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

arXiv: https://arxiv.org/abs/2508.11927 · HTML: https://mlsanity.com/paper/2508.11927/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 4 of its 13 references that are in the map.
- First posted on arXiv 16 Aug 2025.

## Builds on (most cited first, 4 of 4)

- [Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference](https://mlsanity.com/paper/1902.01007/) (2019)
- [OCNLI: Original Chinese Natural Language Inference](https://mlsanity.com/paper/2010.05444/) (2020)
- [Compositional Evaluation on Japanese Textual Entailment and Similarity](https://mlsanity.com/paper/2208.04826/) (2022)
- [Temporal and Aspectual Entailment](https://mlsanity.com/paper/1904.01297/) (2019)

## Abstract (arXiv)

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.