Data to 7 Oct 2026

Incorporating Priors with Feature Attribution on Text Classification

arXiv 1906.08286 ↗First posted 19 Jun 2019cs.CLcited by 68

Not on the map. Why?

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.

Key facts. Cited by 68 papers in the map (data through 7 Oct 2026). First posted on arXiv 19 Jun 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 17; 2022: 22; 2023: 11; 2024: 10; 2025: 6; 2026: 2.

68 papers.

Sort:

By area:

2022The Unreliability of Explanations in Few-shot Prompting for Textual Reasoningcited by 169
2024Rethinking Interpretability in the Era of Large Language Modelscited by 110
2021EDITS: Modeling and Mitigating Data Bias for Graph Neural Networkscited by 92
2022Shortcut Learning of Large Language Models in Natural Language Understandingcited by 83
2023Tell Your Model Where to Attend: Post-hoc Attention Steering for LLMscited by 82
2023A Survey of Large Language Models Attributioncited by 71
2021Fairness via Representation Neutralizationcited by 63
2023Explaining black box text modules in natural language with language modelscited by 61
2022FairPrune: Achieving Fairness Through Pruning for Dermatological Disease Diagnosiscited by 59
2022Beyond Explaining: Opportunities and Challenges of XAI-Based Model Improvementcited by 48
2022Contrastive Language-Vision AI Models Pretrained on Web-Scraped Multimodal Data Exhibit Sexual Objectification Biascited by 43
2021Shapley Explanation Networkscited by 41

38 more

2022Augmenting Interpretable Models with LLMs during Trainingcited by 36
2024InjecGuard: Benchmarking and Mitigating Over-defense in Prompt Injection Guardrail Modelscited by 36
2021Fast Axiomatic Attribution for Neural Networkscited by 35
2022Going Beyond XAI: A Systematic Survey for Explanation-Guided Learningcited by 35
2023TANGOS: Regularizing Tabular Neural Networks through Gradient Orthogonalization and Specializationcited by 32
2021Refining Language Models with Compositional Explanationscited by 27
2022Aligning Eyes between Humans and Deep Neural Network through Interactive Attention Alignmentcited by 27
2021Estimating and Improving Fairness with Adversarial Learningcited by 26
2023An Empirical Evaluation of the Rashomon Effect in Explainable Machine Learningcited by 25
2021Modeling Techniques for Machine Learning Fairness: A Surveycited by 17
2021Enjoy the Salience: Towards Better Transformer-based Faithful Explanations with Word Saliencecited by 16
2022The Birth of Bias: A case study on the evolution of gender bias in an English language modelcited by 16
2022A survey on improving NLP models with human explanationscited by 15
2021Explainable Machine Learning with Prior Knowledge: An Overviewcited by 14
2022VisFIS: Visual Feature Importance Supervision with Right-for-the-Right-Reason Objectivescited by 12
2021Thermostat: A Large Collection of NLP Model Explanations and Analysis Toolscited by 11
2024Crafting Interpretable Embeddings by Asking LLMs Questionscited by 11
2021Towards Benchmarking the Utility of Explanations for Model Debuggingcited by 10
2022Fairness and Bias in Robot Learningcited by 10
2021Efficient Explanations from Empirical Explainerscited by 9
2021Exploring Distantly-Labeled Rationales in Neural Network Modelscited by 8
2022XMD: An End-to-End Framework for Interactive Explanation-Based Debugging of NLP Modelscited by 8
2024XEdgeAI: A Human-centered Industrial Inspection Framework with Data-centric Explainable Edge AI Approachcited by 7
2022ER-Test: Evaluating Explanation Regularization Methods for Language Modelscited by 6
2022Assessing Out-of-Domain Language Model Performance from Few Examplescited by 6
2021Double Trouble: How to not explain a text classifier's decisions using counterfactuals synthesized by masked language models?cited by 5
2024Exploring the Trade-off Between Model Performance and Explanation Plausibility of Text Classifiers Using Human Rationalescited by 5
2022Privileged Attribution Constrained Deep Networks for Facial Expression Recognitioncited by 4
2023The Thousand Faces of Explainable AI Along the Machine Learning Life Cycle: Industrial Reality and Current State of Researchcited by 4
2023REFER: An End-to-end Rationale Extraction Framework for Explanation Regularizationcited by 4
2023Towards Faithful Explanations for Text Classification with Robustness Improvement and Explanation Guided Trainingcited by 4
2022Dynamically Refined Regularization for Improving Cross-corpora Hate Speech Detectioncited by 3
2023Did the Models Understand Documents? Benchmarking Models for Language Understanding in Document-Level Relation Extractioncited by 3
2023Disparity, Inequality, and Accuracy Tradeoffs in Graph Neural Networks for Node Classificationcited by 3
2023Dual-Teacher De-biasing Distillation Framework for Multi-domain Fake News Detectioncited by 2
2021Regularizing Explanations in Bayesian Convolutional Neural Networkscited by 1
2021Interpreting and improving deep-learning models with reality checkscited by 1
2021Contrastive Clustering: Toward Unsupervised Bias Reduction for Emotion and Sentiment Classificationcited by 1

50 most cited of 68 All 68 (JSON)