# A New Benchmark Dataset and Mixture-of-Experts Language Models for Adversarial Natural Language Inference in Vietnamese

arXiv: https://arxiv.org/abs/2406.17716 · HTML: https://mlsanity.com/paper/2406.17716/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in MoE large language models, one of 12 directions in Mixture-of-experts.
- Builds on 4 of its 80 references that are in the map.
- First posted on arXiv 25 Jun 2024.

## Placed in

- Mixture-of-experts / [MoE large language models](https://mlsanity.com/moe/moe-large-language-models/)

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

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding](https://mlsanity.com/paper/2006.16668/) (2020)

## Built on by (most cited first, 4 of 4)

- [ViLegalNLI: Natural Language Inference for Vietnamese Legal Texts](https://mlsanity.com/paper/2605.00116/) (2026)
- [ViCLSR: A Supervised Contrastive Learning Framework with Natural Language Inference for Natural Language Understanding Tasks](https://mlsanity.com/paper/2603.21084/) (2026)
- [SEA-NLI: Natural Language Inference as a Lens into Southeast Asian Cultural Understanding](https://mlsanity.com/paper/2606.03284/) (2026)
- [How Robust Are LLMs to Vietnamese Dialects?](https://mlsanity.com/paper/2608.10414/) (2026)

## Abstract (arXiv)

Existing Vietnamese Natural Language Inference (NLI) datasets lack adversarial complexity, limiting their ability to evaluate model robustness against challenging linguistic phenomena. In this article, we address the gap in robust Vietnamese NLI resources by introducing ViANLI, the first adversarial NLI dataset for Vietnamese, and propose NLIMoE, a Mixture-of-Experts model to tackle its complexity. We construct ViANLI using an adversarial human-and-machine-in-the-loop approach with rigorous verification. NLIMoE integrates expert subnetworks with a learned dynamic routing mechanism on top of a shared transformer encoder. ViANLI comprises over 10,000 premise-hypothesis pairs and challenges state-of-the-art models, with XLM-R Large achieving only 45.5% accuracy, while NLIMoE reaches 47.3%. Training with ViANLI improves performance on other benchmark Vietnamese NLI datasets including ViNLI, VLSP2021-NLI, and VnNewsNLI. ViANLI is released for enhancing research into model robustness and enriching resources for future Vietnamese and multilingual NLI research.