# Can Large Language Models Robustly Perform Natural Language Inference for Japanese Comparatives?

arXiv: https://arxiv.org/abs/2509.13695 · HTML: https://mlsanity.com/paper/2509.13695/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 18 references that are in the map.
- First posted on arXiv 17 Sep 2025.

## Builds on (most cited first, 7 of 7)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [A large annotated corpus for learning natural language inference](https://mlsanity.com/paper/1508.05326/) (2015)
- [Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference](https://mlsanity.com/paper/1902.01007/) (2019)
- [Evaluating the Logical Reasoning Ability of ChatGPT and GPT-4](https://mlsanity.com/paper/2304.03439/) (2023)
- [Continual Pre-Training for Cross-Lingual LLM Adaptation: Enhancing Japanese Language Capabilities](https://mlsanity.com/paper/2404.17790/) (2024)
- [ScoNe: Benchmarking Negation Reasoning in Language Models With Fine-Tuning and In-Context Learning](https://mlsanity.com/paper/2305.19426/) (2023)
- [Exploring Reasoning Biases in Large Language Models Through Syllogism: Insights from the NeuBAROCO Dataset](https://mlsanity.com/paper/2408.04403/) (2024)

## Abstract (arXiv)

Large Language Models (LLMs) perform remarkably well in Natural Language Inference (NLI). However, NLI involving numerical and logical expressions remains challenging. Comparatives are a key linguistic phenomenon related to such inference, but the robustness of LLMs in handling them, especially in languages that are not dominant in the models' training data, such as Japanese, has not been sufficiently explored. To address this gap, we construct a Japanese NLI dataset that focuses on comparatives and evaluate various LLMs in zero-shot and few-shot settings. Our results show that the performance of the models is sensitive to the prompt formats in the zero-shot setting and influenced by the gold labels in the few-shot examples. The LLMs also struggle to handle linguistic phenomena unique to Japanese. Furthermore, we observe that prompts containing logical semantic representations help the models predict the correct labels for inference problems that they struggle to solve even with few-shot examples.