{"total":58,"rows":[{"id":"2309.01029","title":"Explainability for Large Language Models: A Survey","created":"2023-09-02","cited_by_count":333,"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":"2207.13243","title":"Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networks","created":"2022-07-27","cited_by_count":129,"area":null},{"id":"2401.07927","title":"Are self-explanations from Large Language Models faithful?","created":"2024-01-15","cited_by_count":101,"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":"2203.04212","title":"Measuring the Mixing of Contextual Information in the Transformer","created":"2022-03-08","cited_by_count":65,"area":null},{"id":"2212.04629","title":"Post hoc Explanations may be Ineffective for Detecting Unknown Spurious Correlation","created":"2022-12-09","cited_by_count":59,"area":null},{"id":"2407.14561","title":"NNsight and NDIF: Democratizing Access to Open-Weight Foundation Model Internals","created":"2024-07-18","cited_by_count":45,"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":"2204.10810","title":"Learning to Scaffold: Optimizing Model Explanations for Teaching","created":"2022-04-22","cited_by_count":20,"area":null},{"id":"2201.11239","title":"Diagnosing AI Explanation Methods with Folk Concepts of Behavior","created":"2022-01-27","cited_by_count":15,"area":null},{"id":"2210.11560","title":"Finding Dataset Shortcuts with Grammar Induction","created":"2022-10-20","cited_by_count":15,"area":null},{"id":"2302.14220","title":"Are Character-level Translations Worth the Wait? Comparing ByT5 and mT5 for Machine Translation","created":"2023-02-28","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":"2307.05902","title":"Stability Guarantees for Feature Attributions with Multiplicative Smoothing","created":"2023-07-12","cited_by_count":14,"area":null},{"id":"2311.07682","title":"Fuse to Forget: Bias Reduction and Selective Memorization through Model Fusion","created":"2023-11-13","cited_by_count":13,"area":null},{"id":"2205.08696","title":"The Solvability of Interpretability Evaluation Metrics","created":"2022-05-18","cited_by_count":11,"area":null},{"id":"2405.05386","title":"Interpretability Needs a New Paradigm","created":"2024-05-08","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":"2310.14840","title":"Transparency at the Source: Evaluating and Interpreting Language Models With Access to the True Distribution","created":"2023-10-23","cited_by_count":10,"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":"2508.17744","title":"Randomly Removing 50% of Dimensions in Text Embeddings has Minimal Impact on Retrieval and Classification Tasks","created":"2025-08-25","cited_by_count":8,"area":null},{"id":"2306.07397","title":"Adversarial Attacks on the Interpretation of Neuron Activation Maximization","created":"2023-06-12","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":"2210.06725","title":"Assessing Out-of-Domain Language Model Performance from Few Examples","created":"2022-10-13","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":"2404.07498","title":"Interactive Prompt Debugging with Sequence Salience","created":"2024-04-11","cited_by_count":6,"area":null},{"id":"2206.13498","title":"Auditing Visualizations: Transparency Methods Struggle to Detect Anomalous Behavior","created":"2022-06-27","cited_by_count":5,"area":null},{"id":"2310.07819","title":"Faithfulness Measurable Masked Language Models","created":"2023-10-11","cited_by_count":5,"area":null},{"id":"2310.15921","title":"Contrastive Learning-based Sentence Encoders Implicitly Weight Informative Words","created":"2023-10-24","cited_by_count":5,"area":null},{"id":"2505.06032","title":"Short-circuiting Shortcuts: Mechanistic Investigation of Shortcuts in Text Classification","created":"2025-05-09","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":"2201.05610","title":"When less is more: Simplifying inputs aids neural network understanding","created":"2022-01-14","cited_by_count":4,"area":null},{"id":"2210.13439","title":"Cascading Biases: Investigating the Effect of Heuristic Annotation Strategies on Data and Models","created":"2022-10-24","cited_by_count":4,"area":null},{"id":"2303.02860","title":"A Multi-Grained Self-Interpretable Symbolic-Neural Model For Single/Multi-Labeled Text Classification","created":"2023-03-06","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":"2311.13061","title":"Attribution and Alignment: Effects of Local Context Repetition on Utterance Production and Comprehension in Dialogue","created":"2023-11-21","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},{"id":"2502.14671","title":"Explanations of Large Language Models Explain Language Representations in the Brain","created":"2025-02-20","cited_by_count":4,"area":null},{"id":"2212.08399","title":"Assessing the Impact of Sequence Length Learning on Classification Tasks for Transformer Encoder Models","created":"2022-12-16","cited_by_count":3,"area":null},{"id":"2403.19424","title":"The Role of Syntactic Span Preferences in Post-Hoc Explanation Disagreement","created":"2024-03-28","cited_by_count":3,"area":null},{"id":"2408.11252","title":"Counterfactuals As a Means for Evaluating Faithfulness of Attribution Methods in Autoregressive Language Models","created":"2024-08-21","cited_by_count":3,"area":null},{"id":"2411.02664","title":"Explanations that reveal all through the definition of encoding","created":"2024-11-04","cited_by_count":3,"area":null},{"id":"2211.05485","title":"Understanding Text Classification Data and Models Using Aggregated Input Salience","created":"2022-11-10","cited_by_count":2,"area":null},{"id":"2311.01605","title":"Faithful and Robust Local Interpretability for Textual Predictions","created":"2023-10-30","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":"2507.09185","title":"Detecting and Pruning Prominent but Detrimental Neurons in Large Language Models","created":"2025-07-12","cited_by_count":2,"area":null},{"id":"2512.08440","title":"What Triggers my Model? Contrastive Explanations Inform Gender Choices by Translation Models","created":"2025-12-09","cited_by_count":2,"area":null},{"id":"2305.14104","title":"Out-of-Distribution Generalization in Text Classification: Past, Present, and Future","created":"2023-05-23","cited_by_count":1,"area":null},{"id":"2410.13488","title":"Seeing Through VisualBERT: A Causal Adventure on Memetic Landscapes","created":"2024-10-17","cited_by_count":1,"area":null},{"id":"2505.16406","title":"On the reliability of feature attribution methods for speech classification","created":"2025-05-22","cited_by_count":1,"area":null},{"id":"2602.08715","title":"Exploring SAIG Methods for an Objective Evaluation of XAI","created":"2026-02-09","cited_by_count":1,"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":"2411.04649","title":"DISCO: DISCovering Overfittings as Causal Rules for Text Classification Models","created":"2024-11-07","cited_by_count":0,"area":null},{"id":"2503.04989","title":"Application of integrated gradients explainability to sociopsychological semantic markers","created":"2025-03-06","cited_by_count":0,"area":null},{"id":"2604.12321","title":"ToxiTrace: Gradient-Aligned Training for Explainable Chinese Toxicity Detection","created":"2026-04-14","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}