{"total":38,"rows":[{"id":"2302.13942","title":"Inseq: An Interpretability Toolkit for Sequence Generation Models","created":"2023-02-27","cited_by_count":78,"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":"2301.12971","title":"Quantifying Context Mixing in Transformers","created":"2023-01-30","cited_by_count":43,"area":null},{"id":"2302.00456","title":"Analyzing Feed-Forward Blocks in Transformers through the Lens of Attention Maps","created":"2023-02-01","cited_by_count":33,"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":"2406.12053","title":"InternalInspector $I^2$: Robust Confidence Estimation in LLMs through Internal States","created":"2024-06-17","cited_by_count":30,"area":null},{"id":"2312.02073","title":"A Glitch in the Matrix? Locating and Detecting Language Model Grounding with Fakepedia","created":"2023-12-04","cited_by_count":24,"area":null},{"id":"2310.09925","title":"Homophone Disambiguation Reveals Patterns of Context Mixing in Speech Transformers","created":"2023-10-15","cited_by_count":13,"area":null},{"id":"2406.08958","title":"An Unsupervised Approach to Achieve Supervised-Level Explainability in Healthcare Records","created":"2024-06-13","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":"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":"2401.09972","title":"Better Explain Transformers by Illuminating Important Information","created":"2024-01-18","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":"2505.08546","title":"Are We Paying Attention to Her? Investigating Gender Disambiguation and Attention in Machine Translation","created":"2025-05-13","cited_by_count":7,"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":"2411.16760","title":"LibraGrad: Balancing Gradient Flow for Universally Better Vision Transformer Attributions","created":"2024-11-24","cited_by_count":5,"area":null},{"id":"2402.03191","title":"Isotropy, Clusters, and Classifiers","created":"2024-02-05","cited_by_count":4,"area":null},{"id":"2411.16252","title":"NormXLogit: The Head-on-Top Never Lies","created":"2024-11-25","cited_by_count":4,"area":null},{"id":"2502.12992","title":"B-cos LM: Efficiently Transforming Pre-trained Language Models for Improved Explainability","created":"2025-02-18","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":"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":"2601.17958","title":"TensorLens: End-to-End Transformer Analysis via High-Order Attention Tensors","created":"2026-01-25","cited_by_count":3,"area":null},{"id":"2304.06337","title":"Computational modeling of semantic change","created":"2023-04-13","cited_by_count":2,"area":null},{"id":"2310.06977","title":"Why bother with geometry? On the relevance of linear decompositions of Transformer embeddings","created":"2023-10-10","cited_by_count":2,"area":null},{"id":"2502.03418","title":"Which Words Matter Most in Zero-Shot Prompts?","created":"2025-02-05","cited_by_count":2,"area":null},{"id":"2505.19613","title":"TESSER: Transfer-Enhancing Adversarial Attacks from Vision Transformers via Spectral and Semantic Regularization","created":"2025-05-26","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":"2601.01162","title":"Bridging the Semantic Gap for Categorical Data Clustering via Large Language Models","created":"2026-01-03","cited_by_count":2,"area":null},{"id":"2305.14735","title":"Centering the Margins: Outlier-Based Identification of Harmed Populations in Toxicity Detection","created":"2023-05-24","cited_by_count":1,"area":null},{"id":"2407.16693","title":"Explanation Regularisation through the Lens of Attributions","created":"2024-07-23","cited_by_count":1,"area":null},{"id":"2407.20274","title":"Exploring the Plausibility of Hate and Counter Speech Detectors with Explainable AI","created":"2024-07-25","cited_by_count":1,"area":null},{"id":"2410.03447","title":"How Language Models Prioritize Contextual Grammatical Cues?","created":"2024-10-04","cited_by_count":1,"area":null},{"id":"2504.02064","title":"From Text to Graph: Leveraging Graph Neural Networks for Enhanced Explainability in NLP","created":"2025-04-02","cited_by_count":1,"area":null},{"id":"2509.18010","title":"Cross-Attention is Half Explanation in Speech-to-Text Models","created":"2025-09-22","cited_by_count":1,"area":null},{"id":"2510.16439","title":"FrugalPrompt: Reducing Contextual Overhead in Large Language Models via Token Attribution","created":"2025-10-18","cited_by_count":1,"area":null},{"id":"2509.22291","title":"Bridging Fairness and Explainability: Can Input-Based Explanations Promote Fairness in Hate Speech Detection?","created":"2025-09-26","cited_by_count":0,"area":null},{"id":"2603.19742","title":"Layer-wise Target Propagation: Efficient Component Attribution through Target Centric Propagation","created":"2026-03-20","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}