Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2507.14307 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908677368184832 |
|---|---|
| author | de Langis, Karin Park, Jong Inn Schramm, Andreas Hu, Bin Le, Khanh Chi Mensink, Michael Tong, Ahn Thu Kang, Dongyeop |
| author_facet | de Langis, Karin Park, Jong Inn Schramm, Andreas Hu, Bin Le, Khanh Chi Mensink, Michael Tong, Ahn Thu Kang, Dongyeop |
| contents | Large language models (LLMs) exhibit increasingly sophisticated linguistic capabilities, yet the extent to which these behaviors reflect human-like cognition versus advanced pattern recognition remains an open question. In this study, we investigate how LLMs process the temporal meaning of linguistic aspect in narratives that were previously used in human studies. Using an Expert-in-the-Loop probing pipeline, we conduct a series of targeted experiments to assess whether LLMs construct semantic representations and pragmatic inferences in a human-like manner. Our findings show that LLMs over-rely on prototypicality, produce inconsistent aspectual judgments, and struggle with causal reasoning derived from aspect, raising concerns about their ability to fully comprehend narratives. These results suggest that LLMs process aspect fundamentally differently from humans and lack robust narrative understanding. Beyond these empirical findings, we develop a standardized experimental framework for the reliable assessment of LLMs' cognitive and linguistic capabilities. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_14307 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | How LLMs Comprehend Temporal Meaning in Narratives: A Case Study in Cognitive Evaluation of LLMs de Langis, Karin Park, Jong Inn Schramm, Andreas Hu, Bin Le, Khanh Chi Mensink, Michael Tong, Ahn Thu Kang, Dongyeop Computation and Language Large language models (LLMs) exhibit increasingly sophisticated linguistic capabilities, yet the extent to which these behaviors reflect human-like cognition versus advanced pattern recognition remains an open question. In this study, we investigate how LLMs process the temporal meaning of linguistic aspect in narratives that were previously used in human studies. Using an Expert-in-the-Loop probing pipeline, we conduct a series of targeted experiments to assess whether LLMs construct semantic representations and pragmatic inferences in a human-like manner. Our findings show that LLMs over-rely on prototypicality, produce inconsistent aspectual judgments, and struggle with causal reasoning derived from aspect, raising concerns about their ability to fully comprehend narratives. These results suggest that LLMs process aspect fundamentally differently from humans and lack robust narrative understanding. Beyond these empirical findings, we develop a standardized experimental framework for the reliable assessment of LLMs' cognitive and linguistic capabilities. |
| title | How LLMs Comprehend Temporal Meaning in Narratives: A Case Study in Cognitive Evaluation of LLMs |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2507.14307 |