{"total":68,"rows":[{"id":"2205.03401","title":"The Unreliability of Explanations in Few-shot Prompting for Textual Reasoning","created":"2022-05-06","cited_by_count":169,"area":"lr"},{"id":"2402.01761","title":"Rethinking Interpretability in the Era of Large Language Models","created":"2024-01-30","cited_by_count":111,"area":"lr"},{"id":"2108.05233","title":"EDITS: Modeling and Mitigating Data Bias for Graph Neural Networks","created":"2021-08-11","cited_by_count":92,"area":null},{"id":"2311.02262","title":"Tell Your Model Where to Attend: Post-hoc Attention Steering for LLMs","created":"2023-11-03","cited_by_count":91,"area":null},{"id":"2208.11857","title":"Shortcut Learning of Large Language Models in Natural Language Understanding","created":"2022-08-25","cited_by_count":85,"area":null},{"id":"2311.03731","title":"A Survey of Large Language Models Attribution","created":"2023-11-07","cited_by_count":71,"area":null},{"id":"2106.12674","title":"Fairness via Representation Neutralization","created":"2021-06-23","cited_by_count":63,"area":null},{"id":"2305.09863","title":"Explaining black box text modules in natural language with language models","created":"2023-05-17","cited_by_count":62,"area":null},{"id":"2203.02110","title":"FairPrune: Achieving Fairness Through Pruning for Dermatological Disease Diagnosis","created":"2022-03-04","cited_by_count":59,"area":null},{"id":"2203.08008","title":"Beyond Explaining: Opportunities and Challenges of XAI-Based Model Improvement","created":"2022-03-15","cited_by_count":48,"area":null},{"id":"2212.11261","title":"Contrastive Language-Vision AI Models Pretrained on Web-Scraped Multimodal Data Exhibit Sexual Objectification Bias","created":"2022-12-21","cited_by_count":43,"area":null},{"id":"2410.22770","title":"InjecGuard: Benchmarking and Mitigating Over-defense in Prompt Injection Guardrail Models","created":"2024-10-30","cited_by_count":42,"area":"safety"},{"id":"2104.02297","title":"Shapley Explanation Networks","created":"2021-04-06","cited_by_count":41,"area":null},{"id":"2209.11799","title":"Augmenting Interpretable Models with LLMs during Training","created":"2022-09-23","cited_by_count":38,"area":null},{"id":"2212.03954","title":"Going Beyond XAI: A Systematic Survey for Explanation-Guided Learning","created":"2022-12-07","cited_by_count":36,"area":null},{"id":"2111.07668","title":"Fast Axiomatic Attribution for Neural Networks","created":"2021-11-15","cited_by_count":35,"area":null},{"id":"2303.05506","title":"TANGOS: Regularizing Tabular Neural Networks through Gradient Orthogonalization and Specialization","created":"2023-03-09","cited_by_count":32,"area":null},{"id":"2103.10415","title":"Refining Language Models with Compositional Explanations","created":"2021-03-18","cited_by_count":27,"area":null},{"id":"2202.02838","title":"Aligning Eyes between Humans and Deep Neural Network through Interactive Attention Alignment","created":"2022-02-06","cited_by_count":27,"area":null},{"id":"2103.04243","title":"Estimating and Improving Fairness with Adversarial Learning","created":"2021-03-07","cited_by_count":26,"area":null},{"id":"2306.15786","title":"An Empirical Evaluation of the Rashomon Effect in Explainable Machine Learning","created":"2023-06-27","cited_by_count":25,"area":null},{"id":"2111.03015","title":"Modeling Techniques for Machine Learning Fairness: A Survey","created":"2021-11-04","cited_by_count":17,"area":null},{"id":"2108.13759","title":"Enjoy the Salience: Towards Better Transformer-based Faithful Explanations with Word Salience","created":"2021-08-31","cited_by_count":16,"area":null},{"id":"2207.10245","title":"The Birth of Bias: A case study on the evolution of gender bias