{"total":112,"rows":[{"id":"2304.14767","title":"Dissecting Recall of Factual Associations in Auto-Regressive Language Models","created":"2023-04-28","cited_by_count":528,"area":null},{"id":"2108.04840","title":"Post-hoc Interpretability for Neural NLP: A Survey","created":"2021-08-10","cited_by_count":156,"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":"2306.01941","title":"AI Transparency in the Age of LLMs: A Human-Centered Research Roadmap","created":"2023-06-02","cited_by_count":123,"area":null},{"id":"2403.00824","title":"Information Flow Routes: Automatically Interpreting Language Models at Scale","created":"2024-02-27","cited_by_count":95,"area":null},{"id":"2310.01427","title":"Attention Sorting Combats Recency Bias In Long Context Language Models","created":"2023-09-28","cited_by_count":90,"area":null},{"id":"2202.05786","title":"Multi-Modal Knowledge Graph Construction and Application: A Survey","created":"2022-02-11","cited_by_count":74,"area":null},{"id":"2111.07367","title":"\"Will You Find These Shortcuts?\" A Protocol for Evaluating the Faithfulness of Input Salience Methods for Text Classification","created":"2021-11-14","cited_by_count":66,"area":null},{"id":"2208.05309","title":"Looking for a Needle in a Haystack: A Comprehensive Study of Hallucinations in Neural Machine Translation","created":"2022-08-10","cited_by_count":61,"area":null},{"id":"2207.14526","title":"Leveraging Explanations in Interactive Machine Learning: An Overview","created":"2022-07-29","cited_by_count":53,"area":null},{"id":"2209.14803","title":"polyBERT: A chemical language model to enable fully machine-driven ultrafast polymer informatics","created":"2022-09-29","cited_by_count":48,"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":"2204.11073","title":"Grad-SAM: Explaining Transformers via Gradient Self-Attention Maps","created":"2022-04-23","cited_by_count":42,"area":null},{"id":"2104.05824","title":"Evaluating Saliency Methods for Neural Language Models","created":"2021-04-12","cited_by_count":37,"area":null},{"id":"2105.03287","title":"Order in the Court: Explainable AI Methods Prone to Disagreement","created":"2021-05-07","cited_by_count":36,"area":null},{"id":"2110.13880","title":"Understanding Interlocking Dynamics of Cooperative Rationalization","created":"2021-10-26","cited_by_count":36,"area":null},{"id":"2305.11746","title":"HalOmi: A Manually Annotated Benchmark for Multilingual Hallucination and Omission Detection in Machine Translation","created":"2023-05-19","cited_by_count":35,"area":null},{"id":"2206.07023","title":"SBERT studies Meaning Representations: Decomposing Sentence Embeddings into Explainable Semantic Features","created":"2022-06-14","cited_by_count":33,"area":null},{"id":"2112.08802","title":"UNIREX: A Unified Learning Framework for Language Model Rationale Extraction","created":"2021-12-16","cited_by_count":32,"area":null},{"id":"2106.01087","title":"Is Sparse Attention more Interpretable?","created":"2021-06-02","cited_by_count":31,"area":null},{"id":"2110.08412","title":"Evaluating the Faithfulness of Importance Measures in NLP by Recursively Masking Allegedly Important Tokens and Retraining","created":"2021-10-15","cited_by_count":31,"area":null},{"id":"2305.09770","title":"ConvXAI: Delivering Heterogeneous AI Explanations via Conversations to Support Human-AI Scientific Writing","created":"2023-05-16","cited_by_count":31,"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":"2306.10898","title":"B-cos Alignment for Inherently Interpretable CNNs and Vision Transformers","created":"2023-06-19","cited_by_count":31,"area":null},{"id":"2104.08782","title":"On the Sensitivity and Stability of Model Interpretations in NLP","created":"2021-04-18","cited_by_count":30,"area":null},{"id":"2104.01477","title":"Exploring the Role of BERT Token Representations to Explain Sentence Probing Results","created":"2021-04-03","cited_by_count":29,"area":null},{"id":"2104.05433","title":"Multilingual Language Models Predict Human Reading Behavior","created":"2021-04-12","cited_by_count":29,"area":null},{"id":"2211.03064","title":"ViT-CX: Causal Explanation of Vision Transformers","created":"2022-11-06","cited_by_count":28,"area":null},{"id":"2306.03009","title":"Using Sequences of Life-events to Predict Human Lives","created":"2023-06-05","cited_by_count":27,"area":null},{"id":"2109.06387","title":"Rationales for Sequential Predictions","created":"2021-09-14","cited_by_count":26,"area":null},{"id":"2301.07002","title":"Opti-CAM: Optimizing saliency maps for interpretability","created":"2023-01-17","cited_by_count":25,"area":null},{"id":"2210.13836","title":"Deconfounding Legal Judgment Prediction for European Court of Human Rights Cases Towards Better Alignment with