{"list":"other","total":59,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"id":"1705.07874","title":"A Unified Approach to Interpreting Model Predictions","created":"2017-05-22","cited_by_count":6555},{"id":"1602.04938","title":"\"Why Should I Trust You?\": Explaining the Predictions of Any Classifier","created":"2016-02-16","cited_by_count":5070},{"id":"1911.02116","title":"Unsupervised Cross-lingual Representation Learning at Scale","created":"2019-11-05","cited_by_count":3935},{"id":"1703.01365","title":"Axiomatic Attribution for Deep Networks","created":"2017-03-04","cited_by_count":3384},{"id":"1512.04150","title":"Learning Deep Features for Discriminative Localization","created":"2015-12-14","cited_by_count":2436},{"id":"1311.2901","title":"Visualizing and Understanding Convolutional Networks","created":"2013-11-12","cited_by_count":2290},{"id":"1802.05365","title":"Deep contextualized word representations","created":"2018-02-15","cited_by_count":2290},{"id":"1704.02685","title":"Learning Important Features Through Propagating Activation Differences","created":"2017-04-10","cited_by_count":1458},{"id":"1711.11279","title":"Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)","created":"2017-11-30","cited_by_count":1319},{"id":"1706.03825","title":"SmoothGrad: removing noise by adding noise","created":"2017-06-12","cited_by_count":1109},{"id":"1905.05950","title":"BERT Rediscovers the Classical NLP Pipeline","created":"2019-05-15","cited_by_count":1059},{"id":"1906.04341","title":"What Does BERT Look At? An Analysis of BERT's Attention","created":"2019-06-11","cited_by_count":1003},{"id":"1902.10186","title":"Attention is not Explanation","created":"2019-02-26","cited_by_count":929},{"id":"2002.12327","title":"A Primer in BERTology: What we know about how BERT works","created":"2020-02-27","cited_by_count":815},{"id":"1909.00512","title":"How Contextual are Contextualized Word Representations? Comparing the Geometry of BERT, ELMo, and GPT-2 Embeddings","created":"2019-09-02","cited_by_count":784},{"id":"2005.00928","title":"Quantifying Attention Flow in Transformers","created":"2020-05-02","cited_by_count":775},{"id":"1908.04626","title":"Attention is not not Explanation","created":"2019-08-13","cited_by_count":636},{"id":"2012.09838","title":"Transformer Interpretability Beyond Attention Visualization","created":"2020-12-17","cited_by_count":627},{"id":"1911.03429","title":"ERASER: A Benchmark to Evaluate Rationalized NLP Models","created":"2019-11-08","cited_by_count":530},{"id":"1906.03731","title":"Is Attention Interpretable?","created":"2019-06-09","cited_by_count":389},{"id":"1903.08855","title":"Linguistic Knowledge and Transferability of Contextual Representations","created":"2019-03-21","cited_by_count":383},{"id":"2201.08164","title":"From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI","created":"2022-01-20","cited_by_count":302},{"id":"1908.08593","title":"Revealing the Dark Secrets of BERT","created":"2019-08-21","cited_by_count":301},{"id":"1906.05714","title":"A Multiscale Visualization of Attention in the Transformer Model","created":"2019-06-12","cited_by_count":292},{"id":"1901.05287","title":"Assessing BERT's Syntactic Abilities","created":"2019-01-16","cited_by_count":192},{"id":"1905.00780","title":"Full-Gradient Representation for Neural Network Visualization","created":"2019-05-02","cited_by_count":191},{"id":"1903.10318","title":"Fine-tune BERT for Extractive Summarization","created":"2019-03-25","cited_by_count":122},{"id":"2402.05602","title":"AttnLRP: Attention-Aware Layer-Wise Relevance Propagation for Transformers","created":"2024-02-08","cited_by_count":120},{"id":"2002.04138","title":"Explaining Explanations: Axiomatic Feature Interactions for Deep Networks","created":"2020-02-10","cited_by_count":103},{"id":"2106.09788","title":"Guided