# On the Diversity and Limits of Human Explanations

arXiv: https://arxiv.org/abs/2106.11988 · HTML: https://mlsanity.com/paper/2106.11988/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 73 references that are in the map.
- First posted on arXiv 22 Jun 2021.

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

- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [FEVER: a large-scale dataset for Fact Extraction and VERification](https://mlsanity.com/paper/1803.05355/) (2018)
- [Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies](https://mlsanity.com/paper/2101.02235/) (2021)
- [Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problems](https://mlsanity.com/paper/1705.04146/) (2017)
- [Fact or Fiction: Verifying Scientific Claims](https://mlsanity.com/paper/2004.14974/) (2020)
- [ERASER: A Benchmark to Evaluate Rationalized NLP Models](https://mlsanity.com/paper/1911.03429/) (2019)
- [e-SNLI: Natural Language Inference with Natural Language Explanations](https://mlsanity.com/paper/1812.01193/) (2018)
- [Social Bias Frames: Reasoning about Social and Power Implications of Language](https://mlsanity.com/paper/1911.03891/) (2019)
- [Explain Yourself! Leveraging Language Models for Commonsense Reasoning](https://mlsanity.com/paper/1906.02361/) (2019)
- [QASC: A Dataset for Question Answering via Sentence Composition](https://mlsanity.com/paper/1910.11473/) (2019)
- [Textual Explanations for Self-Driving Vehicles](https://mlsanity.com/paper/1807.11546/) (2018)
- [Explainable Automated Fact-Checking for Public Health Claims](https://mlsanity.com/paper/2010.09926/) (2020)
- [Multimodal Explanations: Justifying Decisions and Pointing to the Evidence](https://mlsanity.com/paper/1802.08129/) (2018)
- [Teach Me to Explain: A Review of Datasets for Explainable Natural Language Processing](https://mlsanity.com/paper/2102.12060/) (2021)
- ["Why is 'Chicago' deceptive?" Towards Building Model-Driven Tutorials for Humans](https://mlsanity.com/paper/2001.05871/) (2020)
- [Automated Rationale Generation: A Technique for Explainable AI and its Effects on Human Perceptions](https://mlsanity.com/paper/1901.03729/) (2019)
- [A Richly Annotated Corpus for Different Tasks in Automated Fact-Checking](https://mlsanity.com/paper/1911.01214/) (2019)
- [Inferring Which Medical Treatments Work from Reports of Clinical Trials](https://mlsanity.com/paper/1904.01606/) (2019)
- [What is More Likely to Happen Next? Video-and-Language Future Event Prediction](https://mlsanity.com/paper/2010.07999/) (2020)
- [WorldTree: A Corpus of Explanation Graphs for Elementary Science Questions supporting Multi-Hop Inference](https://mlsanity.com/paper/1802.03052/) (2018)
- [Training Classifiers with Natural Language Explanations](https://mlsanity.com/paper/1805.03818/) (2018)
- [QED: A Framework and Dataset for Explanations in Question Answering](https://mlsanity.com/paper/2009.06354/) (2020)
- [VQA-E: Explaining, Elaborating, and Enhancing Your Answers for Visual Questions](https://mlsanity.com/paper/1803.07464/) (2018)
- [Learning to Explain: Datasets and Models for Identifying Valid Reasoning Chains in Multihop Question-Answering](https://mlsanity.com/paper/2010.03274/) (2020)
- [WinoWhy: A Deep Diagnosis of Essential Commonsense Knowledge for Answering Winograd Schema Challenge](https://mlsanity.com/paper/2005.05763/) (2020)
- [R4C: A Benchmark for Evaluating RC Systems to Get the Right Answer for the Right Reason](https://mlsanity.com/paper/1910.04601/) (2019)
- [Evaluating and Characterizing Human Rationales](https://mlsanity.com/paper/2010.04736/) (2020)
- [e-SNLI-VE: Corrected Visual-Textual Entailment with Natural Language Explanations](https://mlsanity.com/paper/2004.03744/) (2020)
- [Learning to Rationalize for Nonmonotonic Reasoning with Distant Supervision](https://mlsanity.com/paper/2012.08012/) (2020)
- [Teaching Machine Comprehension with Compositional Explanations](https://mlsanity.com/paper/2005.00806/) (2020)

