# Incorporating Priors with Feature Attribution on Text Classification

arXiv: https://arxiv.org/abs/1906.08286 · HTML: https://mlsanity.com/paper/1906.08286/

## Key facts

- Cited by 68 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Jun 2019.

## Built on by (most cited first, 30 of 68)

- [The Unreliability of Explanations in Few-shot Prompting for Textual Reasoning](https://mlsanity.com/paper/2205.03401/) (2022)
- [Rethinking Interpretability in the Era of Large Language Models](https://mlsanity.com/paper/2402.01761/) (2024)
- [EDITS: Modeling and Mitigating Data Bias for Graph Neural Networks](https://mlsanity.com/paper/2108.05233/) (2021)
- [Tell Your Model Where to Attend: Post-hoc Attention Steering for LLMs](https://mlsanity.com/paper/2311.02262/) (2023)
- [Shortcut Learning of Large Language Models in Natural Language Understanding](https://mlsanity.com/paper/2208.11857/) (2022)
- [A Survey of Large Language Models Attribution](https://mlsanity.com/paper/2311.03731/) (2023)
- [Fairness via Representation Neutralization](https://mlsanity.com/paper/2106.12674/) (2021)
- [Explaining black box text modules in natural language with language models](https://mlsanity.com/paper/2305.09863/) (2023)
- [FairPrune: Achieving Fairness Through Pruning for Dermatological Disease Diagnosis](https://mlsanity.com/paper/2203.02110/) (2022)
- [Beyond Explaining: Opportunities and Challenges of XAI-Based Model Improvement](https://mlsanity.com/paper/2203.08008/) (2022)
- [Contrastive Language-Vision AI Models Pretrained on Web-Scraped Multimodal Data Exhibit Sexual Objectification Bias](https://mlsanity.com/paper/2212.11261/) (2022)
- [InjecGuard: Benchmarking and Mitigating Over-defense in Prompt Injection Guardrail Models](https://mlsanity.com/paper/2410.22770/) (2024)
- [Shapley Explanation Networks](https://mlsanity.com/paper/2104.02297/) (2021)
- [Augmenting Interpretable Models with LLMs during Training](https://mlsanity.com/paper/2209.11799/) (2022)
- [Going Beyond XAI: A Systematic Survey for Explanation-Guided Learning](https://mlsanity.com/paper/2212.03954/) (2022)
- [Fast Axiomatic Attribution for Neural Networks](https://mlsanity.com/paper/2111.07668/) (2021)
- [TANGOS: Regularizing Tabular Neural Networks through Gradient Orthogonalization and Specialization](https://mlsanity.com/paper/2303.05506/) (2023)
- [Refining Language Models with Compositional Explanations](https://mlsanity.com/paper/2103.10415/) (2021)
- [Aligning Eyes between Humans and Deep Neural Network through Interactive Attention Alignment](https://mlsanity.com/paper/2202.02838/) (2022)
- [Estimating and Improving Fairness with Adversarial Learning](https://mlsanity.com/paper/2103.04243/) (2021)
- [An Empirical Evaluation of the Rashomon Effect in Explainable Machine Learning](https://mlsanity.com/paper/2306.15786/) (2023)
- [Modeling Techniques for Machine Learning Fairness: A Survey](https://mlsanity.com/paper/2111.03015/) (2021)
- [Enjoy the Salience: Towards Better Transformer-based Faithful Explanations with Word Salience](https://mlsanity.com/paper/2108.13759/) (2021)
- [The Birth of Bias: A case study on the evolution of gender bias in an English language model](https://mlsanity.com/paper/2207.10245/) (2022)
- [Explainable Machine Learning with Prior Knowledge: An Overview](https://mlsanity.com/paper/2105.10172/) (2021)
- [A survey on improving NLP models with human explanations](https://mlsanity.com/paper/2204.08892/) (2022)
- [VisFIS: Visual Feature Importance Supervision with Right-for-the-Right-Reason Objectives](https://mlsanity.com/paper/2206.11212/) (2022)
- [Thermostat: A Large Collection of NLP Model Explanations and Analysis Tools](https://mlsanity.com/paper/2108.13961/) (2021)
- [Crafting Interpretable Embeddings by Asking LLMs Questions](https://mlsanity.com/paper/2405.16714/) (2024)
- [Towards Benchmarking the Utility of Explanations for Model Debugging](https://mlsanity.com/paper/2105.04505/) (2021)

## Abstract (arXiv)

Feature attribution methods, proposed recently, help users interpret the predictions of complex models. Our approach integrates feature attributions into the objective function to allow machine learning practitioners to incorporate priors in model building. To demonstrate the effectiveness our technique, we apply it to two tasks: (1) mitigating unintended bias in text classifiers by neutralizing identity terms; (2) improving classifier performance in a scarce data setting by forcing the model to focus on toxic terms. Our approach adds an L2 distance loss between feature attributions and task-specific prior values to the objective. Our experiments show that i) a classifier trained with our technique reduces undesired model biases without a trade off on the original task; ii) incorporating priors helps model performance in scarce data settings.