# Self-training with Few-shot Rationalization: Teacher Explanations Aid Student in Few-shot NLU

arXiv: https://arxiv.org/abs/2109.08259 · HTML: https://mlsanity.com/paper/2109.08259/

## Key facts

- Cited by 13 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 18 of its 24 references that are in the map.
- First posted on arXiv 17 Sep 2021.

## 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, 18 of 18)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions](https://mlsanity.com/paper/1905.10044/) (2019)
- [Understanding deep learning requires rethinking generalization](https://mlsanity.com/paper/1611.03530/) (2016)
- [FEVER: a large-scale dataset for Fact Extraction and VERification](https://mlsanity.com/paper/1803.05355/) (2018)
- [Self-training with Noisy Student improves ImageNet classification](https://mlsanity.com/paper/1911.04252/) (2019)
- [Learning to Reweight Examples for Robust Deep Learning](https://mlsanity.com/paper/1803.09050/) (2018)
- [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)
- [Rethinking Pre-training and Self-training](https://mlsanity.com/paper/2006.06882/) (2020)
- [Rationalizing Neural Predictions](https://mlsanity.com/paper/1606.04155/) (2016)
- [Learning to Faithfully Rationalize by Construction](https://mlsanity.com/paper/2005.00115/) (2020)
- [Rethinking Cooperative Rationalization: Introspective Extraction and Complement Control](https://mlsanity.com/paper/1910.13294/) (2019)
- [Evaluating Explanations: How much do explanations from the teacher aid students?](https://mlsanity.com/paper/2012.00893/) (2020)
- [An Information Bottleneck Approach for Controlling Conciseness in Rationale Extraction](https://mlsanity.com/paper/2005.00652/) (2020)
- [Inferring Which Medical Treatments Work from Reports of Clinical Trials](https://mlsanity.com/paper/1904.01606/) (2019)
- [Adaptive Self-training for Few-shot Neural Sequence Labeling](https://mlsanity.com/paper/2010.03680/) (2020)
- [Weakly- and Semi-supervised Evidence Extraction](https://mlsanity.com/paper/2011.01459/) (2020)

## Built on by (most cited first, 13 of 13)

- [UNIREX: A Unified Learning Framework for Language Model Rationale Extraction](https://mlsanity.com/paper/2112.08802/) (2021)
- [Beyond Labels: Empowering Human Annotators with Natural Language Explanations through a Novel Active-Learning Architecture](https://mlsanity.com/paper/2305.12710/) (2023)
- [Does Self-Rationalization Improve Robustness to Spurious Correlations?](https://mlsanity.com/paper/2210.13575/) (2022)
- [Characterizing Large Language Models as Rationalizers of Knowledge-intensive Tasks](https://mlsanity.com/paper/2311.05085/) (2023)
- [Towards Faithful Explanations: Boosting Rationalization with Shortcuts Discovery](https://mlsanity.com/paper/2403.07955/) (2024)
- [ER-Test: Evaluating Explanation Regularization Methods for Language Models](https://mlsanity.com/paper/2205.12542/) (2022)
- [DuNST: Dual Noisy Self Training for Semi-Supervised Controllable Text Generation](https://mlsanity.com/paper/2212.08724/) (2022)
- [Rationale-Guided Few-Shot Classification to Detect Abusive Language](https://mlsanity.com/paper/2211.17046/) (2022)
- [REFER: An End-to-end Rationale Extraction Framework for Explanation Regularization](https://mlsanity.com/paper/2310.14418/) (2023)
- [Towards Faithful Explanations for Text Classification with Robustness Improvement and Explanation Guided Training](https://mlsanity.com/paper/2312.17591/) (2023)
- [Few Shot Rationale Generation using Self-Training with Dual Teachers](https://mlsanity.com/paper/2306.03315/) (2023)
- [Friend-training: Learning from Models of Different but Related Tasks](https://mlsanity.com/paper/2301.13683/) (2023)
- [KEST: Kernel Distance Based Efficient Self-Training for Improving Controllable Text Generation](https://mlsanity.com/paper/2306.10414/) (2023)

## Abstract (arXiv)

While pre-trained language models have obtained state-of-the-art performance for several natural language understanding tasks, they are quite opaque in terms of their decision-making process. While some recent works focus on rationalizing neural predictions by highlighting salient concepts in the text as justifications or rationales, they rely on thousands of labeled training examples for both task labels as well as an-notated rationales for every instance. Such extensive large-scale annotations are infeasible to obtain for many tasks. To this end, we develop a multi-task teacher-student framework based on self-training language models with limited task-specific labels and rationales, and judicious sample selection to learn from informative pseudo-labeled examples1. We study several characteristics of what constitutes a good rationale and demonstrate that the neural model performance can be significantly improved by making it aware of its rationalized predictions, particularly in low-resource settings. Extensive experiments in several bench-mark datasets demonstrate the effectiveness of our approach.