# Enhancing adversarial robustness in Natural Language Inference using explanations

arXiv: https://arxiv.org/abs/2409.07423 · HTML: https://mlsanity.com/paper/2409.07423/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 58 references that are in the map.
- First posted on arXiv 11 Sep 2024.

## Builds on (most cited first, 30 of 34)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://mlsanity.com/paper/1909.11942/) (2019)
- [A large annotated corpus for learning natural language inference](https://mlsanity.com/paper/1508.05326/) (2015)
- [Theoretically Principled Trade-off between Robustness and Accuracy](https://mlsanity.com/paper/1901.08573/) (2019)
- [Robustness May Be at Odds with Accuracy](https://mlsanity.com/paper/1805.12152/) (2018)
- [Annotation Artifacts in Natural Language Inference Data](https://mlsanity.com/paper/1803.02324/) (2018)
- [Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment](https://mlsanity.com/paper/1907.11932/) (2019)
- [BERT-ATTACK: Adversarial Attack Against BERT Using BERT](https://mlsanity.com/paper/2004.09984/) (2020)
- [e-SNLI: Natural Language Inference with Natural Language Explanations](https://mlsanity.com/paper/1812.01193/) (2018)
- [Generating Natural Language Adversarial Examples](https://mlsanity.com/paper/1804.07998/) (2018)
- [Reasoning with Language Model Prompting: A Survey](https://mlsanity.com/paper/2212.09597/) (2022)
- [Enhanced LSTM for Natural Language Inference](https://mlsanity.com/paper/1609.06038/) (2016)
- [Towards Faithful Model Explanation in NLP: A Survey](https://mlsanity.com/paper/2209.11326/) (2022)
- [AI Transparency in the Age of LLMs: A Human-Centered Research Roadmap](https://mlsanity.com/paper/2306.01941/) (2023)
- [Semantics-aware BERT for Language Understanding](https://mlsanity.com/paper/1909.02209/) (2019)
- [Robustness and Accuracy Could Be Reconcilable by (Proper) Definition](https://mlsanity.com/paper/2202.10103/) (2022)
- [Robustness Gym: Unifying the NLP Evaluation Landscape](https://mlsanity.com/paper/2101.04840/) (2021)
- [NILE : Natural Language Inference with Faithful Natural Language Explanations](https://mlsanity.com/paper/2005.12116/) (2020)
- [Generating Fluent Adversarial Examples for Natural Languages](https://mlsanity.com/paper/2007.06174/) (2020)
- [Puzzle Solving using Reasoning of Large Language Models: A Survey](https://mlsanity.com/paper/2402.11291/) (2024)
- [Faithful Explanations of Black-box NLP Models Using LLM-generated Counterfactuals](https://mlsanity.com/paper/2310.00603/) (2023)
- [LIREx: Augmenting Language Inference with Relevant Explanation](https://mlsanity.com/paper/2012.09157/) (2020)
- [Self-Explaining Structures Improve NLP Models](https://mlsanity.com/paper/2012.01786/) (2020)
- [Logical Reasoning with Span-Level Predictions for Interpretable and Robust NLI Models](https://mlsanity.com/paper/2205.11432/) (2022)
- [Logical Satisfiability of Counterfactuals for Faithful Explanations in NLI](https://mlsanity.com/paper/2205.12469/) (2022)
- [TextShield: Beyond Successfully Detecting Adversarial Sentences in Text Classification](https://mlsanity.com/paper/2302.02023/) (2023)
- [INTERACTION: A Generative XAI Framework for Natural Language Inference Explanations](https://mlsanity.com/paper/2209.01061/) (2022)

## Built on by (most cited first, 2 of 2)

- [Improving the OOD Performance of Closed-Source LLMs on NLI Through Strategic Data Selection](https://mlsanity.com/paper/2505.20209/) (2025)
- [Are Time-Series Foundation Models Deployment-Ready? A Systematic Study of Adversarial Robustness Across Domains](https://mlsanity.com/paper/2505.19397/) (2025)

## Abstract (arXiv)

The surge of state-of-the-art Transformer-based models has undoubtedly pushed the limits of NLP model performance, excelling in a variety of tasks. We cast the spotlight on the underexplored task of Natural Language Inference (NLI), since models trained on popular well-suited datasets are susceptible to adversarial attacks, allowing subtle input interventions to mislead the model. In this work, we validate the usage of natural language explanation as a model-agnostic defence strategy through extensive experimentation: only by fine-tuning a classifier on the explanation rather than premise-hypothesis inputs, robustness under various adversarial attacks is achieved in comparison to explanation-free baselines. Moreover, since there is no standard strategy of testing the semantic validity of the generated explanations, we research the correlation of widely used language generation metrics with human perception, in order for them to serve as a proxy towards robust NLI models. Our approach is resource-efficient and reproducible without significant computational limitations.