# WT5?! Training Text-to-Text Models to Explain their Predictions

arXiv: https://arxiv.org/abs/2004.14546 · HTML: https://mlsanity.com/paper/2004.14546/

## Key facts

- Cited by 148 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Apr 2020.

## Built on by (most cited first, 30 of 148)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering](https://mlsanity.com/paper/2209.09513/) (2022)
- [Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes](https://mlsanity.com/paper/2305.02301/) (2023)
- [Large Language Models Can Self-Improve](https://mlsanity.com/paper/2210.11610/) (2022)
- [Teaching language models to support answers with verified quotes](https://mlsanity.com/paper/2203.11147/) (2022)
- [Can language models learn from explanations in context?](https://mlsanity.com/paper/2204.02329/) (2022)
- [Maieutic Prompting: Logically Consistent Reasoning with Recursive Explanations](https://mlsanity.com/paper/2205.11822/) (2022)
- [A Review on Language Models as Knowledge Bases](https://mlsanity.com/paper/2204.06031/) (2022)
- [Symbolic Chain-of-Thought Distillation: Small Models Can Also "Think" Step-by-Step](https://mlsanity.com/paper/2306.14050/) (2023)
- [Natural Language Descriptions of Deep Visual Features](https://mlsanity.com/paper/2201.11114/) (2022)
- [Towards Faithful Model Explanation in NLP: A Survey](https://mlsanity.com/paper/2209.11326/) (2022)
- [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)
- [Explanations from Large Language Models Make Small Reasoners Better](https://mlsanity.com/paper/2210.06726/) (2022)
- [Rationale-Augmented Ensembles in Language Models](https://mlsanity.com/paper/2207.00747/) (2022)
- [Faithfulness Tests for Natural Language Explanations](https://mlsanity.com/paper/2305.18029/) (2023)
- [Do Transformer Modifications Transfer Across Implementations and Applications?](https://mlsanity.com/paper/2102.11972/) (2021)
- [Do Models Explain Themselves? Counterfactual Simulatability of Natural Language Explanations](https://mlsanity.com/paper/2307.08678/) (2023)
- [e-ViL: A Dataset and Benchmark for Natural Language Explanations in Vision-Language Tasks](https://mlsanity.com/paper/2105.03761/) (2021)
- [Few-Shot Self-Rationalization with Natural Language Prompts](https://mlsanity.com/paper/2111.08284/) (2021)
- [FLUTE: Figurative Language Understanding through Textual Explanations](https://mlsanity.com/paper/2205.12404/) (2022)
- [Identifying and Mitigating Spurious Correlations for Improving Robustness in NLP Models](https://mlsanity.com/paper/2110.07736/) (2021)
- [When Can Models Learn From Explanations? A Formal Framework for Understanding the Roles of Explanation Data](https://mlsanity.com/paper/2102.02201/) (2021)
- [On Measuring Faithfulness or Self-consistency of Natural Language Explanations](https://mlsanity.com/paper/2311.07466/) (2023)
- [Recitation-Augmented Language Models](https://mlsanity.com/paper/2210.01296/) (2022)
- [FiD-Light: Efficient and Effective Retrieval-Augmented Text Generation](https://mlsanity.com/paper/2209.14290/) (2022)
- [Leveraging Large Language Models in Conversational Recommender Systems](https://mlsanity.com/paper/2305.07961/) (2023)
- [Explaining black box text modules in natural language with language models](https://mlsanity.com/paper/2305.09863/) (2023)
- [NLX-GPT: A Model for Natural Language Explanations in Vision and Vision-Language Tasks](https://mlsanity.com/paper/2203.05081/) (2022)
- [ExplaGraphs: An Explanation Graph Generation Task for Structured Commonsense Reasoning](https://mlsanity.com/paper/2104.07644/) (2021)

## Abstract (arXiv)

Neural networks have recently achieved human-level performance on various challenging natural language processing (NLP) tasks, but it is notoriously difficult to understand why a neural network produced a particular prediction. In this paper, we leverage the text-to-text framework proposed by Raffel et al.(2019) to train language models to output a natural text explanation alongside their prediction. Crucially, this requires no modifications to the loss function or training and decoding procedures -- we simply train the model to output the explanation after generating the (natural text) prediction. We show that this approach not only obtains state-of-the-art results on explainability benchmarks, but also permits learning from a limited set of labeled explanations and transferring rationalization abilities across datasets. To facilitate reproducibility and future work, we release our code use to train the models.