{"total":150,"rows":[{"id":"2108.11896","title":"A Survey on Automated Fact-Checking","created":"2021-08-26","cited_by_count":378,"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":"2209.11326","title":"Towards Faithful Model Explanation in NLP: A Survey","created":"2022-09-22","cited_by_count":130,"area":null},{"id":"2204.08570","title":"A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainability","created":"2022-04-18","cited_by_count":118,"area":null},{"id":"2305.18029","title":"Faithfulness Tests for Natural Language Explanations","created":"2023-05-29","cited_by_count":107,"area":null},{"id":"2202.07304","title":"XAI for Transformers: Better Explanations through Conservative Propagation","created":"2022-02-15","cited_by_count":100,"area":null},{"id":"2302.13942","title":"Inseq: An Interpretability Toolkit for Sequence Generation Models","created":"2023-02-27","cited_by_count":78,"area":null},{"id":"2111.07367","title":"\"Will You Find These Shortcuts?\" A Protocol for Evaluating the Faithfulness of Input Salience Methods for Text Classification","created":"2021-11-14","cited_by_count":66,"area":null},{"id":"2203.04212","title":"Measuring the Mixing of Contextual Information in the Transformer","created":"2022-03-08","cited_by_count":65,"area":null},{"id":"2305.06590","title":"FactKG: Fact Verification via Reasoning on Knowledge Graphs","created":"2023-05-11","cited_by_count":57,"area":null},{"id":"2401.12874","title":"From Understanding to Utilization: A Survey on Explainability for Large Language Models","created":"2024-01-23","cited_by_count":48,"area":null},{"id":"2205.03286","title":"GlobEnc: Quantifying Global Token Attribution by Incorporating the Whole Encoder Layer in Transformers","created":"2022-05-06","cited_by_count":44,"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":"2301.12971","title":"Quantifying Context Mixing in Transformers","created":"2023-01-30","cited_by_count":43,"area":null},{"id":"2305.12535","title":"Explaining How Transformers Use Context to Build Predictions","created":"2023-05-21","cited_by_count":43,"area":null},{"id":"2107.00323","title":"Combining Feature and Instance Attribution to Detect Artifacts","created":"2021-07-01","cited_by_count":38,"area":null},{"id":"2104.05824","title":"Evaluating Saliency Methods for Neural Language Models","created":"2021-04-12","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":"2106.01087","title":"Is Sparse Attention more Interpretable?","created":"2021-06-02","cited_by_count":31,"area":null},{"id":"2306.02873","title":"DecompX: Explaining Transformers Decisions by Propagating Token Decomposition","created":"2023-06-05","cited_by_count":31,"area":null},{"id":"2104.08782","title":"On the Sensitivity and Stability of Model Interpretations in NLP","created":"2021-04-18","cited_by_count":30,"area":null},{"id":"2104.01477","title":"Exploring the Role of BERT Token Representations to Explain Sentence Probing Results","created":"2021-04-03","cited_by_count":29,"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":"2103.14625","title":"Dodrio: Exploring Transformer Models with Interactive Visualization","created":"2021-03-26","cited_by_count":28,"area":null},{"id":"2110.04392","title":"The Eval4NLP Shared Task on Explainable Quality Estimation: Overview and Results","created":"2021-10-08","cited_by_count":27,"area":null},{"id":"2306.03009","title":"Using Sequences of Life-events to Predict Human Lives","created":"2023-06-05","cited_by_count":27,"area":null},{"id":"2208.01575","title":"ferret: a Framework for Benchmarking Explainers on Transformers","created":"2022-08-02","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":"2107.03134","title":"MedGPT: Medical Concept Prediction from Clinical Narratives","created":"2021-07-07","cited_by_count":24,"area":null},{"id":"2108.12197","title":"Translation Error Detection as Rationale Extraction","created":"2021-08-27","cited_by_count":22,"area":null},{"id":"2203.00056","title":"An Empirical Study on Explanations in Out-of-Domain Settings","created":"2022-02-28","cited_by_count":21,"area":null},{"id":"2204.10810","title":"Learning to Scaffold: Optimizing Model Explanations for Teaching","created":"2022-04-22","cited_by_count":20,"area":null},{"id":"2203.08991","title":"AdapLeR: Speeding up Inference by Adaptive Length Reduction","created":"2022-03-16","cited_by_count":19,"area":null},{"id":"2403.14552","title":"Token Transformation Matters: Towards Faithful Post-hoc Explanation for Vision Transformer","created":"2024-03-21","cited_by_count":19,"area":null},{"id":"2404.01415","title":"On the Faithfulness of Vision Transformer Explanations","created":"2024-04-01","cited_by_count":19,"area":null},{"id":"2405.04793","title":"Zero-shot LLM-guided Counterfactual Generation: