# A survey on improving NLP models with human explanations

arXiv: https://arxiv.org/abs/2204.08892 · HTML: https://mlsanity.com/paper/2204.08892/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 51 references that are in the map.
- First posted on arXiv 19 Apr 2022.

## Builds on (most cited first, 30 of 33)

- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [e-SNLI: Natural Language Inference with Natural Language Explanations](https://mlsanity.com/paper/1812.01193/) (2018)
- [HateXplain: A Benchmark Dataset for Explainable Hate Speech Detection](https://mlsanity.com/paper/2012.10289/) (2020)
- [Explain Yourself! Leveraging Language Models for Commonsense Reasoning](https://mlsanity.com/paper/1906.02361/) (2019)
- [Mitigating Gender Bias in Natural Language Processing: Literature Review](https://mlsanity.com/paper/1906.08976/) (2019)
- [Rationalizing Neural Predictions](https://mlsanity.com/paper/1606.04155/) (2016)
- [Data Programming: Creating Large Training Sets, Quickly](https://mlsanity.com/paper/1605.07723/) (2016)
- [Measuring Association Between Labels and Free-Text Rationales](https://mlsanity.com/paper/2010.12762/) (2020)
- [A Diagnostic Study of Explainability Techniques for Text Classification](https://mlsanity.com/paper/2009.13295/) (2020)
- [Interpretations are useful: penalizing explanations to align neural networks with prior knowledge](https://mlsanity.com/paper/1909.13584/) (2019)
- [Teach Me to Explain: A Review of Datasets for Explainable Natural Language Processing](https://mlsanity.com/paper/2102.12060/) (2021)
- [Rethinking Cooperative Rationalization: Introspective Extraction and Complement Control](https://mlsanity.com/paper/1910.13294/) (2019)
- [NILE : Natural Language Inference with Faithful Natural Language Explanations](https://mlsanity.com/paper/2005.12116/) (2020)
- [Evaluating Explanations: How much do explanations from the teacher aid students?](https://mlsanity.com/paper/2012.00893/) (2020)
- [Aligning Faithful Interpretations with their Social Attribution](https://mlsanity.com/paper/2006.01067/) (2020)
- [When Can Models Learn From Explanations? A Formal Framework for Understanding the Roles of Explanation Data](https://mlsanity.com/paper/2102.02201/) (2021)
- [Incorporating Priors with Feature Attribution on Text Classification](https://mlsanity.com/paper/1906.08286/) (2019)
- [Training Classifiers with Natural Language Explanations](https://mlsanity.com/paper/1805.03818/) (2018)
- [Deriving Machine Attention from Human Rationales](https://mlsanity.com/paper/1808.09367/) (2018)
- [Explanation-Based Human Debugging of NLP Models: A Survey](https://mlsanity.com/paper/2104.15135/) (2021)
- [Rationale-Augmented Convolutional Neural Networks for Text Classification](https://mlsanity.com/paper/1605.04469/) (2016)
- [Evaluating and Characterizing Human Rationales](https://mlsanity.com/paper/2010.04736/) (2020)
- [Do Human Rationales Improve Machine Explanations?](https://mlsanity.com/paper/1905.13714/) (2019)
- [On the Diversity and Limits of Human Explanations](https://mlsanity.com/paper/2106.11988/) (2021)
- [ExpBERT: Representation Engineering with Natural Language Explanations](https://mlsanity.com/paper/2005.01932/) (2020)
- [Refining Language Models with Compositional Explanations](https://mlsanity.com/paper/2103.10415/) (2021)
- [What to Learn, and How: Toward Effective Learning from Rationales](https://mlsanity.com/paper/2112.00071/) (2021)
- [LIREx: Augmenting Language Inference with Relevant Explanation](https://mlsanity.com/paper/2012.09157/) (2020)
- [Fine-grained Sentiment Analysis with Faithful Attention](https://mlsanity.com/paper/1908.06870/) (2019)
- [Teaching Machine Comprehension with Compositional Explanations](https://mlsanity.com/paper/2005.00806/) (2020)

## Built on by (most cited first, 15 of 15)

- [Graph of Thoughts: Solving Elaborate Problems with Large Language Models](https://mlsanity.com/paper/2308.09687/) (2023)
- [Demystifying Chains, Trees, and Graphs of Thoughts](https://mlsanity.com/paper/2401.14295/) (2024)
- [Explain-then-Translate: An Analysis on Improving Program Translation with Self-generated Explanations](https://mlsanity.com/paper/2311.07070/) (2023)
- [XMD: An End-to-End Framework for Interactive Explanation-Based Debugging of NLP Models](https://mlsanity.com/paper/2210.16978/) (2022)
- [Mediators: Conversational Agents Explaining NLP Model Behavior](https://mlsanity.com/paper/2206.06029/) (2022)
- [ER-Test: Evaluating Explanation Regularization Methods for Language Models](https://mlsanity.com/paper/2205.12542/) (2022)
- [Human-LLM Hybrid Text Answer Aggregation for Crowd Annotations](https://mlsanity.com/paper/2410.17099/) (2024)
- [EXCGEC: A Benchmark for Edit-Wise Explainable Chinese Grammatical Error Correction](https://mlsanity.com/paper/2407.00924/) (2024)
- [Explanation Regularisation through the Lens of Attributions](https://mlsanity.com/paper/2407.16693/) (2024)
- [Learning from Sufficient Rationales: Analysing the Relationship Between Explanation Faithfulness and Token-level Regularisation Strategies](https://mlsanity.com/paper/2511.16353/) (2025)
- [Disagreeing Rationales: Rethinking Classification and Explainability Evaluation in Hate Speech Detection](https://mlsanity.com/paper/2605.31563/) (2026)
- [Teach Me How to Improve My Argumentation Skills: A Survey on Feedback in Argumentation](https://mlsanity.com/paper/2307.15341/) (2023)
- [Emerging categories in scientific explanations](https://mlsanity.com/paper/2505.17832/) (2025)
- [Decoding the Multimodal Maze: A Systematic Review on the Adoption of Explainability in Multimodal Attention-based Models](https://mlsanity.com/paper/2508.04427/) (2025)
- [Can LLM-Generated Textual Explanations Enhance Model Classification Performance? An Empirical Study](https://mlsanity.com/paper/2508.09776/) (2025)

## Abstract (arXiv)

Training a model with access to human explanations can improve data efficiency and model performance on in- and out-of-domain data. Adding to these empirical findings, similarity with the process of human learning makes learning from explanations a promising way to establish a fruitful human-machine interaction. Several methods have been proposed for improving natural language processing (NLP) models with human explanations, that rely on different explanation types and mechanism for integrating these explanations into the learning process. These methods are rarely compared with each other, making it hard for practitioners to choose the best combination of explanation type and integration mechanism for a specific use-case. In this paper, we give an overview of different methods for learning from human explanations, and discuss different factors that can inform the decision of which method to choose for a specific use-case.