Experts","created":"2022-10-25","cited_by_count":24,"area":null},{"id":"2106.03471","title":"Relative Importance in Sentence Processing","created":"2021-06-07","cited_by_count":22,"area":null},{"id":"2203.08991","title":"AdapLeR: Speeding up Inference by Adaptive Length Reduction","created":"2022-03-16","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":"2108.13759","title":"Enjoy the Salience: Towards Better Transformer-based Faithful Explanations with Word Salience","created":"2021-08-31","cited_by_count":16,"area":null},{"id":"2404.07004","title":"LM Transparency Tool: Interactive Tool for Analyzing Transformer Language Models","created":"2024-04-10","cited_by_count":16,"area":null},{"id":"2109.01962","title":"Counterfactual Evaluation for Explainable AI","created":"2021-09-05","cited_by_count":15,"area":null},{"id":"2205.04559","title":"A Song of (Dis)agreement: Evaluating the Evaluation of Explainable Artificial Intelligence in Natural Language Processing","created":"2022-05-09","cited_by_count":13,"area":null},{"id":"2402.00794","title":"ReAGent: A Model-agnostic Feature Attribution Method for Generative Language Models","created":"2024-02-01","cited_by_count":12,"area":null},{"id":"2402.03485","title":"Attention Meets Post-hoc Interpretability: A Mathematical Perspective","created":"2024-02-05","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":"2505.15807","title":"The Atlas of In-Context Learning: How Attention Heads Shape In-Context Retrieval Augmentation","created":"2025-05-21","cited_by_count":11,"area":null},{"id":"2104.08219","title":"Flexible Instance-Specific Rationalization of NLP Models","created":"2021-04-16","cited_by_count":10,"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":"2111.08510","title":"CVSS-BERT: Explainable Natural Language Processing to Determine the Severity of a Computer Security Vulnerability from its Description","created":"2021-11-16","cited_by_count":10,"area":null},{"id":"2408.08137","title":"Normalized AOPC: Fixing Misleading Faithfulness Metrics for Feature Attribution Explainability","created":"2024-08-15","cited_by_count":10,"area":null},{"id":"2203.13397","title":"GPT-D: Inducing Dementia-related Linguistic Anomalies by Deliberate Degradation of Artificial Neural Language Models","created":"2022-03-25","cited_by_count":8,"area":null},{"id":"2301.08669","title":"Holistically Explainable Vision Transformers","created":"2023-01-20","cited_by_count":8,"area":null},{"id":"2310.05703","title":"An Attribution Method for Siamese Encoders","created":"2023-10-09","cited_by_count":8,"area":null},{"id":"2104.08793","title":"SalKG: Learning From Knowledge Graph Explanations for Commonsense Reasoning","created":"2021-04-18","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":"2402.02883","title":"Approximate Attributions for Off-the-Shelf Siamese Transformers","created":"2024-02-05","cited_by_count":7,"area":null},{"id":"2209.10876","title":"An Attention Matrix for Every Decision: Faithfulness-based Arbitration Among Multiple Attention-Based Interpretations of Transformers in Text Classification","created":"2022-09-22","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":"2108.11574","title":"Multilingual Multi-Aspect Explainability Analyses on Machine Reading Comprehension Models","created":"2021-08-26","cited_by_count":5,"area":null},{"id":"2112.05125","title":"Rethinking the Authorship Verification Experimental Setups","created":"2021-12-09","cited_by_count":5,"area":null},{"id":"2204.05428","title":"A Multilingual Perspective Towards the Evaluation of Attribution Methods in Natural Language Inference","created":"2022-04-11","cited_by_count":5,"area":null},{"id":"2212.10154","title":"Human-Guided Fair Classification for Natural Language Processing","created":"2022-12-20","cited_by_count":5,"area":null},{"id":"2303.15190","title":"Evaluating self-attention interpretability through human-grounded experimental protocol","created":"2023-03-27","cited_by_count":5,"area":null},{"id":"2308.05219","title":"Decoding Layer Saliency in Language Transformers","created":"2023-08-09","cited_by_count":5,"area":null},{"id":"2601.05328","title":"Bi-Orthogonal Factor Decomposition for Vision Transformers","created":"2026-01-08","cited_by_count":5,"area":null},{"id":"2104.00312","title":"Normal vs. Adversarial: Salience-based Analysis of Adversarial Samples for Relation Extraction","created":"2021-04-01","cited_by_count":4,"area":null},{"id":"2105.04126","title":"ExpMRC: Explainability Evaluation for Machine Reading Comprehension","created":"2021-05-10","cited_by_count":4,"area":null},{"id":"2203.01146","title":"Controlling the Focus of Pretrained Language Generation Models","created":"2022-03-02","cited_by_count":4,"area":null},{"id":"2212.08216","title":"Azimuth: Systematic Error Analysis for Text