A Case Study on NLP Model Evaluation","created":"2024-05-08","cited_by_count":18,"area":null},{"id":"2410.02970","title":"F-Fidelity: A Robust Framework for Faithfulness Evaluation of Explainable AI","created":"2024-10-03","cited_by_count":18,"area":null},{"id":"2105.10912","title":"CiteWorth: Cite-Worthiness Detection for Improved Scientific Document Understanding","created":"2021-05-23","cited_by_count":17,"area":null},{"id":"2106.04631","title":"On the Lack of Robust Interpretability of Neural Text Classifiers","created":"2021-06-08","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":"2201.05088","title":"Grow-and-Clip: Informative-yet-Concise Evidence Distillation for Answer Explanation","created":"2022-01-13","cited_by_count":16,"area":null},{"id":"2112.06924","title":"Generating Fluent Fact Checking Explanations with Unsupervised Post-Editing","created":"2021-12-13","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":"2305.11806","title":"The Inside Story: Towards Better Understanding of Machine Translation Neural Evaluation Metrics","created":"2023-05-19","cited_by_count":15,"area":null},{"id":"2210.09197","title":"On the Impact of Temporal Concept Drift on Model Explanations","created":"2022-10-17","cited_by_count":14,"area":null},{"id":"2106.15355","title":"On the Interaction of Belief Bias and Explanations","created":"2021-06-29","cited_by_count":13,"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":"2209.07430","title":"Machine Reading, Fast and Slow: When Do Models \"Understand\" Language?","created":"2022-09-15","cited_by_count":13,"area":null},{"id":"2402.00794","title":"ReAGent: A Model-agnostic Feature Attribution Method for Generative Language Models","created":"2024-02-01","cited_by_count":12,"area":null},{"id":"2407.00219","title":"Evaluating Human Alignment and Model Faithfulness of LLM Rationale","created":"2024-06-28","cited_by_count":12,"area":null},{"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":"2212.08072","title":"Foresight -- Generative Pretrained Transformer (GPT) for Modelling of Patient Timelines using EHRs","created":"2022-12-13","cited_by_count":11,"area":null},{"id":"2310.05592","title":"InterroLang: Exploring NLP Models and Datasets through Dialogue-based Explanations","created":"2023-10-09","cited_by_count":11,"area":null},{"id":"2310.11906","title":"Rather a Nurse than a Physician -- Contrastive Explanations under Investigation","created":"2023-10-18","cited_by_count":11,"area":null},{"id":"2402.03485","title":"Attention Meets Post-hoc Interpretability: A Mathematical Perspective","created":"2024-02-05","cited_by_count":11,"area":null},{"id":"2407.19897","title":"BEExAI: Benchmark to Evaluate Explainable AI","created":"2024-07-29","cited_by_count":11,"area":null},{"id":"2502.15886","title":"A Close Look at Decomposition-based XAI-Methods for Transformer Language Models","created":"2025-02-21","cited_by_count":11,"area":null},{"id":"2602.13042","title":"GPTZero: Robust Detection of LLM-Generated Texts","created":"2026-02-13","cited_by_count":11,"area":null},{"id":"2104.08219","title":"Flexible Instance-Specific Rationalization of NLP Models","created":"2021-04-16","cited_by_count":10,"area":null},{"id":"2111.08510","title":"CVSS-BERT: Explainable Natural Language Processing to Determine the Severity of a Computer Security Vulnerability from its Description","created":"2021-11-16","cited_by_count":10,"area":null},{"id":"2312.02364","title":"Class-Discriminative Attention Maps for Vision Transformers","created":"2023-12-04","cited_by_count":10,"area":null},{"id":"2505.22823","title":"Self-Critique and Refinement for Faithful Natural Language Explanations","created":"2025-05-28","cited_by_count":10,"area":null},{"id":"2405.06604","title":"Explaining Text Similarity in Transformer Models","created":"2024-05-10","cited_by_count":9,"area":null},{"id":"2504.13787","title":"Probabilistic Stability Guarantees for Feature Attributions","created":"2025-04-18","cited_by_count":9,"area":null},{"id":"2306.12181","title":"Feature Interactions Reveal Linguistic Structure in Language Models","created":"2023-06-21","cited_by_count":8,"area":null},{"id":"2310.05703","title":"An Attribution Method for Siamese Encoders","created":"2023-10-09","cited_by_count":8,"area":null},{"id":"2401.09972","title":"Better Explain Transformers by Illuminating Important Information","created":"2024-01-18","cited_by_count":8,"area":null},{"id":"2410.02609","title":"Ethio-Fake: Cutting-Edge Approaches to Combat Fake News in Under-Resourced Languages Using Explainable AI","created":"2024-10-03","cited_by_count":8,"area":null},{"id":"2106.06528","title":"Local Explanation of Dialogue Response Generation","created":"2021-06-11","cited_by_count":7,"area":null},{"id":"2203.03668","title":"A