood. The collocational frequency of expressions also impacts performance. We make our code and dataset publicly available.