# Few Shot Rationale Generation using Self-Training with Dual Teachers

arXiv: https://arxiv.org/abs/2306.03315 · HTML: https://mlsanity.com/paper/2306.03315/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Self-training for few-shot NLP, one of 13 directions in Synthetic data and self-improvement for LLMs.
- Builds on 28 of its 33 references that are in the map.
- First posted on arXiv 5 Jun 2023.

## Placed in

- Synthetic data and self-improvement for LLMs / [Self-training for few-shot NLP](https://mlsanity.com/synth/self-training-for-few-shot-nlp/)

## Builds on (most cited first, 28 of 28)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [A large annotated corpus for learning natural language inference](https://mlsanity.com/paper/1508.05326/) (2015)
- [CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge](https://mlsanity.com/paper/1811.00937/) (2018)
- [A Call for Clarity in Reporting BLEU Scores](https://mlsanity.com/paper/1804.08771/) (2018)
- [STaR: Bootstrapping Reasoning With Reasoning](https://mlsanity.com/paper/2203.14465/) (2022)
- [Sequence-Level Knowledge Distillation](https://mlsanity.com/paper/1606.07947/) (2016)
- [Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?](https://mlsanity.com/paper/2004.03685/) (2020)
- [Born Again Neural Networks](https://mlsanity.com/paper/1805.04770/) (2018)
- [ERASER: A Benchmark to Evaluate Rationalized NLP Models](https://mlsanity.com/paper/1911.03429/) (2019)
- [Towards Robust Interpretability with Self-Explaining Neural Networks](https://mlsanity.com/paper/1806.07538/) (2018)
- [e-SNLI: Natural Language Inference with Natural Language Explanations](https://mlsanity.com/paper/1812.01193/) (2018)
- [Evaluating Explainable AI: Which Algorithmic Explanations Help Users Predict Model Behavior?](https://mlsanity.com/paper/2005.01831/) (2020)
- [Measuring Association Between Labels and Free-Text Rationales](https://mlsanity.com/paper/2010.12762/) (2020)
- [Revisiting Self-Training for Neural Sequence Generation](https://mlsanity.com/paper/1909.13788/) (2019)
- [WT5?! Training Text-to-Text Models to Explain their Predictions](https://mlsanity.com/paper/2004.14546/) (2020)
- [Leakage-Adjusted Simulatability: Can Models Generate Non-Trivial Explanations of Their Behavior in Natural Language?](https://mlsanity.com/paper/2010.04119/) (2020)
- [Multi-Task Self-Training for Learning General Representations](https://mlsanity.com/paper/2108.11353/) (2021)
- [Few-Shot Self-Rationalization with Natural Language Prompts](https://mlsanity.com/paper/2111.08284/) (2021)
- [Adaptive Multi-Teacher Multi-level Knowledge Distillation](https://mlsanity.com/paper/2103.04062/) (2021)
- [Reinforced Multi-Teacher Selection for Knowledge Distillation](https://mlsanity.com/paper/2012.06048/) (2020)
- [PINTO: Faithful Language Reasoning Using Prompt-Generated Rationales](https://mlsanity.com/paper/2211.01562/) (2022)
- [SemEval-2020 Task 4: Commonsense Validation and Explanation](https://mlsanity.com/paper/2007.00236/) (2020)
- [Improving Compositional Generalization with Self-Training for Data-to-Text Generation](https://mlsanity.com/paper/2110.08467/) (2021)
- [Self-training with Few-shot Rationalization: Teacher Explanations Aid Student in Few-shot NLU](https://mlsanity.com/paper/2109.08259/) (2021)
- [FRAME: Evaluating Rationale-Label Consistency Metrics for Free-Text Rationales](https://mlsanity.com/paper/2207.00779/) (2022)
- [Are Training Resources Insufficient? Predict First Then Explain!](https://mlsanity.com/paper/2110.02056/) (2021)

## Built on by (most cited first, 3 of 3)

- [Self-Rationalization in the Wild: A Large Scale Out-of-Distribution Evaluation on NLI-related tasks](https://mlsanity.com/paper/2502.04797/) (2025)
- [Corrections Meet Explanations: A Unified Framework for Explainable Grammatical Error Correction](https://mlsanity.com/paper/2502.15261/) (2025)
- [Evidence-Consistent Generative Detection under Scenario-Level Distribution Shift](https://mlsanity.com/paper/2608.21043/) (2026)

## Abstract (arXiv)

Self-rationalizing models that also generate a free-text explanation for their predicted labels are an important tool to build trustworthy AI applications. Since generating explanations for annotated labels is a laborious and costly pro cess, recent models rely on large pretrained language models (PLMs) as their backbone and few-shot learning. In this work we explore a self-training approach leveraging both labeled and unlabeled data to further improve few-shot models, under the assumption that neither human written rationales nor annotated task labels are available at scale. We introduce a novel dual-teacher learning framework, which learns two specialized teacher models for task prediction and rationalization using self-training and distills their knowledge into a multi-tasking student model that can jointly generate the task label and rationale. Furthermore, we formulate a new loss function, Masked Label Regularization (MLR) which promotes explanations to be strongly conditioned on predicted labels. Evaluation on three public datasets demonstrate that the proposed methods are effective in modeling task labels and generating faithful rationales.