Challenge: Large language models (LLMs) achieve strong performance on idiom identification benchmarks, yet their robustness to misleading contextual signals remains largely untested.
Approach: They propose an adversarial extension of the ID10M dataset that jams idiom understanding by injecting coherent but conflicting context before each target sentence.
Outcome: The proposed benchmark exposes systematic vulnerabilities in LLMs’ contextual reasoning, pushing idiom identification to its breaking point.

Similar Papers

ID10M: Idiom Identification in 10 Languages (2022.findings-naacl)

Copied to clipboard

Challenge: Identifying and understanding idioms in context is a key goal and challenge in Natural Language Understanding tasks.
Approach: They propose a multilingual Transformer-based system for the identification of idioms and a manually-curated evaluation benchmark.
Outcome: The proposed system performs well in 10 languages and is released on github.
Rolling the DICE on Idiomaticity: How LLMs Fail to Grasp Context (2025.acl-long)

Copied to clipboard

Challenge: Existing models fail to resolve idiomaticity when it depends on contextual understanding . idiom frequency influences performance but does not guarantee accurate interpretation.
Approach: They propose a novel contrastive dataset to assess whether large language models can effectively leverage context to disambiguate idiomatic meanings.
Outcome: The proposed model performs better on sentences deemed more likely by the model . collocational frequency and sentence probability influence performance but not accuracy .
No Context Needed: Contextual Quandary In Idiomatic Reasoning With Pre-Trained Language Models (2024.naacl-long)

Copied to clipboard

Challenge: idiomatic expressions (IEs) are a non-compositional aspect of a text that makes it difficult for a model to comprehend . general purpose PTLMs are negatively affected by the context, as performance increases with its removal.
Approach: They propose to use idiomatic expressions to infer additional meaning from IEs . they argue that only IE-aware models are suitable for idiom- matic reasoning tasks .
Outcome: The proposed models can reason in the presence of idiomatic expressions, the authors show . they show that general purpose PTLMs are negatively affected by the context .
Easy as PIE? Identifying Multi-Word Expressions with LLMs (2025.emnlp-main)

Copied to clipboard

Challenge: Multiword expressions (MWEs) are a semantically non-compositional subclass of multiword expression . authors show that prompt-based LLMs can perform competitively with supervised models .
Approach: They propose a prompt-based approach to identify idiomatic expressions in running text . they find prompt-driven LLMs can perform competitively with supervised models .
Outcome: The proposed approach can perform well with supervised models on annotated data.
Getting BART to Ride the Idiomatic Train: Learning to Represent Idiomatic Expressions (2022.tacl-1)

Copied to clipboard

Challenge: Prior work has identified deficiencies in their contextualized representation stemming from the underlying compositional paradigm of representation.
Approach: They propose to use an adapter as a lightweight non-compositional language expert trained on idiomatic sentences to build idiomity into BART.
Outcome: The proposed approach improves idiomaticity over baselines and up to 25% higher sequence accuracy on idiom processing tasks.
Deconstructing In-Context Learning: Understanding Prompts via Corruption (2024.lrec-main)

Copied to clipboard

Challenge: Prior work examined how modifying different elements of the prompt can affect model performance, but this limited number of elements made replication challenging.
Approach: They decompose the entire prompt into four components: task description, demonstration inputs, labels, and inline instructions provided for each demonstration.
Outcome: The proposed model is robust to minor prompt modifications, but its underlying pre-trained backbone is brittle . previous studies focused on models with fewer than 15 billion parameters or exclusively examined black-box models like GPT-3 or PaLM, making replication challenging.
AStitchInLanguageModels: Dataset and Methods for the Exploration of Idiomaticity in Pre-Trained Language Models (2021.findings-emnlp)

Copied to clipboard

Challenge: Existing datasets are limited to providing the degree of idiomaticity of expressions along with the literal and, where applicable, (a single) non-literal interpretation of MWEs.
Approach: They propose to use a dataset to test the effectiveness of a language model in generating representations of sentences containing idioms.
Outcome: The proposed model performs reasonably well on the one-shot and few-shot scenarios, but there is scope for improvement in the zero-shot scenario.
Memorization or Reasoning? Exploring the Idiom Understanding of LLMs (2025.emnlp-main)

Copied to clipboard

Challenge: idioms have long posed a challenge due to their unique linguistic properties, which set them apart from other common expressions.
Approach: They propose to use a large-scale dataset of idioms in six languages to evaluate LLMs' idiomatic processing ability.
Outcome: The proposed model integrates contextual cues and reasoning to improve idiom understanding in LLMs, suggesting that their performance is influenced by memorization and reasoning.
Idiomatic Expression Identification using Semantic Compatibility (2021.tacl-1)

Copied to clipboard

Challenge: Existing approaches to localize idiomatic expressions have limited views of their generalizability to new idioms.
Approach: They propose a multi-stage neural architecture to detect whether a sentence has an idiomatic expression and localize it when it occurs in a figurative sense.
Outcome: The proposed model achieves state-of-the-art on three of the largest datasets with idiomatic expressions of varied syntactic patterns and degrees of non-compositionality.
Out-of-Context Reasoning in Large Language Models (2025.findings-emnlp)

Copied to clipboard

Challenge: a lightweight technique trains only new token embeddings on axioms and evaluates them on unseen tasks.
Approach: They propose a lightweight technique that trains only new token embeddings on axioms . they train only new embeddables and evaluate them on unseen tasks .
Outcome: The proposed technique trains only new token embeddings on axioms and evaluates them on unseen tasks.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations