LLMs Struggle with NLI for Perfect Aspect: A Cross-Linguistic Study in Chinese and Japanese

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lu, Jie, Jin, Du, Yanaka, Hitomi
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912539774812160
author Lu, Jie
Jin, Du
Yanaka, Hitomi
author_facet Lu, Jie
Jin, Du
Yanaka, Hitomi
contents Unlike English, which uses distinct forms (e.g., had, has, will have) to mark the perfect aspect across tenses, Chinese and Japanese lack separate grammatical forms for tense within the perfect aspect, which complicates Natural Language Inference (NLI). Focusing on the perfect aspect in these languages, we construct a linguistically motivated, template-based NLI dataset (1,350 pairs per language). Experiments reveal that even advanced LLMs struggle with temporal inference, particularly in detecting subtle tense and reference-time shifts. These findings highlight model limitations and underscore the need for cross-linguistic evaluation in temporal semantics. Our dataset is available at https://github.com/Lujie2001/CrossNLI.
format Preprint
id arxiv_https___arxiv_org_abs_2508_11927
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LLMs Struggle with NLI for Perfect Aspect: A Cross-Linguistic Study in Chinese and Japanese
Lu, Jie
Jin, Du
Yanaka, Hitomi
Computation and Language
Unlike English, which uses distinct forms (e.g., had, has, will have) to mark the perfect aspect across tenses, Chinese and Japanese lack separate grammatical forms for tense within the perfect aspect, which complicates Natural Language Inference (NLI). Focusing on the perfect aspect in these languages, we construct a linguistically motivated, template-based NLI dataset (1,350 pairs per language). Experiments reveal that even advanced LLMs struggle with temporal inference, particularly in detecting subtle tense and reference-time shifts. These findings highlight model limitations and underscore the need for cross-linguistic evaluation in temporal semantics. Our dataset is available at https://github.com/Lujie2001/CrossNLI.
title LLMs Struggle with NLI for Perfect Aspect: A Cross-Linguistic Study in Chinese and Japanese
topic Computation and Language
url https://arxiv.org/abs/2508.11927