Integrated Gradients: An Adaptive Path Method for Removing Noise","created":"2021-06-17","cited_by_count":102},{"id":"1706.07206","title":"Explaining Recurrent Neural Network Predictions in Sentiment Analysis","created":"2017-06-22","cited_by_count":88},{"id":"2405.00208","title":"A Primer on the Inner Workings of Transformer-based Language Models","created":"2024-04-30","cited_by_count":85},{"id":"2203.04212","title":"Measuring the Mixing of Contextual Information in the Transformer","created":"2022-03-08","cited_by_count":65},{"id":"2305.03210","title":"AttentionViz: A Global View of Transformer Attention","created":"2023-05-04","cited_by_count":50},{"id":"2211.03263","title":"AfroLM: A Self-Active Learning-based Multilingual Pretrained Language Model for 23 African Languages","created":"2022-11-07","cited_by_count":46},{"id":"2409.00265","title":"Explainable Artificial Intelligence: A Survey of Needs, Techniques, Applications, and Future Direction","created":"2024-08-30","cited_by_count":46},{"id":"2403.01509","title":"Fantastic Semantics and Where to Find Them: Investigating Which Layers of Generative LLMs Reflect Lexical Semantics","created":"2024-03-03","cited_by_count":44},{"id":"2406.18406","title":"IRCAN: Mitigating Knowledge Conflicts in LLM Generation via Identifying and Reweighting Context-Aware Neurons","created":"2024-06-26","cited_by_count":38},{"id":"2010.06396","title":"Interpreting Attention Models with Human Visual Attention in Machine Reading Comprehension","created":"2020-10-13","cited_by_count":29},{"id":"2106.03471","title":"Relative Importance in Sentence Processing","created":"2021-06-07","cited_by_count":22},{"id":"2509.17178","title":"Attention Consistency for LLMs Explanation","created":"2025-09-21","cited_by_count":11},{"id":"2410.00134","title":"Semantic-Driven Topic Modeling Using Transformer-Based Embeddings and Clustering Algorithms","created":"2024-09-30","cited_by_count":8},{"id":"2410.02609","title":"Ethio-Fake: Cutting-Edge Approaches to Combat Fake News in Under-Resourced Languages Using Explainable AI","created":"2024-10-03","cited_by_count":8},{"id":"2501.13066","title":"SMART-Vision: Survey of Modern Action Recognition Techniques in Vision","created":"2025-01-22","cited_by_count":8},{"id":"2312.04764","title":"First Attempt at Building Parallel Corpora for Machine Translation of Northeast India's Very Low-Resource Languages","created":"2023-12-08","cited_by_count":7},{"id":"2501.15374","title":"Evaluating the Effectiveness of XAI Techniques for Encoder-Based Language Models","created":"2025-01-26","cited_by_count":7},{"id":"2503.05050","title":"A Unified Framework with Novel Metrics for Evaluating the Effectiveness of XAI Techniques in LLMs","created":"2025-03-06","cited_by_count":7},{"id":"2412.18036","title":"Explainability in Neural Networks for Natural Language Processing Tasks","created":"2024-12-23","cited_by_count":6},{"id":"2308.05219","title":"Decoding Layer Saliency in Language Transformers","created":"2023-08-09","cited_by_count":5},{"id":"2506.03484","title":"Explainable AI: XAI-Guided Context-Aware Data Augmentation","created":"2025-06-04","cited_by_count":5},{"id":"2502.15765","title":"Generalized Attention Flow: Feature Attribution for Transformer Models via Maximum Flow","created":"2025-02-14","cited_by_count":4},{"id":"2509.25539","title":"Toxicity in Online Platforms and AI Systems: A Survey of Needs, Challenges, Mitigations, and Future Directions","created":"2025-09-29","cited_by_count":3},{"id":"2509.16835","title":"Semantic-Driven Topic Modeling for Analyzing Creativity in Virtual Brainstorming","created":"2025-09-20","cited_by_count":2},{"id":"2507.21186","title":"Contrast-CAT: Contrasting Activations for Enhanced Interpretability in Transformer-based Text Classifiers","created":"2025-07-27","cited_by_count":1}],"next_cursor":null}