# Make Up Your Mind! Adversarial Generation of Inconsistent Natural Language Explanations

arXiv: https://arxiv.org/abs/1910.03065 · HTML: https://mlsanity.com/paper/1910.03065/

## Key facts

- Cited by 71 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Oct 2019.

## Built on by (most cited first, 30 of 71)

- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [Measuring and Improving Consistency in Pretrained Language Models](https://mlsanity.com/paper/2102.01017/) (2021)
- [From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI](https://mlsanity.com/paper/2201.08164/) (2022)
- [Personality Traits in Large Language Models](https://mlsanity.com/paper/2307.00184/) (2023)
- [A Review on Language Models as Knowledge Bases](https://mlsanity.com/paper/2204.06031/) (2022)
- [Towards Faithful Model Explanation in NLP: A Survey](https://mlsanity.com/paper/2209.11326/) (2022)
- [Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networks](https://mlsanity.com/paper/2207.13243/) (2022)
- [Teach Me to Explain: A Review of Datasets for Explainable Natural Language Processing](https://mlsanity.com/paper/2102.12060/) (2021)
- [Faithfulness Tests for Natural Language Explanations](https://mlsanity.com/paper/2305.18029/) (2023)
- [Moral Foundations of Large Language Models](https://mlsanity.com/paper/2310.15337/) (2023)
- [e-ViL: A Dataset and Benchmark for Natural Language Explanations in Vision-Language Tasks](https://mlsanity.com/paper/2105.03761/) (2021)
- [Multi-Agent Consensus Seeking via Large Language Models](https://mlsanity.com/paper/2310.20151/) (2023)
- [Measuring Chain of Thought Faithfulness by Unlearning Reasoning Steps](https://mlsanity.com/paper/2502.14829/) (2025)
- [A Review on Explainability in Multimodal Deep Neural Nets](https://mlsanity.com/paper/2105.07878/) (2021)
- [Prompting Contrastive Explanations for Commonsense Reasoning Tasks](https://mlsanity.com/paper/2106.06823/) (2021)
- [Consistency Analysis of ChatGPT](https://mlsanity.com/paper/2303.06273/) (2023)
- [Can Rationalization Improve Robustness?](https://mlsanity.com/paper/2204.11790/) (2022)
- [Interpretable Long-Form Legal Question Answering with Retrieval-Augmented Large Language Models](https://mlsanity.com/paper/2309.17050/) (2023)
- [Verification and Refinement of Natural Language Explanations through LLM-Symbolic Theorem Proving](https://mlsanity.com/paper/2405.01379/) (2024)
- [Local Interpretations for Explainable Natural Language Processing: A Survey](https://mlsanity.com/paper/2103.11072/) (2021)
- [The Trickle-down Impact of Reward (In-)consistency on RLHF](https://mlsanity.com/paper/2309.16155/) (2023)
- [E-KAR: A Benchmark for Rationalizing Natural Language Analogical Reasoning](https://mlsanity.com/paper/2203.08480/) (2022)
- [On Behalf of the Stakeholders: Trends in NLP Model Interpretability in the Era of LLMs](https://mlsanity.com/paper/2407.19200/) (2024)
- [Knowledge-Grounded Self-Rationalization via Extractive and Natural Language Explanations](https://mlsanity.com/paper/2106.13876/) (2021)
- [What's the Meaning of Superhuman Performance in Today's NLU?](https://mlsanity.com/paper/2305.08414/) (2023)
- [ChatGPT Rates Natural Language Explanation Quality Like Humans: But on Which Scales?](https://mlsanity.com/paper/2403.17368/) (2024)
- [Counterfactual Simulation Training for Chain-of-Thought Faithfulness](https://mlsanity.com/paper/2602.20710/) (2026)
- [Few-Shot Out-of-Domain Transfer Learning of Natural Language Explanations in a Label-Abundant Setup](https://mlsanity.com/paper/2112.06204/) (2021)
- [BatchPrompt: Accomplish more with less](https://mlsanity.com/paper/2309.00384/) (2023)

## Abstract (arXiv)

To increase trust in artificial intelligence systems, a promising research direction consists of designing neural models capable of generating natural language explanations for their predictions. In this work, we show that such models are nonetheless prone to generating mutually inconsistent explanations, such as "Because there is a dog in the image" and "Because there is no dog in the [same] image", exposing flaws in either the decision-making process of the model or in the generation of the explanations. We introduce a simple yet effective adversarial framework for sanity checking models against the generation of inconsistent natural language explanations. Moreover, as part of the framework, we address the problem of adversarial attacks with full target sequences, a scenario that was not previously addressed in sequence-to-sequence attacks. Finally, we apply our framework on a state-of-the-art neural natural language inference model that provides natural language explanations for its predictions. Our framework shows that this model is capable of generating a significant number of inconsistent explanations.