# Rather a Nurse than a Physician -- Contrastive Explanations under Investigation

arXiv: https://arxiv.org/abs/2310.11906 · HTML: https://mlsanity.com/paper/2310.11906/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 37 references that are in the map.
- First posted on arXiv 18 Oct 2023.

## Builds on (most cited first, 23 of 23)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [Explanation in Artificial Intelligence: Insights from the Social Sciences](https://mlsanity.com/paper/1706.07269/) (2017)
- [ERASER: A Benchmark to Evaluate Rationalized NLP Models](https://mlsanity.com/paper/1911.03429/) (2019)
- [Datasets: A Community Library for Natural Language Processing](https://mlsanity.com/paper/2109.02846/) (2021)
- [e-SNLI: Natural Language Inference with Natural Language Explanations](https://mlsanity.com/paper/1812.01193/) (2018)
- [Bias in Bios: A Case Study of Semantic Representation Bias in a High-Stakes Setting](https://mlsanity.com/paper/1901.09451/) (2019)
- [Explanations based on the Missing: Towards Contrastive Explanations with Pertinent Negatives](https://mlsanity.com/paper/1802.07623/) (2018)
- [Visualizing and Understanding Neural Models in NLP](https://mlsanity.com/paper/1506.01066/) (2015)
- [A Diagnostic Study of Explainability Techniques for Text Classification](https://mlsanity.com/paper/2009.13295/) (2020)
- [XAI for Transformers: Better Explanations through Conservative Propagation](https://mlsanity.com/paper/2202.07304/) (2022)
- [Interpreting Language Models with Contrastive Explanations](https://mlsanity.com/paper/2202.10419/) (2022)
- [Contrastive Explanations for Model Interpretability](https://mlsanity.com/paper/2103.01378/) (2021)
- [DynaSent: A Dynamic Benchmark for Sentiment Analysis](https://mlsanity.com/paper/2012.15349/) (2020)
- [Quantifying Interpretability and Trust in Machine Learning Systems](https://mlsanity.com/paper/1901.08558/) (2019)
- [Prompting Contrastive Explanations for Commonsense Reasoning Tasks](https://mlsanity.com/paper/2106.06823/) (2021)
- [Understanding Individual Decisions of CNNs via Contrastive Backpropagation](https://mlsanity.com/paper/1812.02100/) (2018)
- [Improved Multi-label Classification under Temporal Concept Drift: Rethinking Group-Robust Algorithms in a Label-Wise Setting](https://mlsanity.com/paper/2203.07856/) (2022)
- [An Exploration of Encoder-Decoder Approaches to Multi-Label Classification for Legal and Biomedical Text](https://mlsanity.com/paper/2305.05627/) (2023)
- [Do Transformer Models Show Similar Attention Patterns to Task-Specific Human Gaze?](https://mlsanity.com/paper/2205.10226/) (2022)
- [Being Right for Whose Right Reasons?](https://mlsanity.com/paper/2306.00639/) (2023)
- [Evaluating Deep Taylor Decomposition for Reliability Assessment in the Wild](https://mlsanity.com/paper/2206.02661/) (2022)

## Built on by (most cited first, 11 of 11)

- [MambaLRP: Explaining Selective State Space Sequence Models](https://mlsanity.com/paper/2406.07592/) (2024)
- [RelP: Faithful and Efficient Circuit Discovery in Language Models via Relevance Patching](https://mlsanity.com/paper/2508.21258/) (2025)
- [Evaluating Human Alignment and Model Faithfulness of LLM Rationale](https://mlsanity.com/paper/2407.00219/) (2024)
- [A Close Look at Decomposition-based XAI-Methods for Transformer Language Models](https://mlsanity.com/paper/2502.15886/) (2025)
- [Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety](https://mlsanity.com/paper/2506.05451/) (2025)
- [On the Interplay between Fairness and Explainability](https://mlsanity.com/paper/2310.16607/) (2023)
- [Position: We Need An Algorithmic Understanding of Generative AI](https://mlsanity.com/paper/2507.07544/) (2025)
- [The Unheard Alternative: Contrastive Explanations for Speech-to-Text Models](https://mlsanity.com/paper/2509.26543/) (2025)
- [A Systematic Comparison between Extractive Self-Explanations and Human Rationales in Text Classification](https://mlsanity.com/paper/2410.03296/) (2024)
- [Cross-Attention is Half Explanation in Speech-to-Text Models](https://mlsanity.com/paper/2509.18010/) (2025)
- [Visual Analytics for Fine-grained Text Classification Models and Datasets](https://mlsanity.com/paper/2403.15492/) (2024)

## Abstract (arXiv)

Contrastive explanations, where one decision is explained in contrast to another, are supposed to be closer to how humans explain a decision than non-contrastive explanations, where the decision is not necessarily referenced to an alternative. This claim has never been empirically validated. We analyze four English text-classification datasets (SST2, DynaSent, BIOS and DBpedia-Animals). We fine-tune and extract explanations from three different models (RoBERTa, GTP-2, and T5), each in three different sizes and apply three post-hoc explainability methods (LRP, GradientxInput, GradNorm). We furthermore collect and release human rationale annotations for a subset of 100 samples from the BIOS dataset for contrastive and non-contrastive settings. A cross-comparison between model-based rationales and human annotations, both in contrastive and non-contrastive settings, yields a high agreement between the two settings for models as well as for humans. Moreover, model-based explanations computed in both settings align equally well with human rationales. Thus, we empirically find that humans do not necessarily explain in a contrastive manner.9 pages, long paper at ACL 2022 proceedings.