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

- [Reframing Human-AI Collaboration for Generating Free-Text Explanations](https://mlsanity.com/paper/2112.08674/) (2021)
- [Do Androids Laugh at Electric Sheep? Humor "Understanding" Benchmarks from The New Yorker Caption Contest](https://mlsanity.com/paper/2209.06293/) (2022)
- [In Search of Verifiability: Explanations Rarely Enable Complementary Performance in AI-Advised Decision Making](https://mlsanity.com/paper/2305.07722/) (2023)
- [Are Machine Rationales (Not) Useful to Humans? Measuring and Improving Human Utility of Free-Text Rationales](https://mlsanity.com/paper/2305.07095/) (2023)
- [Going Beyond XAI: A Systematic Survey for Explanation-Guided Learning](https://mlsanity.com/paper/2212.03954/) (2022)
- [Mechanistic?](https://mlsanity.com/paper/2410.09087/) (2024)
- [Properties and Challenges of LLM-Generated Explanations](https://mlsanity.com/paper/2402.10532/) (2024)
- [Ecologically Valid Explanations for Label Variation in NLI](https://mlsanity.com/paper/2310.13850/) (2023)
- [A survey on improving NLP models with human explanations](https://mlsanity.com/paper/2204.08892/) (2022)
- [From Dissonance to Insights: Dissecting Disagreements in Rationale Construction for Case Outcome Classification](https://mlsanity.com/paper/2310.11878/) (2023)
- [Investigating the Benefits of Free-Form Rationales](https://mlsanity.com/paper/2206.11083/) (2022)
- [Saliency Map Verbalization: Comparing Feature Importance Representations from Model-free and Instruction-based Methods](https://mlsanity.com/paper/2210.07222/) (2022)
- [Enhancing Systematic Decompositional Natural Language Inference Using Informal Logic](https://mlsanity.com/paper/2402.14798/) (2024)
- [FLamE: Few-shot Learning from Natural Language Explanations](https://mlsanity.com/paper/2306.08042/) (2023)
- [Characterizing Large Language Models as Rationalizers of Knowledge-intensive Tasks](https://mlsanity.com/paper/2311.05085/) (2023)
- [Cross-Refine: Improving Natural Language Explanation Generation by Learning in Tandem](https://mlsanity.com/paper/2409.07123/) (2024)
- [ER-Test: Evaluating Explanation Regularization Methods for Language Models](https://mlsanity.com/paper/2205.12542/) (2022)
- [Understanding and Predicting Human Label Variation in Natural Language Inference through Explanation](https://mlsanity.com/paper/2304.12443/) (2023)
- [Using Large Language Models to Categorize Strategic Situations and Decipher Motivations Behind Human Behaviors](https://mlsanity.com/paper/2503.15752/) (2025)
- [Agree, Disagree, Explain: Decomposing Human Label Variation in NLI through the Lens of Explanations](https://mlsanity.com/paper/2510.16458/) (2025)
- [Explanation Regeneration via Information Bottleneck](https://mlsanity.com/paper/2212.09603/) (2022)
- [LiTEx: A Linguistic Taxonomy of Explanations for Understanding Within-Label Variation in Natural Language Inference](https://mlsanity.com/paper/2505.22848/) (2025)
- [Prompting as Scientific Inquiry](https://mlsanity.com/paper/2507.00163/) (2025)
- [Scientific Explanation and Natural Language: A Unified Epistemological-Linguistic Perspective for Explainable AI](https://mlsanity.com/paper/2205.01809/) (2022)
- [On Faithfulness and Coherence of Language Explanations for Recommendation Systems](https://mlsanity.com/paper/2209.05409/) (2022)
- [Truthful Meta-Explanations for Local Interpretability of Machine Learning Models](https://mlsanity.com/paper/2212.03513/) (2022)
- [A look under the hood of the Interactive Deep Learning Enterprise (No-IDLE)](https://mlsanity.com/paper/2406.19054/) (2024)
- [Complete Evidence Extraction with Model Ensembles: A Case Study on Medical Coding](https://mlsanity.com/paper/2511.07055/) (2025)
- [Emerging categories in scientific explanations](https://mlsanity.com/paper/2505.17832/) (2025)
- [Can LLM-Generated Textual Explanations Enhance Model Classification Performance? An Empirical Study](https://mlsanity.com/paper/2508.09776/) (2025)

## Abstract (arXiv)

A growing effort in NLP aims to build datasets of human explanations. However, the term explanation encompasses a broad range of notions, each with different properties and ramifications. Our goal is to provide an overview of diverse types of explanations and human limitations, and discuss implications for collecting and using explanations in NLP. Inspired by prior work in psychology and cognitive sciences, we group existing human explanations in NLP into three categories: proximal mechanism, evidence, and procedure. These three types differ in nature and have implications for the resultant explanations. For instance, procedure is not considered explanations in psychology and connects with a rich body of work on learning from instructions. The diversity of explanations is further evidenced by proxy questions that are needed for annotators to interpret and answer open-ended why questions. Finally, explanations may require different, often deeper, understandings than predictions, which casts doubt on whether humans can provide useful explanations in some tasks.