{"total":67,"rows":[{"id":"2206.03208","title":"From Attribution Maps to Human-Understandable Explanations through Concept Relevance Propagation","created":"2022-06-07","cited_by_count":141,"area":null},{"id":"2108.13138","title":"Neuron-level Interpretation of Deep NLP Models: A Survey","created":"2021-08-30","cited_by_count":81,"area":null},{"id":"2103.13084","title":"Paragraph-level Rationale Extraction through Regularization: A case study on European Court of Human Rights Cases","created":"2021-03-24","cited_by_count":77,"area":null},{"id":"2303.01179","title":"SHAP-IQ: Unified Approximation of any-order Shapley Interactions","created":"2023-03-02","cited_by_count":51,"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":"2108.13654","title":"Discretized Integrated Gradients for Explaining Language Models","created":"2021-08-31","cited_by_count":46,"area":null},{"id":"2104.02297","title":"Shapley Explanation Networks","created":"2021-04-06","cited_by_count":41,"area":null},{"id":"2111.06206","title":"Defining and Quantifying the Emergence of Sparse Concepts in DNNs","created":"2021-11-11","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":"2309.17050","title":"Interpretable Long-Form Legal Question Answering with Retrieval-Augmented Large Language Models","created":"2023-09-29","cited_by_count":35,"area":"rag"},{"id":"2107.09145","title":"Adaptive wavelet distillation from neural networks through interpretations","created":"2021-07-19","cited_by_count":32,"area":null},{"id":"2203.10261","title":"FaiRR: Faithful and Robust Deductive Reasoning over Natural Language","created":"2022-03-19","cited_by_count":29,"area":"lr"},{"id":"2302.13080","title":"Does a Neural Network Really Encode Symbolic Concepts?","created":"2023-02-25","cited_by_count":27,"area":null},{"id":"2407.00886","title":"Efficient Automated Circuit Discovery in Transformers using Contextual Decomposition","created":"2024-07-01","cited_by_count":23,"area":"mechinterp"},{"id":"2405.10852","title":"KernelSHAP-IQ: Weighted Least-Square Optimization for Shapley Interactions","created":"2024-05-17","cited_by_count":22,"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":"2109.05463","title":"Logic Traps in Evaluating Attribution Scores","created":"2021-09-12","cited_by_count":18,"area":null},{"id":"2305.12895","title":"DEGREE: Decomposition Based Explanation For Graph Neural Networks","created":"2023-05-22","cited_by_count":18,"area":null},{"id":"2310.04861","title":"Uncovering hidden geometry in Transformers via disentangling position and context","created":"2023-10-07","cited_by_count":18,"area":null},{"id":"2111.03536","title":"A Unified Game-Theoretic Interpretation of Adversarial Robustness","created":"2021-11-05","cited_by_count":17,"area":null},{"id":"2303.12641","title":"Reveal to Revise: An Explainable AI Life Cycle for Iterative Bias Correction of Deep Models","created":"2023-03-22","cited_by_count":17,"area":null},{"id":"2112.02625","title":"Explainable Deep Learning in Healthcare: A Methodological Survey from an Attribution View","created":"2021-12-05","cited_by_count":15,"area":null},{"id":"2205.11097","title":"A Fine-grained Interpretability Evaluation Benchmark for Neural NLP","created":"2022-05-23","cited_by_count":15,"area":null},{"id":"2310.01011","title":"Towards Fixing Clever-Hans Predictors with Counterfactual Knowledge Distillation","created":"2023-10-02","cited_by_count":14,"area":"distill"},{"id":"2108.06895","title":"Interpreting Attributions and Interactions of Adversarial Attacks","created":"2021-08-16","cited_by_count":13,"area":null},{"id":"2210.07024","title":"Self-explaining deep models with logic rule reasoning","created":"2022-10-13","cited_by_count":13,"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":"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":"2502.00837","title":"Explainability in Practice: A Survey of Explainable NLP Across Various Domains","created":"2025-02-02","cited_by_count":11,"area":null},{"id":"2105.10719","title":"Can We Faithfully Represent Masked States to Compute Shapley Values on a DNN?","created":"2021-05-22","cited_by_count":10,"area":null},{"id":"2303.14496","title":"Learning with Explanation Constraints","created":"2023-03-25","cited_by_count":8,"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":"2312.01582","title":"Explaining with Contrastive Phrasal Highlighting: A Case Study in Assisting Humans to Detect Translation