# Are Hard Examples also Harder to Explain? A Study with Human and Model-Generated Explanations

arXiv: https://arxiv.org/abs/2211.07517 · HTML: https://mlsanity.com/paper/2211.07517/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 45 references that are in the map.
- First posted on arXiv 14 Nov 2022.

## Builds on (most cited first, 30 of 32)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [Calibrate Before Use: Improving Few-Shot Performance of Language Models](https://mlsanity.com/paper/2102.09690/) (2021)
- [Explanation in Artificial Intelligence: Insights from the Social Sciences](https://mlsanity.com/paper/1706.07269/) (2017)
- [Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity](https://mlsanity.com/paper/2104.08786/) (2021)
- [Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inference](https://mlsanity.com/paper/2001.07676/) (2020)
- [Show Your Work: Scratchpads for Intermediate Computation with Language Models](https://mlsanity.com/paper/2112.00114/) (2021)
- [Attention is not not Explanation](https://mlsanity.com/paper/1908.04626/) (2019)
- [Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?](https://mlsanity.com/paper/2004.03685/) (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)
- [Dataset Cartography: Mapping and Diagnosing Datasets with Training Dynamics](https://mlsanity.com/paper/2009.10795/) (2020)
- [Explain Yourself! Leveraging Language Models for Commonsense Reasoning](https://mlsanity.com/paper/1906.02361/) (2019)
- [Can language models learn from explanations in context?](https://mlsanity.com/paper/2204.02329/) (2022)
- [WANLI: Worker and AI Collaboration for Natural Language Inference Dataset Creation](https://mlsanity.com/paper/2201.05955/) (2022)
- [Unsupervised Commonsense Question Answering with Self-Talk](https://mlsanity.com/paper/2004.05483/) (2020)
- [WT5?! Training Text-to-Text Models to Explain their Predictions](https://mlsanity.com/paper/2004.14546/) (2020)
- [Teach Me to Explain: A Review of Datasets for Explainable Natural Language Processing](https://mlsanity.com/paper/2102.12060/) (2021)
- [Reframing Human-AI Collaboration for Generating Free-Text Explanations](https://mlsanity.com/paper/2112.08674/) (2021)
- [Leakage-Adjusted Simulatability: Can Models Generate Non-Trivial Explanations of Their Behavior in Natural Language?](https://mlsanity.com/paper/2010.04119/) (2020)
- [GLUCOSE: GeneraLized and COntextualized Story Explanations](https://mlsanity.com/paper/2009.07758/) (2020)
- [Few-Shot Self-Rationalization with Natural Language Prompts](https://mlsanity.com/paper/2111.08284/) (2021)
- [WorldTree: A Corpus of Explanation Graphs for Elementary Science Questions supporting Multi-Hop Inference](https://mlsanity.com/paper/1802.03052/) (2018)
- [ExplaGraphs: An Explanation Graph Generation Task for Structured Commonsense Reasoning](https://mlsanity.com/paper/2104.07644/) (2021)
- [WinoWhy: A Deep Diagnosis of Essential Commonsense Knowledge for Answering Winograd Schema Challenge](https://mlsanity.com/paper/2005.05763/) (2020)
- [Rationalization: A Neural Machine Translation Approach to Generating Natural Language Explanations](https://mlsanity.com/paper/1702.07826/) (2017)

## Built on by (most cited first, 7 of 7)

- [Phenomenal Yet Puzzling: Testing Inductive Reasoning Capabilities of Language Models with Hypothesis Refinement](https://mlsanity.com/paper/2310.08559/) (2023)
- [Large Language Models are Temporal and Causal Reasoners for Video Question Answering](https://mlsanity.com/paper/2310.15747/) (2023)
- [Legal Syllogism Prompting: Teaching Large Language Models for Legal Judgment Prediction](https://mlsanity.com/paper/2307.08321/) (2023)
- [Explainable Generative AI (GenXAI): A Survey, Conceptualization, and Research Agenda](https://mlsanity.com/paper/2404.09554/) (2024)
- [Can Language Models Teach Weaker Agents? Teacher Explanations Improve Students via Personalization](https://mlsanity.com/paper/2306.09299/) (2023)
- [ExplainCPE: A Free-text Explanation Benchmark of Chinese Pharmacist Examination](https://mlsanity.com/paper/2305.12945/) (2023)
- [Mixed Signals: Understanding Model Disagreement in Multimodal Empathy Detection](https://mlsanity.com/paper/2505.13979/) (2025)

## Abstract (arXiv)

Recent work on explainable NLP has shown that few-shot prompting can enable large pretrained language models (LLMs) to generate grammatical and factual natural language explanations for data labels. In this work, we study the connection between explainability and sample hardness by investigating the following research question - "Are LLMs and humans equally good at explaining data labels for both easy and hard samples?" We answer this question by first collecting human-written explanations in the form of generalizable commonsense rules on the task of Winograd Schema Challenge (Winogrande dataset). We compare these explanations with those generated by GPT-3 while varying the hardness of the test samples as well as the in-context samples. We observe that (1) GPT-3 explanations are as grammatical as human explanations regardless of the hardness of the test samples, (2) for easy examples, GPT-3 generates highly supportive explanations but human explanations are more generalizable, and (3) for hard examples, human explanations are significantly better than GPT-3 explanations both in terms of label-supportiveness and generalizability judgements. We also find that hardness of the in-context examples impacts the quality of GPT-3 explanations. Finally, we show that the supportiveness and generalizability aspects of human explanations are also impacted by sample hardness, although by a much smaller margin than models. Supporting code and data are available at https://github.com/swarnaHub/ExplanationHardness