{"total":52,"rows":[{"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":"2110.07736","title":"Identifying and Mitigating Spurious Correlations for Improving Robustness in NLP Models","created":"2021-10-14","cited_by_count":76,"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":"2306.02873","title":"DecompX: Explaining Transformers Decisions by Propagating Token Decomposition","created":"2023-06-05","cited_by_count":31,"area":null},{"id":"2212.14855","title":"Disentangled Explanations of Neural Network Predictions by Finding Relevant Subspaces","created":"2022-12-30","cited_by_count":25,"area":null},{"id":"2104.04515","title":"Connecting Attributions and QA Model Behavior on Realistic Counterfactuals","created":"2021-04-09","cited_by_count":20,"area":null},{"id":"2110.10470","title":"Interpreting Deep Learning Models in Natural Language Processing: A Review","created":"2021-10-20","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":"2109.05463","title":"Logic Traps in Evaluating Attribution Scores","created":"2021-09-12","cited_by_count":18,"area":null},{"id":"2301.09138","title":"Explaining Quantum Circuits with Shapley Values: Towards Explainable Quantum Machine Learning","created":"2023-01-22","cited_by_count":17,"area":null},{"id":"2104.06164","title":"Fast Hierarchical Games for Image Explanations","created":"2021-04-13","cited_by_count":15,"area":null},{"id":"2306.13041","title":"Towards Explainable Evaluation Metrics for Machine Translation","created":"2023-06-22","cited_by_count":15,"area":null},{"id":"2406.04606","title":"Helpful or Harmful Data? Fine-tuning-free Shapley Attribution for Explaining Language Model Predictions","created":"2024-06-07","cited_by_count":14,"area":null},{"id":"2104.04488","title":"Explaining Neural Network Predictions on Sentence Pairs via Learning Word-Group Masks","created":"2021-04-09","cited_by_count":12,"area":null},{"id":"2402.09259","title":"SyntaxShap: Syntax-aware Explainability Method for Text Generation","created":"2024-02-14","cited_by_count":11,"area":null},{"id":"2403.14459","title":"Multi-Level Explanations for Generative Language Models","created":"2024-03-21","cited_by_count":11,"area":null},{"id":"2106.01518","title":"Dissecting Generation Modes for Abstractive Summarization Models via Ablation and Attribution","created":"2021-06-03","cited_by_count":10,"area":null},{"id":"2403.06009","title":"Detectors for Safe and Reliable LLMs: Implementations, Uses, and Limitations","created":"2024-03-09","cited_by_count":10,"area":null},{"id":"2405.20434","title":"Facilitating Human-LLM Collaboration through Factuality Scores and Source Attributions","created":"2024-05-30","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":"2405.13536","title":"Attention Mechanisms Don't Learn Additive Models: Rethinking Feature Importance for Transformers","created":"2024-05-22","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":"2210.11318","title":"A Survey of Computer Vision Technologies In Urban and Controlled-environment Agriculture","created":"2022-10-20","cited_by_count":6,"area":null},{"id":"2302.02016","title":"Improving Interpretability via Explicit Word Interaction Graph Layer","created":"2023-02-03","cited_by_count":6,"area":null},{"id":"2202.09792","title":"Hierarchical Interpretation of Neural Text Classification","created":"2022-02-20","cited_by_count":5,"area":null},{"id":"2209.03798","title":"ReX: A Framework for Incorporating Temporal Information in Model-Agnostic Local Explanation Techniques","created":"2022-09-08","cited_by_count":5,"area":null},{"id":"2209.09975","title":"Power of Explanations: Towards automatic debiasing in hate speech detection","created":"2022-09-07","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":"2205.02724","title":"Implicit N-grams Induced by Recurrence","created":"2022-05-05","cited_by_count":4,"area":null},{"id":"2212.03396","title":"Learning to Select Prototypical Parts for Interpretable Sequential Data Modeling","created":"2022-12-07","cited_by_count":4,"area":null},{"id":"2402.18678","title":"RORA: Robust Free-Text Rationale Evaluation","created":"2024-02-28","cited_by_count":4,"area":null},{"id":"2502.15765","title":"Generalized Attention Flow: Feature Attribution for Transformer Models via Maximum Flow","created":"2025-02-14","cited_by_count":4,"area":null},{"id":"2204.08039","title":"Pathologies of Pre-trained Language Models in Few-shot Fine-tuning","created":"2022-04-17","cited_by_count":3,"area":null},{"id":"2201.03742","title":"Explaining Predictive Uncertainty by Looking Back at Model Explanations","created":"2022-01-11","cited_by_count":2,"area":null},{"id":"2211.03046","title":"Knowledge is Power: Understanding Causality Makes Legal judgment Prediction Models More Generalizable and Robust","created":"2022-11-06","cited_by_count":2,"area":null},{"id":"2304.14986","title":"Interpreting Vision and Language Generative Models with Semantic Visual Priors","created":"2023-04-28","cited_by_count":2,"area":null},{"id":"2405.08468","title":"Challenges and Opportunities in Text Generation Explainability","created":"2024-05-14","cited_by_count":2,"area":null},{"id":"2409.13764","title":"Local Explanations and Self-Explanations for Assessing Faithfulness in black-box LLMs","created":"2024-09-18","cited_by_count":2,"area":null},{"id":"2410.15464","title":"A Novel Interpretability Metric for Explaining Bias in Language Models: Applications on Multilingual Models from Southeast Asia","created":"2024-10-20","cited_by_count":2,"area":null},{"id":"2506.07249","title":"Bias Attribution in Filipino Language Models: Extending a Bias Interpretability Metric for Application on Agglutinative Languages","created":"2025-06-08","cited_by_count":2,"area":null},{"id":"2512.14354","title":"Enhancing Interpretability for Vision Models via Shapley Value Optimization","created":"2025-12-16","cited_by_count":2,"area":null},{"id":"2101.06232","title":"Towards interpreting ML-based automated malware detection models: a survey","created":"2021-01-15","cited_by_count":1,"area":null},{"id":"2210.13270","title":"Generating Hierarchical Explanations on Text Classification Without Connecting Rules","created":"2022-10-24","cited_by_count":1,"area":null},{"id":"2305.07224","title":"Asymmetric feature interaction for interpreting model predictions","created":"2023-05-12","cited_by_count":1,"area":null},{"id":"2403.13106","title":"Using Shapley interactions to understand how models use structure","created":"2024-03-19","cited_by_count":1,"area":null},{"id":"2109.03200","title":"ExCode-Mixed: Explainable Approaches towards Sentiment Analysis on Code-Mixed Data using BERT models","created":"2021-09-07","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":"2308.16588","title":"Interpreting Sentiment Composition with Latent Semantic Tree","created":"2023-08-31","cited_by_count":0,"area":null},{"id":"2312.08157","title":"CIDR: A Cooperative Integrated Dynamic Refining Method for Minimal Feature Removal Problem","created":"2023-12-13","cited_by_count":0,"area":null},{"id":"2403.16554","title":"PE: A Poincare Explanation Method for Fast Text Hierarchy Generation","created":"2024-03-25","cited_by_count":0,"area":null},{"id":"2606.03085","title":"Multi-component Causal Tracing in Large Language Models","created":"2026-06-02","cited_by_count":0,"area":null}],"next_cursor":null}