in an English language model","created":"2022-07-21","cited_by_count":16,"area":null},{"id":"2105.10172","title":"Explainable Machine Learning with Prior Knowledge: An Overview","created":"2021-05-21","cited_by_count":15,"area":null},{"id":"2204.08892","title":"A survey on improving NLP models with human explanations","created":"2022-04-19","cited_by_count":15,"area":null},{"id":"2206.11212","title":"VisFIS: Visual Feature Importance Supervision with Right-for-the-Right-Reason Objectives","created":"2022-06-22","cited_by_count":12,"area":"lr"},{"id":"2108.13961","title":"Thermostat: A Large Collection of NLP Model Explanations and Analysis Tools","created":"2021-08-31","cited_by_count":11,"area":null},{"id":"2405.16714","title":"Crafting Interpretable Embeddings by Asking LLMs Questions","created":"2024-05-26","cited_by_count":11,"area":null},{"id":"2105.04505","title":"Towards Benchmarking the Utility of Explanations for Model Debugging","created":"2021-05-10","cited_by_count":10,"area":null},{"id":"2207.03444","title":"Fairness and Bias in Robot Learning","created":"2022-07-07","cited_by_count":10,"area":null},{"id":"2103.15429","title":"Efficient Explanations from Empirical Explainers","created":"2021-03-29","cited_by_count":9,"area":null},{"id":"2106.01809","title":"Exploring Distantly-Labeled Rationales in Neural Network Models","created":"2021-06-03","cited_by_count":8,"area":null},{"id":"2210.16978","title":"XMD: An End-to-End Framework for Interactive Explanation-Based Debugging of NLP Models","created":"2022-10-30","cited_by_count":8,"area":null},{"id":"2407.11771","title":"XEdgeAI: A Human-centered Industrial Inspection Framework with Data-centric Explainable Edge AI Approach","created":"2024-07-16","cited_by_count":8,"area":null},{"id":"2205.12542","title":"ER-Test: Evaluating Explanation Regularization Methods for Language Models","created":"2022-05-25","cited_by_count":6,"area":null},{"id":"2210.06725","title":"Assessing Out-of-Domain Language Model Performance from Few Examples","created":"2022-10-13","cited_by_count":6,"area":null},{"id":"2110.11929","title":"Double Trouble: How to not explain a text classifier's decisions using counterfactuals synthesized by masked language models?","created":"2021-10-22","cited_by_count":5,"area":null},{"id":"2404.03098","title":"Exploring the Trade-off Between Model Performance and Explanation Plausibility of Text Classifiers Using Human Rationales","created":"2024-04-03","cited_by_count":5,"area":null},{"id":"2203.12905","title":"Privileged Attribution Constrained Deep Networks for Facial Expression Recognition","created":"2022-03-24","cited_by_count":4,"area":null},{"id":"2310.07882","title":"The Thousand Faces of Explainable AI Along the Machine Learning Life Cycle: Industrial Reality and Current State of Research","created":"2023-10-11","cited_by_count":4,"area":null},{"id":"2310.14418","title":"REFER: An End-to-end Rationale Extraction Framework for Explanation Regularization","created":"2023-10-22","cited_by_count":4,"area":null},{"id":"2312.17591","title":"Towards Faithful Explanations for Text Classification with Robustness Improvement and Explanation Guided Training","created":"2023-12-29","cited_by_count":4,"area":null},{"id":"2203.12536","title":"Dynamically Refined Regularization for Improving Cross-corpora Hate Speech Detection","created":"2022-03-23","cited_by_count":3,"area":null},{"id":"2306.11386","title":"Did the Models Understand Documents? Benchmarking Models for Language Understanding in Document-Level Relation Extraction","created":"2023-06-20","cited_by_count":3,"area":null},{"id":"2308.09596","title":"Disparity, Inequality, and Accuracy Tradeoffs in Graph Neural