{"total":46,"rows":[{"id":"2309.01029","title":"Explainability for Large Language Models: A Survey","created":"2023-09-02","cited_by_count":333,"area":null},{"id":"2201.08164","title":"From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI","created":"2022-01-20","cited_by_count":302,"area":null},{"id":"2201.12987","title":"Interpretable and Generalizable Graph Learning via Stochastic Attention Mechanism","created":"2022-01-31","cited_by_count":171,"area":null},{"id":"2204.06031","title":"A Review on Language Models as Knowledge Bases","created":"2022-04-12","cited_by_count":157,"area":null},{"id":"2203.14263","title":"A General Survey on Attention Mechanisms in Deep Learning","created":"2022-03-27","cited_by_count":64,"area":null},{"id":"2201.12114","title":"Rethinking Attention-Model Explainability through Faithfulness Violation Test","created":"2022-01-28","cited_by_count":43,"area":null},{"id":"2210.06929","title":"On the Explainability of Natural Language Processing Deep Models","created":"2022-10-13","cited_by_count":38,"area":null},{"id":"2312.12141","title":"Neuron-Level Knowledge Attribution in Large Language Models","created":"2023-12-19","cited_by_count":37,"area":null},{"id":"2105.03287","title":"Order in the Court: Explainable AI Methods Prone to Disagreement","created":"2021-05-07","cited_by_count":36,"area":null},{"id":"2110.13880","title":"Understanding Interlocking Dynamics of Cooperative Rationalization","created":"2021-10-26","cited_by_count":36,"area":null},{"id":"2305.09770","title":"ConvXAI: Delivering Heterogeneous AI Explanations via Conversations to Support Human-AI Scientific Writing","created":"2023-05-16","cited_by_count":31,"area":null},{"id":"2105.02657","title":"Improving the Faithfulness of Attention-based Explanations with Task-specific Information for Text Classification","created":"2021-05-06","cited_by_count":29,"area":null},{"id":"2109.06387","title":"Rationales for Sequential Predictions","created":"2021-09-14","cited_by_count":26,"area":null},{"id":"2211.13290","title":"SEAT: Stable and Explainable Attention","created":"2022-11-23","cited_by_count":25,"area":null},{"id":"2111.04927","title":"Self-Interpretable Model with TransformationEquivariant Interpretation","created":"2021-11-09","cited_by_count":21,"area":null},{"id":"2203.14266","title":"A Survey on Aspect-Based Sentiment Classification","created":"2022-03-27","cited_by_count":18,"area":null},{"id":"2501.15638","title":"A Comprehensive Survey on Self-Interpretable Neural Networks","created":"2025-01-26","cited_by_count":18,"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":"2205.04559","title":"A Song of (Dis)agreement: Evaluating the Evaluation of Explainable Artificial Intelligence in Natural Language Processing","created":"2022-05-09","cited_by_count":13,"area":null},{"id":"2105.08855","title":"Effective Attention Sheds Light On Interpretability","created":"2021-05-18","cited_by_count":11,"area":null},{"id":"2305.13088","title":"Should We Attend More or Less? Modulating Attention for Fairness","created":"2023-05-22","cited_by_count":11,"area":null},{"id":"2407.08983","title":"Towards More Trustworthy and Interpretable LLMs for Code through Syntax-Grounded Explanations","created":"2024-07-12","cited_by_count":11,"area":null},{"id":"2503.14421","title":"ExDDV: A New Dataset for Explainable Deepfake Detection in Video","created":"2025-03-18","cited_by_count":10,"area":null},{"id":"2104.05361","title":"The Great Misalignment Problem in Human Evaluation of NLP Methods","created":"2021-04-12","cited_by_count":8,"area":null},{"id":"2104.08763","title":"Making Attention Mechanisms More Robust and Interpretable with Virtual Adversarial Training","created":"2021-04-18","cited_by_count":8,"area":null},{"id":"2104.08793","title":"SalKG: Learning From Knowledge Graph Explanations for Commonsense Reasoning","created":"2021-04-18","cited_by_count":7,"area":null},{"id":"2402.08479","title":"Plausible Extractive Rationalization through Semi-Supervised Entailment Signal","created":"2024-02-13","cited_by_count":6,"area":null},{"id":"2204.11424","title":"It Takes Two Flints to Make a Fire: Multitask Learning of Neural Relation and Explanation Classifiers","created":"2022-04-25","cited_by_count":5,"area":null},{"id":"2502.10689","title":"Self-Explaining Hypergraph Neural Networks for Diagnosis Prediction","created":"2025-02-15","cited_by_count":3,"area":null},{"id":"2106.02566","title":"BR-NPA: A Non-Parametric High-Resolution Attention Model to improve the Interpretability of Attention","created":"2021-06-04","cited_by_count":2,"area":null},{"id":"2301.02080","title":"Semantic match: Debugging feature attribution methods in XAI for healthcare","created":"2023-01-05","cited_by_count":2,"area":null},{"id":"2511.05064","title":"Order-Level Attention Similarity Across Language Models: A Latent Commonality","created":"2025-11-07","cited_by_count":2,"area":null},{"id":"2205.09943","title":"Explainable Supervised Domain Adaptation","created":"2022-05-20","cited_by_count":1,"area":null},{"id":"2307.06963","title":"Is Task-Agnostic Explainable AI a Myth?","created":"2023-07-13","cited_by_count":1,"area":null},{"id":"2407.00849","title":"Towards Understanding Sensitive and Decisive Patterns in Explainable AI: A Case Study of Model Interpretation in Geometric Deep Learning","created":"2024-06-30","cited_by_count":1,"area":null},{"id":"2501.12775","title":"Regularization, Semi-supervision, and Supervision for a Plausible Attention-Based Explanation","created":"2025-01-22","cited_by_count":1,"area":null},{"id":"2503.16771","title":"Enabling Global, Human-Centered Explanations for LLMs:From Tokens to Interpretable Code and Test Generation","created":"2025-03-21","cited_by_count":1,"area":null},{"id":"2601.01089","title":"Central Dogma Transformer: Towards Mechanism-Oriented AI for Cellular Understanding","created":"2026-01-03","cited_by_count":1,"area":null},{"id":"2602.13087","title":"EXCODER: EXplainable Classification Of DiscretE time series Representations","created":"2026-02-13","cited_by_count":1,"area":null},{"id":"2210.06394","title":"On Text Style Transfer via Style Masked Language Models","created":"2022-10-12","cited_by_count":0,"area":null},{"id":"2211.08369","title":"Easy to Decide, Hard to Agree: Reducing Disagreements Between Saliency Methods","created":"2022-11-15","cited_by_count":0,"area":null},{"id":"2212.07126","title":"Explainability of Text Processing and Retrieval Methods: A Survey","created":"2022-12-14","cited_by_count":0,"area":null},{"id":"2308.13797","title":"DeLELSTM: Decomposition-based Linear Explainable LSTM to Capture Instantaneous and Long-term Effects in Time Series","created":"2023-08-26","cited_by_count":0,"area":null},{"id":"2406.00004","title":"Navigating the Future of Federated Recommendation Systems with Foundation Models","created":"2024-05-12","cited_by_count":0,"area":null},{"id":"2503.13793","title":"Mapping the Trust Terrain: LLMs in Software Engineering -- Insights and Perspectives","created":"2025-03-18","cited_by_count":0,"area":null},{"id":"2602.08500","title":"Is Meta-Path Attention an Explanation? Evidence of Alignment and Decoupling in Heterogeneous GNNs","created":"2026-02-09","cited_by_count":0,"area":null}],"next_cursor":null}