Typology for Exploring the Mitigation of Shortcut Behavior","created":"2022-03-04","cited_by_count":7,"area":null},{"id":"2211.03041","title":"Calibration Meets Explanation: A Simple and Effective Approach for Model Confidence Estimates","created":"2022-11-06","cited_by_count":7,"area":null},{"id":"2309.07733","title":"Explaining Speech Classification Models via Word-Level Audio Segments and Paralinguistic Features","created":"2023-09-14","cited_by_count":7,"area":null},{"id":"2310.01188","title":"Quantifying the Plausibility of Context Reliance in Neural Machine Translation","created":"2023-10-02","cited_by_count":7,"area":null},{"id":"2402.02883","title":"Approximate Attributions for Off-the-Shelf Siamese Transformers","created":"2024-02-05","cited_by_count":7,"area":null},{"id":"2402.13016","title":"Understanding the effects of language-specific class imbalance in multilingual fine-tuning","created":"2024-02-20","cited_by_count":7,"area":null},{"id":"2403.04758","title":"KnowledgeVIS: Interpreting Language Models by Comparing Fill-in-the-Blank Prompts","created":"2024-03-07","cited_by_count":7,"area":null},{"id":"2403.20322","title":"Towards a Framework for Evaluating Explanations in Automated Fact Verification","created":"2024-03-29","cited_by_count":7,"area":null},{"id":"2501.15374","title":"Evaluating the Effectiveness of XAI Techniques for Encoder-Based Language Models","created":"2025-01-26","cited_by_count":7,"area":null},{"id":"2503.05050","title":"A Unified Framework with Novel Metrics for Evaluating the Effectiveness of XAI Techniques in LLMs","created":"2025-03-06","cited_by_count":7,"area":null},{"id":"2109.03756","title":"Diagnostics-Guided Explanation Generation","created":"2021-09-08","cited_by_count":6,"area":null},{"id":"2110.08887","title":"Schr\\\"odinger's Tree -- On Syntax and Neural Language Models","created":"2021-10-17","cited_by_count":6,"area":null},{"id":"2210.08500","title":"This Patient Looks Like That Patient: Prototypical Networks for Interpretable Diagnosis Prediction from Clinical Text","created":"2022-10-16","cited_by_count":6,"area":null},{"id":"2403.04760","title":"iScore: Visual Analytics for Interpreting How Language Models Automatically Score Summaries","created":"2024-03-07","cited_by_count":6,"area":null},{"id":"2403.12809","title":"Comparing Explanation Faithfulness between Multilingual and Monolingual Fine-tuned Language Models","created":"2024-03-19","cited_by_count":6,"area":null},{"id":"2405.11891","title":"Unveiling and Manipulating Prompt Influence in Large Language Models","created":"2024-05-20","cited_by_count":6,"area":null},{"id":"2406.02625","title":"Progressive Inference: Explaining Decoder-Only Sequence Classification Models Using Intermediate Predictions","created":"2024-06-03","cited_by_count":6,"area":null},{"id":"2103.14465","title":"Zero-shot Sequence Labeling for Transformer-based Sentence Classifiers","created":"2021-03-26","cited_by_count":5,"area":null},{"id":"2204.05428","title":"A Multilingual Perspective Towards the Evaluation of Attribution Methods in Natural Language Inference","created":"2022-04-11","cited_by_count":5,"area":null},{"id":"2304.01680","title":"Can BERT eat RuCoLA? Topological Data Analysis to Explain","created":"2023-04-04","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":"2406.15085","title":"Evaluating Input Feature Explanations through a Unified Diagnostic Evaluation Framework","created":"2024-06-21","cited_by_count":5,"area":null},{"id":"2407.19471","title":"On the Evaluation Consistency of Attribution-based Explanations","created":"2024-07-28","cited_by_count":5,"area":null},{"id":"2506.03484","title":"Explainable AI: XAI-Guided Context-Aware Data Augmentation","created":"2025-06-04","cited_by_count":5,"area":null},{"id":"2506.08713","title":"Explainable Compliance Detection with Multi-Hop Natural Language Inference on Assurance Case Structure","created":"2025-06-10","cited_by_count":5,"area":null},{"id":"2110.02058","title":"Interactively Providing Explanations for Transformer Language Models","created":"2021-09-02","cited_by_count":4,"area":null},{"id":"2207.13948","title":"An Interpretability Evaluation Benchmark for Pre-trained Language Models","created":"2022-07-28","cited_by_count":4,"area":null},{"id":"2212.08216","title":"Azimuth: Systematic Error Analysis for Text Classification","created":"2022-12-16","cited_by_count":4,"area":null},{"id":"2310.05619","title":"Dynamic Top-k Estimation Consolidates Disagreement between Feature Attribution Methods","created":"2023-10-09","cited_by_count":4,"area":null},{"id":"2312.07991","title":"Accelerating the Global Aggregation of Local Explanations","created":"2023-12-13","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}],"next_cursor":"100"}