Networks for Node Classification","created":"2023-08-18","cited_by_count":3,"area":null},{"id":"2312.01006","title":"Dual-Teacher De-biasing Distillation Framework for Multi-domain Fake News Detection","created":"2023-12-02","cited_by_count":2,"area":"distill"},{"id":"2105.02653","title":"Regularizing Explanations in Bayesian Convolutional Neural Networks","created":"2021-04-29","cited_by_count":1,"area":null},{"id":"2108.06847","title":"Interpreting and improving deep-learning models with reality checks","created":"2021-08-16","cited_by_count":1,"area":null},{"id":"2111.07448","title":"Contrastive Clustering: Toward Unsupervised Bias Reduction for Emotion and Sentiment Classification","created":"2021-11-14","cited_by_count":1,"area":null},{"id":"2212.13014","title":"Bias Mitigation Framework for Intersectional Subgroups in Neural Networks","created":"2022-12-26","cited_by_count":1,"area":null},{"id":"2407.16693","title":"Explanation Regularisation through the Lens of Attributions","created":"2024-07-23","cited_by_count":1,"area":null},{"id":"2502.01270","title":"Main Predicate and Their Arguments as Explanation Signals For Intent Classification","created":"2025-02-03","cited_by_count":1,"area":null},{"id":"2502.20268","title":"Large Language Models as Attribution Regularizers for Efficient Model Training","created":"2025-02-27","cited_by_count":1,"area":null},{"id":"2204.10467","title":"Neural Contrastive Clustering: Fully Unsupervised Bias Reduction for Sentiment Classification","created":"2022-04-22","cited_by_count":0,"area":null},{"id":"2209.08681","title":"Domain Classification-based Source-specific Term Penalization for Domain Adaptation in Hate-speech Detection","created":"2022-09-18","cited_by_count":0,"area":null},{"id":"2210.01848","title":"Explaining Patterns in Data with Language Models via Interpretable Autoprompting","created":"2022-10-04","cited_by_count":0,"area":null},{"id":"2210.06630","title":"Fairness via Adversarial Attribute Neighbourhood Robust Learning","created":"2022-10-12","cited_by_count":0,"area":null},{"id":"2403.10373","title":"Towards a general framework for improving the performance of classifiers using XAI methods","created":"2024-03-15","cited_by_count":0,"area":null},{"id":"2404.02068","title":"Using Interpretation Methods for Model Enhancement","created":"2024-04-02","cited_by_count":0,"area":null},{"id":"2407.03009","title":"Model Guidance via Explanations Turns Image Classifiers into Segmentation Models","created":"2024-07-03","cited_by_count":0,"area":null},{"id":"2407.06206","title":"The Impact of an XAI-Augmented Approach on Binary Classification with Scarce Data","created":"2024-07-01","cited_by_count":0,"area":null},{"id":"2502.12222","title":"IMPACTX: improving model performance by appropriately constraining the training with teacher explanations","created":"2025-02-17","cited_by_count":0,"area":null},{"id":"2503.11732","title":"Class-Level Feature Selection Method Using Feature Weighted Growing Self-Organising Maps","created":"2025-03-14","cited_by_count":0,"area":null},{"id":"2507.04788","title":"Machine Learning from Explanations","created":"2025-07-07","cited_by_count":0,"area":null},{"id":"2512.14719","title":"Hybrid Attribution Priors for Explainable and Robust Model Training","created":"2025-12-09","cited_by_count":0,"area":null},{"id":"2606.07524","title":"ABLE: Representing and Mapping LLMs via Attribution-Based Large-model Embedding","created":"2026-04-20","cited_by_count":0,"area":null},{"id":"2607.08641","title":"Steering Neural Network Training through Interpretable Constraints Based on Partial Dependence","created":"2026-07-09","cited_by_count":0,"area":null}],"next_cursor":null}