Classification","created":"2022-12-16","cited_by_count":4,"area":null},{"id":"2310.14418","title":"REFER: An End-to-end Rationale Extraction Framework for Explanation Regularization","created":"2023-10-22","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":"2403.16852","title":"Towards Explainability in Legal Outcome Prediction Models","created":"2024-03-25","cited_by_count":4,"area":null},{"id":"2103.14973","title":"Explaining the Road Not Taken","created":"2021-03-27","cited_by_count":3,"area":null},{"id":"2306.11386","title":"Did the Models Understand Documents? Benchmarking Models for Language Understanding in Document-Level Relation Extraction","created":"2023-06-20","cited_by_count":3,"area":null},{"id":"2408.14153","title":"Explaining Caption-Image Interactions in CLIP Models with Second-Order Attributions","created":"2024-08-26","cited_by_count":3,"area":null},{"id":"2106.02566","title":"BR-NPA: A Non-Parametric High-Resolution Attention Model to improve the Interpretability of Attention","created":"2021-06-04","cited_by_count":2,"area":null},{"id":"2107.05264","title":"The Brownian motion in the transformer model","created":"2021-07-12","cited_by_count":2,"area":null},{"id":"2109.08588","title":"Does Commonsense help in detecting Sarcasm?","created":"2021-09-17","cited_by_count":2,"area":null},{"id":"2110.15253","title":"Understanding How Encoder-Decoder Architectures Attend","created":"2021-10-28","cited_by_count":2,"area":null},{"id":"2203.07216","title":"A Novel Perspective to Look At Attention: Bi-level Attention-based Explainable Topic Modeling for News Classification","created":"2022-03-14","cited_by_count":2,"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":"2212.11409","title":"DExT: Detector Explanation Toolkit","created":"2022-12-21","cited_by_count":2,"area":null},{"id":"2404.07725","title":"Unraveling the Dilemma of AI Errors: Exploring the Effectiveness of Human and Machine Explanations for Large Language Models","created":"2024-04-11","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":"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":"2601.21541","title":"Vision KAN: Towards an Attention-Free Backbone for Vision with Kolmogorov-Arnold Networks","created":"2026-01-29","cited_by_count":2,"area":null},{"id":"2602.01135","title":"Your Autoregressive Model Already Reveals the Causal Graph","created":"2026-02-01","cited_by_count":2,"area":null},{"id":"2205.06546","title":"Comparison of attention models and post-hoc explanation methods for embryo stage identification: a case study","created":"2022-05-13","cited_by_count":1,"area":null},{"id":"2210.10636","title":"Using Interventions to Improve Out-of-Distribution Generalization of Text-Matching Recommendation Systems","created":"2022-10-07","cited_by_count":1,"area":null},{"id":"2406.19054","title":"A look under the hood of the Interactive Deep Learning Enterprise (No-IDLE)","created":"2024-06-27","cited_by_count":1,"area":null},{"id":"2501.12775","title":"Regularization, Semi-supervision, and Supervision for a Plausible Attention-Based Explanation","created":"2025-01-22","cited_by_count":1,"area":null},{"id":"2503.16771","title":"Enabling Global, Human-Centered Explanations for LLMs:From Tokens to Interpretable Code and Test Generation","created":"2025-03-21","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":"2509.18010","title":"Cross-Attention is Half Explanation in Speech-to-Text Models","created":"2025-09-22","cited_by_count":1,"area":null},{"id":"2601.05647","title":"Transformer Is Inherently a Causal Learner","created":"2026-01-09","cited_by_count":1,"area":null},{"id":"2603.08358","title":"Do Language Models Know Theo Has a Wife? Investigating the Proviso Problem","created":"2026-03-09","cited_by_count":1,"area":null},{"id":"2206.07587","title":"Cross-lingual AMR Aligner: Paying Attention to Cross-Attention","created":"2022-06-15","cited_by_count":0,"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":"2308.16584","title":"Unsupervised Text Style Transfer with Deep Generative Models","created":"2023-08-31","cited_by_count":0,"area":null},{"id":"2309.10421","title":"Exploring Different Levels of Supervision for Detecting and Localizing Solar Panels on Remote Sensing Imagery","created":"2023-09-19","cited_by_count":0,"area":null},{"id":"2310.10187","title":"An Interpretable Deep-Learning Framework for Predicting Hospital Readmissions From Electronic Health Records","created":"2023-10-16","cited_by_count":0,"area":null},{"id":"2312.17624","title":"XAI for In-hospital Mortality Prediction via Multimodal ICU Data","created":"2023-12-29","cited_by_count":0,"area":null},{"id":"2411.17705","title":"EEG-DCNet: A Fast and Accurate MI-EEG Dilated CNN Classification Method","created":"2024-11-12","cited_by_count":0,"area":null}],"next_cursor":"100"}