Investigating the Impact of Conceptual Metaphors on LLM-based NLI through Shapley Interactions

Sengupta, Meghdut; Muschalik, Maximilian ; Fumagalli, Fabian ; Hammer, Barbara ; Hüllermeier, Eyke ; Ghosh, Debanjan und Wachsmuth, Henning (November 2025): Investigating the Impact of Conceptual Metaphors on LLM-based NLI through Shapley Interactions. The 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP 2025), Suzhou, China, 4. –9. November 2025. Christodoulopoulos, Christos; Chakraborty, Tanmoy; Rose, Carolyn und Peng, Violet (eds.) : In: Findings of the Association for Computational Linguistics: EMNLP 2025, Suzhou, China: Association for Computational Linguistics. pp. 17393-17403

Abstract

Metaphorical language is prevalent in everyday communication, often used unconsciously, as in ``rising crime.'' While LLMs excel at identifying metaphors in text, they struggle with downstream tasks that implicitly require correct metaphor interpretation, such as natural language inference (NLI). This work explores how LLMs perform on NLI with metaphorical input. Particularly, we investigate whether incorporating conceptual metaphors (source and target domains) enhances performance in zero-shot and few-shot settings. Our contributions are two-fold: (1) we extend metaphorical texts in an existing NLI dataset by source and target domains, and (2) we conduct an ablation study using Shapley values and interactions to assess the extent to which LLMs interpret metaphorical language correctly in NLI. Our results indicate that incorporating conceptual metaphors often improves task performance.

• Item Type: Conference or Workshop Item (Paper)
• Faculties: Mathematics, Computer Science and Statistics > Computer Science > Artificial Intelligence and Machine Learning
• Subjects: 000 Computer science, information and general works > 004 Data processing computer science
• Place of Publication: Suzhou, China
• DFG: Gefördert durch die Deutsche Forschungsgemeinschaft (DFG) - 438445824