# Adversarially Regularising Neural NLI Models to Integrate Logical Background Knowledge

arXiv: https://arxiv.org/abs/1808.08609 · HTML: https://mlsanity.com/paper/1808.08609/

## Key facts

- Cited by 46 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Aug 2018.

## Built on by (most cited first, 30 of 46)

- [Dynabench: Rethinking Benchmarking in NLP](https://mlsanity.com/paper/2104.14337/) (2021)
- [Maieutic Prompting: Logically Consistent Reasoning with Recursive Explanations](https://mlsanity.com/paper/2205.11822/) (2022)
- [Measure and Improve Robustness in NLP Models: A Survey](https://mlsanity.com/paper/2112.08313/) (2021)
- [Towards Interpreting and Mitigating Shortcut Learning Behavior of NLU Models](https://mlsanity.com/paper/2103.06922/) (2021)
- [BeliefBank: Adding Memory to a Pre-Trained Language Model for a Systematic Notion of Belief](https://mlsanity.com/paper/2109.14723/) (2021)
- [Generating Data to Mitigate Spurious Correlations in Natural Language Inference Datasets](https://mlsanity.com/paper/2203.12942/) (2022)
- [Deep Learning with Logical Constraints](https://mlsanity.com/paper/2205.00523/) (2022)
- [Beyond Accuracy: Evaluating Self-Consistency of Code Large Language Models with IdentityChain](https://mlsanity.com/paper/2310.14053/) (2023)
- [EXplainable Neural-Symbolic Learning (X-NeSyL) methodology to fuse deep learning representations with expert knowledge graphs: the MonuMAI cultural heritage use case](https://mlsanity.com/paper/2104.11914/) (2021)
- [DISCO: Distilling Counterfactuals with Large Language Models](https://mlsanity.com/paper/2212.10534/) (2022)
- [Supervising Model Attention with Human Explanations for Robust Natural Language Inference](https://mlsanity.com/paper/2104.08142/) (2021)
- [RockNER: A Simple Method to Create Adversarial Examples for Evaluating the Robustness of Named Entity Recognition Models](https://mlsanity.com/paper/2109.05620/) (2021)
- [A Survey of Adversarial Defences and Robustness in NLP](https://mlsanity.com/paper/2203.06414/) (2022)
- [Separating form and meaning: Using self-consistency to quantify task understanding across multiple senses](https://mlsanity.com/paper/2305.11662/) (2023)
- [Improving Adversarial Data Collection by Supporting Annotators: Lessons from GAHD, a German Hate Speech Dataset](https://mlsanity.com/paper/2403.19559/) (2024)
- [DoubleMix: Simple Interpolation-Based Data Augmentation for Text Classification](https://mlsanity.com/paper/2209.05297/) (2022)
- [AGRO: Adversarial Discovery of Error-prone groups for Robust Optimization](https://mlsanity.com/paper/2212.00921/) (2022)
- [Consistency Training with Virtual Adversarial Discrete Perturbation](https://mlsanity.com/paper/2104.07284/) (2021)
- [GLUECons: A Generic Benchmark for Learning Under Constraints](https://mlsanity.com/paper/2302.10914/) (2023)
- [ULLER: A Unified Language for Learning and Reasoning](https://mlsanity.com/paper/2405.00532/) (2024)
- [Learning with Instance Bundles for Reading Comprehension](https://mlsanity.com/paper/2104.08735/) (2021)
- [Residue-Based Natural Language Adversarial Attack Detection](https://mlsanity.com/paper/2204.10192/) (2022)
- [From Instructions to Constraints: Language Model Alignment with Automatic Constraint Verification](https://mlsanity.com/paper/2403.06326/) (2024)
- [Improving the robustness and accuracy of biomedical language models through adversarial training](https://mlsanity.com/paper/2111.08529/) (2021)
- [Robustness Over Time: Understanding Adversarial Examples' Effectiveness on Longitudinal Versions of Large Language Models](https://mlsanity.com/paper/2308.07847/) (2023)
- [From Form(s) to Meaning: Probing the Semantic Depths of Language Models Using Multisense Consistency](https://mlsanity.com/paper/2404.12145/) (2024)
- [Paired Examples as Indirect Supervision in Latent Decision Models](https://mlsanity.com/paper/2104.01759/) (2021)
- [VAULT: Vigilant Adversarial Updates via LLM-Driven Retrieval-Augmented Generation for NLI](https://mlsanity.com/paper/2508.00965/) (2025)
- [How Fragile is Relation Extraction under Entity Replacements?](https://mlsanity.com/paper/2305.13551/) (2023)
- [Towards Effective Paraphrasing for Information Disguise](https://mlsanity.com/paper/2311.05018/) (2023)

## Abstract (arXiv)

Adversarial examples are inputs to machine learning models designed to cause the model to make a mistake. They are useful for understanding the shortcomings of machine learning models, interpreting their results, and for regularisation. In NLP, however, most example generation strategies produce input text by using known, pre-specified semantic transformations, requiring significant manual effort and in-depth understanding of the problem and domain. In this paper, we investigate the problem of automatically generating adversarial examples that violate a set of given First-Order Logic constraints in Natural Language Inference (NLI). We reduce the problem of identifying such adversarial examples to a combinatorial optimisation problem, by maximising a quantity measuring the degree of violation of such constraints and by using a language model for generating linguistically-plausible examples. Furthermore, we propose a method for adversarially regularising neural NLI models for incorporating background knowledge. Our results show that, while the proposed method does not always improve results on the SNLI and MultiNLI datasets, it significantly and consistently increases the predictive accuracy on adversarially-crafted datasets -- up to a 79.6% relative improvement -- while drastically reducing the number of background knowledge violations. Furthermore, we show that adversarial examples transfer among model architectures, and that the proposed adversarial training procedure improves the robustness of NLI models to adversarial examples.