Unveiling LLMs' Metaphorical Understanding: Exploring Conceptual Irrelevance, Context Leveraging and Syntactic Influence
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911192225677312 |
|---|---|
| author | Ye, Fengying Wang, Shanshan Chao, Lidia S. Wong, Derek F. |
| author_facet | Ye, Fengying Wang, Shanshan Chao, Lidia S. Wong, Derek F. |
| contents | Metaphor analysis is a complex linguistic phenomenon shaped by context and external factors. While Large Language Models (LLMs) demonstrate advanced capabilities in knowledge integration, contextual reasoning, and creative generation, their mechanisms for metaphor comprehension remain insufficiently explored. This study examines LLMs' metaphor-processing abilities from three perspectives: (1) Concept Mapping: using embedding space projections to evaluate how LLMs map concepts in target domains (e.g., misinterpreting "fall in love" as "drop down from love"); (2) Metaphor-Literal Repository: analyzing metaphorical words and their literal counterparts to identify inherent metaphorical knowledge; and (3) Syntactic Sensitivity: assessing how metaphorical syntactic structures influence LLMs' performance. Our findings reveal that LLMs generate 15\%-25\% conceptually irrelevant interpretations, depend on metaphorical indicators in training data rather than contextual cues, and are more sensitive to syntactic irregularities than to structural comprehension. These insights underline the limitations of LLMs in metaphor analysis and call for more robust computational approaches. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_04120 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Unveiling LLMs' Metaphorical Understanding: Exploring Conceptual Irrelevance, Context Leveraging and Syntactic Influence Ye, Fengying Wang, Shanshan Chao, Lidia S. Wong, Derek F. Computation and Language Artificial Intelligence Metaphor analysis is a complex linguistic phenomenon shaped by context and external factors. While Large Language Models (LLMs) demonstrate advanced capabilities in knowledge integration, contextual reasoning, and creative generation, their mechanisms for metaphor comprehension remain insufficiently explored. This study examines LLMs' metaphor-processing abilities from three perspectives: (1) Concept Mapping: using embedding space projections to evaluate how LLMs map concepts in target domains (e.g., misinterpreting "fall in love" as "drop down from love"); (2) Metaphor-Literal Repository: analyzing metaphorical words and their literal counterparts to identify inherent metaphorical knowledge; and (3) Syntactic Sensitivity: assessing how metaphorical syntactic structures influence LLMs' performance. Our findings reveal that LLMs generate 15\%-25\% conceptually irrelevant interpretations, depend on metaphorical indicators in training data rather than contextual cues, and are more sensitive to syntactic irregularities than to structural comprehension. These insights underline the limitations of LLMs in metaphor analysis and call for more robust computational approaches. |
| title | Unveiling LLMs' Metaphorical Understanding: Exploring Conceptual Irrelevance, Context Leveraging and Syntactic Influence |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2510.04120 |