# Investigating the Effect of Natural Language Explanations on Out-of-Distribution Generalization in Few-shot NLI

arXiv: https://arxiv.org/abs/2110.06223 · HTML: https://mlsanity.com/paper/2110.06223/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 18 references that are in the map.
- First posted on arXiv 12 Oct 2021.

## Builds on (most cited first, 11 of 11)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference](https://mlsanity.com/paper/1902.01007/) (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)
- [Don't Take the Easy Way Out: Ensemble Based Methods for Avoiding Known Dataset Biases](https://mlsanity.com/paper/1909.03683/) (2019)
- [Adversarial Filters of Dataset Biases](https://mlsanity.com/paper/2002.04108/) (2020)
- [WT5?! Training Text-to-Text Models to Explain their Predictions](https://mlsanity.com/paper/2004.14546/) (2020)
- [Conditionally Adaptive Multi-Task Learning: Improving Transfer Learning in NLP Using Fewer Parameters & Less Data](https://mlsanity.com/paper/2009.09139/) (2020)
- [Towards Realistic Practices In Low-Resource Natural Language Processing: The Development Set](https://mlsanity.com/paper/1909.01522/) (2019)

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

- [The Unreliability of Explanations in Few-shot Prompting for Textual Reasoning](https://mlsanity.com/paper/2205.03401/) (2022)
- [State-of-the-art generalisation research in NLP: A taxonomy and review](https://mlsanity.com/paper/2210.03050/) (2022)
- [Shall We Pretrain Autoregressive Language Models with Retrieval? A Comprehensive Study](https://mlsanity.com/paper/2304.06762/) (2023)
- [FLamE: Few-shot Learning from Natural Language Explanations](https://mlsanity.com/paper/2306.08042/) (2023)
- [Self-Rationalization in the Wild: A Large Scale Out-of-Distribution Evaluation on NLI-related tasks](https://mlsanity.com/paper/2502.04797/) (2025)
- [Bayesian Cross-Modal Alignment Learning for Few-Shot Out-of-Distribution Generalization](https://mlsanity.com/paper/2504.09448/) (2025)
- [Do Generalisation Results Generalise?](https://mlsanity.com/paper/2512.07832/) (2025)

## Abstract (arXiv)

Although neural models have shown strong performance in datasets such as SNLI, they lack the ability to generalize out-of-distribution (OOD). In this work, we formulate a few-shot learning setup and examine the effects of natural language explanations on OOD generalization. We leverage the templates in the HANS dataset and construct templated natural language explanations for each template. Although generated explanations show competitive BLEU scores against groundtruth explanations, they fail to improve prediction performance. We further show that generated explanations often hallucinate information and miss key elements that indicate the label.