Differences","created":"2023-12-04","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":"2111.04898","title":"Machine Learning for Multimodal Electronic Health Records-based Research: Challenges and Perspectives","created":"2021-11-09","cited_by_count":7,"area":null},{"id":"2310.16607","title":"On the Interplay between Fairness and Explainability","created":"2023-10-25","cited_by_count":7,"area":null},{"id":"2311.01732","title":"Proto-lm: A Prototypical Network-Based Framework for Built-in Interpretability in Large Language Models","created":"2023-11-03","cited_by_count":7,"area":"mechinterp"},{"id":"2103.06179","title":"Towards Learning an Unbiased Classifier from Biased Data via Conditional Adversarial Debiasing","created":"2021-03-10","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":"2103.03103","title":"Interpretable Artificial Intelligence through the Lens of Feature Interaction","created":"2021-03-01","cited_by_count":5,"area":null},{"id":"2109.04922","title":"Beyond the Tip of the Iceberg: Assessing Coherence of Text Classifiers","created":"2021-09-10","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":"2210.02176","title":"Feature Importance for Time Series Data: Improving KernelSHAP","created":"2022-10-05","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":"2102.08634","title":"On the Post-hoc Explainability of Deep Echo State Networks for Time Series Forecasting, Image and Video Classification","created":"2021-02-17","cited_by_count":3,"area":null},{"id":"2104.12424","title":"Attention vs non-attention for a Shapley-based explanation method","created":"2021-04-26","cited_by_count":3,"area":null},{"id":"2307.03887","title":"Improving Prototypical Visual Explanations with Reward Reweighing, Reselection, and Retraining","created":"2023-07-08","cited_by_count":3,"area":"alignment"},{"id":"2202.00391","title":"Right for the Right Latent Factors: Debiasing Generative Models via Disentanglement","created":"2022-02-01","cited_by_count":2,"area":null},{"id":"2306.08373","title":"A semantically enhanced dual encoder for aspect sentiment triplet extraction","created":"2023-06-14","cited_by_count":2,"area":null},{"id":"2307.11906","title":"Unveiling Vulnerabilities in Interpretable Deep Learning Systems with Query-Efficient Black-box Attacks","created":"2023-07-21","cited_by_count":2,"area":null},{"id":"2410.17546","title":"Advancing Interpretability in Text Classification through Prototype Learning","created":"2024-10-23","cited_by_count":2,"area":null},{"id":"2501.13818","title":"Ensuring Medical AI Safety: Interpretability-Driven Detection and Mitigation of Spurious Model Behavior and Associated Data","created":"2025-01-23","cited_by_count":2,"area":null},{"id":"2604.19934","title":"Tracing Relational Knowledge Recall in Large Language Models","created":"2026-04-21","cited_by_count":2,"area":"mechinterp"},{"id":"2108.06847","title":"Interpreting and improving deep-learning models with reality checks","created":"2021-08-16","cited_by_count":1,"area":null},{"id":"2203.14474","title":"Interpretable Research Replication Prediction via Variational Contextual Consistency Sentence Masking","created":"2022-03-28","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":"2307.06484","title":"Single-Class Target-Specific Attack against Interpretable Deep Learning Systems","created":"2023-07-12","cited_by_count":1,"area":null},{"id":"2307.06496","title":"Microbial Genetic Algorithm-based Black-box Attack against Interpretable Deep Learning Systems","created":"2023-07-13","cited_by_count":1,"area":null},{"id":"2505.12381","title":"From n-gram to Attention: How Model Architectures Learn and Propagate Bias in Language Modeling","created":"2025-05-18","cited_by_count":1,"area":null},{"id":"2507.06427","title":"Exploring Task Performance with Interpretable Models via Sparse Auto-Encoders","created":"2025-07-08","cited_by_count":1,"area":null},{"id":"2103.07364","title":"A Unified Game-Theoretic Interpretation of Adversarial Robustness","created":"2021-03-12","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":"2212.12374","title":"Relational Local Explanations","created":"2022-12-23","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":"2509.10825","title":"CUBE: Contrastive Understanding by Balanced Experiments","created":"2025-09-13","cited_by_count":0,"area":null},{"id":"2607.14271","title":"Local Additive Feature Attribution: A Mathematical Taxonomy and Reporting Checklist","created":"2026-07-15","cited_by_count":0,"area":null}],"next_cursor":null}