# Exploring Distantly-Labeled Rationales in Neural Network Models

arXiv: https://arxiv.org/abs/2106.01809 · HTML: https://mlsanity.com/paper/2106.01809/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 28 references that are in the map.
- First posted on arXiv 3 Jun 2021.

## Builds on (most cited first, 17 of 17)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [ERASER: A Benchmark to Evaluate Rationalized NLP Models](https://mlsanity.com/paper/1911.03429/) (2019)
- [Right for the Right Reasons: Training Differentiable Models by Constraining their Explanations](https://mlsanity.com/paper/1703.03717/) (2017)
- [Rationalizing Neural Predictions](https://mlsanity.com/paper/1606.04155/) (2016)
- [A Semantic Loss Function for Deep Learning with Symbolic Knowledge](https://mlsanity.com/paper/1711.11157/) (2017)
- [Visualizing and Understanding Neural Models in NLP](https://mlsanity.com/paper/1506.01066/) (2015)
- [Rethinking Cooperative Rationalization: Introspective Extraction and Complement Control](https://mlsanity.com/paper/1910.13294/) (2019)
- [Incorporating Priors with Feature Attribution on Text Classification](https://mlsanity.com/paper/1906.08286/) (2019)
- [Deriving Machine Attention from Human Rationales](https://mlsanity.com/paper/1808.09367/) (2018)
- [Augmenting Neural Networks with First-order Logic](https://mlsanity.com/paper/1906.06298/) (2019)
- [RESIDE: Improving Distantly-Supervised Neural Relation Extraction using Side Information](https://mlsanity.com/paper/1812.04361/) (2018)
- [Towards Hierarchical Importance Attribution: Explaining Compositional Semantics for Neural Sequence Models](https://mlsanity.com/paper/1911.06194/) (2019)
- [Saliency Learning: Teaching the Model Where to Pay Attention](https://mlsanity.com/paper/1902.08649/) (2019)
- [Marrying up Regular Expressions with Neural Networks: A Case Study for Spoken Language Understanding](https://mlsanity.com/paper/1805.05588/) (2018)
- [Who is Killed by Police: Introducing Supervised Attention for Hierarchical LSTMs](https://mlsanity.com/paper/1807.03409/) (2018)

## Built on by (most cited first, 8 of 8)

- [Investigating the Benefits of Free-Form Rationales](https://mlsanity.com/paper/2206.11083/) (2022)
- [Evaluating Human Alignment and Model Faithfulness of LLM Rationale](https://mlsanity.com/paper/2407.00219/) (2024)
- [XMD: An End-to-End Framework for Interactive Explanation-Based Debugging of NLP Models](https://mlsanity.com/paper/2210.16978/) (2022)
- [ER-Test: Evaluating Explanation Regularization Methods for Language Models](https://mlsanity.com/paper/2205.12542/) (2022)
- [Exploring the Trade-off Between Model Performance and Explanation Plausibility of Text Classifiers Using Human Rationales](https://mlsanity.com/paper/2404.03098/) (2024)
- [REFER: An End-to-end Rationale Extraction Framework for Explanation Regularization](https://mlsanity.com/paper/2310.14418/) (2023)
- [Identifying Self-Disclosures of Use, Misuse and Addiction in Community-based Social Media Posts](https://mlsanity.com/paper/2311.09066/) (2023)
- [Using Interpretation Methods for Model Enhancement](https://mlsanity.com/paper/2404.02068/) (2024)

## Abstract (arXiv)

Recent studies strive to incorporate various human rationales into neural networks to improve model performance, but few pay attention to the quality of the rationales. Most existing methods distribute their models' focus to distantly-labeled rationale words entirely and equally, while ignoring the potential important non-rationale words and not distinguishing the importance of different rationale words. In this paper, we propose two novel auxiliary loss functions to make better use of distantly-labeled rationales, which encourage models to maintain their focus on important words beyond labeled rationales (PINs) and alleviate redundant training on non-helpful rationales (NoIRs). Experiments on two representative classification tasks show that our proposed methods can push a classification model to effectively learn crucial clues from non-perfect rationales while maintaining the ability to spread its focus to other unlabeled important words, thus significantly outperform existing methods.