{"total":43,"rows":[{"id":"2209.11326","title":"Towards Faithful Model Explanation in NLP: A Survey","created":"2022-09-22","cited_by_count":130,"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":"2205.11631","title":"Towards Opening the Black Box of Neural Machine Translation: Source and Target Interpretations of the Transformer","created":"2022-05-23","cited_by_count":45,"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":"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":"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":"2212.10474","title":"ByGPT5: End-to-End Style-conditioned Poetry Generation with Token-free Language Models","created":"2022-12-20","cited_by_count":25,"area":null},{"id":"2212.11185","title":"Entropy- and Distance-Based Predictors From GPT-2 Attention Patterns Predict Reading Times Over and Above GPT-2 Surprisal","created":"2022-12-21","cited_by_count":14,"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":"2305.18294","title":"Transformer Language Models Handle Word Frequency in Prediction Head","created":"2023-05-29","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":"2310.19084","title":"Roles of Scaling and Instruction Tuning in Language Perception: Model vs. Human Attention","created":"2023-10-29","cited_by_count":7,"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":"2305.10614","title":"Token-wise Decomposition of Autoregressive Language Model Hidden States for Analyzing Model Predictions","created":"2023-05-17","cited_by_count":6,"area":null},{"id":"2406.06581","title":"Order-Independence Without Fine Tuning","created":"2024-06-04","cited_by_count":6,"area":null},{"id":"2406.17837","title":"Transformer Normalisation Layers and the Independence of Semantic Subspaces","created":"2024-06-25","cited_by_count":6,"area":null},{"id":"2204.09028","title":"On the Locality of Attention in Direct Speech Translation","created":"2022-04-19","cited_by_count":5,"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":"2205.10696","title":"Life after BERT: What do Other Muppets Understand about Language?","created":"2022-05-21","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":"2412.11187","title":"Analyzing the Attention Heads for Pronoun Disambiguation in Context-aware Machine Translation Models","created":"2024-12-15","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":"2309.11585","title":"SpeechAlign: a Framework for Speech Translation Alignment Evaluation","created":"2023-09-20","cited_by_count":2,"area":null},{"id":"2405.15903","title":"UnitNorm: Rethinking Normalization for Transformers in Time Series","created":"2024-05-24","cited_by_count":2,"area":null},{"id":"2410.18541","title":"On Explaining with Attention Matrices","created":"2024-10-24","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":"2407.16693","title":"Explanation Regularisation through the Lens of Attributions","created":"2024-07-23","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":"2509.18010","title":"Cross-Attention is Half Explanation in Speech-to-Text Models","created":"2025-09-22","cited_by_count":1,"area":null},{"id":"2606.00124","title":"Positional Encodings Anchor Spatial Structure in Vision Transformers: A Geometric Perspective on Robustness","created":"2026-05-28","cited_by_count":1,"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":"2606.07604","title":"Contribution Weights: A Geometrical Analysis of Self-Attention Transformers","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2608.14021","title":"Residual Dominance as a Structural Account of Last-Item Reliance in Causal Self-Attention Recommenders","created":"2026-08-14","cited_by_count":0,"area":null},{"id":"2609.28117","title":"Scaling Attention Head Analysis via Gradient-Based Attribution in Context-Aware Machine Translation","created":"2026-09-23","cited_by_count":0,"area":null}],"next_cursor":null}