{"list":"other","total":71,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1602.04938","title":"\"Why Should I Trust You?\": Explaining the Predictions of Any Classifier","created":"2016-02-16","cited_by_count":5070},{"id":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"1703.01365","title":"Axiomatic Attribution for Deep Networks","created":"2017-03-04","cited_by_count":3384},{"id":"1409.3215","title":"Sequence to Sequence Learning with Neural Networks","created":"2014-09-10","cited_by_count":2986},{"id":"1508.07909","title":"Neural Machine Translation of Rare Words with Subword Units","created":"2015-08-31","cited_by_count":2918},{"id":"2202.05262","title":"Locating and Editing Factual Associations in GPT","created":"2022-02-10","cited_by_count":2691},{"id":"1312.6034","title":"Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps","created":"2013-12-20","cited_by_count":2371},{"id":"1311.2901","title":"Visualizing and Understanding Convolutional Networks","created":"2013-11-12","cited_by_count":2290},{"id":"2309.17453","title":"Efficient Streaming Language Models with Attention Sinks","created":"2023-09-29","cited_by_count":2186},{"id":"1808.06226","title":"SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing","created":"2018-08-19","cited_by_count":1989},{"id":"2005.08100","title":"Conformer: Convolution-augmented Transformer for Speech Recognition","created":"2020-05-16","cited_by_count":1863},{"id":"1804.08771","title":"A Call for Clarity in Reporting BLEU Scores","created":"2018-04-23","cited_by_count":1799},{"id":"1910.10045","title":"Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI","created":"2019-10-22","cited_by_count":1552},{"id":"1704.02685","title":"Learning Important Features Through Propagating Activation Differences","created":"2017-04-10","cited_by_count":1458},{"id":"1702.08608","title":"Towards A Rigorous Science of Interpretable Machine Learning","created":"2017-02-28","cited_by_count":1416},{"id":"1912.06670","title":"Common Voice: A Massively-Multilingual Speech Corpus","created":"2019-12-13","cited_by_count":1384},{"id":"1904.08779","title":"SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition","created":"2019-04-18","cited_by_count":1380},{"id":"2112.04359","title":"Ethical and social risks of harm from Language Models","created":"2021-12-08","cited_by_count":966},{"id":"1806.07421","title":"RISE: Randomized Input Sampling for Explanation of Black-box Models","created":"2018-06-19","cited_by_count":838},{"id":"2304.14997","title":"Towards Automated Circuit Discovery for Mechanistic Interpretability","created":"2023-04-28","cited_by_count":724},{"id":"1704.03296","title":"Interpretable Explanations of Black Boxes by Meaningful Perturbation","created":"2017-04-11","cited_by_count":612},{"id":"2004.03685","title":"Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?","created":"2020-04-07","cited_by_count":599},{"id":"2101.00390","title":"VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation Learning, Semi-Supervised Learning and Interpretation","created":"2021-01-02","cited_by_count":463},{"id":"1509.06321","title":"Evaluating the visualization of what a Deep Neural Network has learned","created":"2015-09-21","cited_by_count":419},{"id":"2309.16042","title":"Towards Best Practices of Activation Patching in Language Models: Metrics and Methods","created":"2023-09-27","cited_by_count":359},{"id":"2309.01029","title":"Explainability for Large Language Models: A Survey","created":"2023-09-02","cited_by_count":333},{"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":"1705.07857","title":"Real Time Image Saliency for Black Box Classifiers","created":"2017-05-22","cited_by_count":246},{"id":"1805.04699","title":"TED-LIUM 3: twice as much data and corpus repartition for experiments on speaker adaptation","created":"2018-05-12","cited_by_count":226},{"id":"2011.14878","title":"Explaining by Removing: A Unified Framework for Model Explanation","created":"2020-11-21","cited_by_count":218},{"id":"2010.00711","title":"A Survey of the State of Explainable AI for Natural Language Processing","created":"2020-10-01","cited_by_count":206},{"id":"2010.05171","title":"fairseq S2T: Fast Speech-to-Text Modeling with fairseq","created":"2020-10-11","cited_by_count":176},{"id":"2108.04840","title":"Post-hoc Interpretability for Neural NLP: A Survey","created":"2021-08-10","cited_by_count":156},{"id":"1912.01451","title":"Sanity Checks for Saliency Metrics","created":"2019-11-29","cited_by_count":119},{"id":"1911.03167","title":"Europarl-ST: A Multilingual Corpus For Speech Translation Of Parliamentary Debates","created":"2019-11-08","cited_by_count":114},{"id":"1909.12072","title":"Towards Explainable Artificial Intelligence","created":"2019-09-26","cited_by_count":106},{"id":"2405.09589","title":"A Comprehensive Survey of Hallucination in Large Language, Image, Video and Audio Foundation Models","created":"2024-05-15","cited_by_count":100},{"id":"2403.00824","title":"Information Flow Routes: Automatically Interpreting Language Models at Scale","created":"2024-02-27","cited_by_count":95},{"id":"1706.07206","title":"Explaining Recurrent Neural Network Predictions in Sentiment Analysis","created":"2017-06-22","cited_by_count":88},{"id":"2302.13942","title":"Inseq: An Interpretability Toolkit for Sequence Generation Models","created":"2023-02-27","cited_by_count":78},{"id":"1807.03418","title":"AudioMNIST: Exploring Explainable Artificial Intelligence for Audio Analysis on a Simple Benchmark","created":"2018-07-09","cited_by_count":72},{"id":"2002.01320","title":"CoVoST: A Diverse Multilingual Speech-To-Text Translation Corpus","created":"2020-02-04","cited_by_count":57},{"id":"2006.05754","title":"Gender in Danger? Evaluating Speech Translation Technology on the MuST-SHE Corpus","created":"2020-06-10","cited_by_count":57},{"id":"1908.02686","title":"Interpretable and Fine-Grained Visual Explanations for Convolutional Neural Networks","created":"2019-08-07","cited_by_count":49},{"id":"2012.10425","title":"Towards Robust Explanations for Deep Neural Networks","created":"2020-12-18","cited_by_count":43},{"id":"2301.12971","title":"Quantifying Context Mixing in Transformers","created":"2023-01-30","cited_by_count":43},{"id":"2309.13876","title":"Reproducing Whisper-Style Training Using an Open-Source Toolkit and Publicly Available Data","created":"2023-09-25","cited_by_count":42},{"id":"2308.12792","title":"Sparks of Large Audio Models: A Survey and Outlook","created":"2023-08-24","cited_by_count":41},{"id":"2202.07728","title":"Don't Lie to Me! Robust and Efficient Explainability with Verified Perturbation Analysis","created":"2022-02-15","cited_by_count":38},{"id":"2312.05491","title":"Using Captum to Explain Generative Language Models","created":"2023-12-09","cited_by_count":33},{"id":"2112.09745","title":"Interpretable Data-Based Explanations for Fairness Debugging","created":"2021-12-17","cited_by_count":30},{"id":"2402.17954","title":"Twists, Humps, and Pebbles: Multilingual Speech Recognition Models Exhibit Gender Performance Gaps","created":"2024-02-28","cited_by_count":25},{"id":"2303.02794","title":"CoRTX: Contrastive Framework for Real-time Explanation","created":"2023-03-05","cited_by_count":20},{"id":"2202.12270","title":"Evaluating Feature Attribution Methods in the Image Domain","created":"2022-02-22","cited_by_count":19},{"id":"2009.04707","title":"On Target Segmentation for Direct Speech Translation","created":"2020-09-10","cited_by_count":12},{"id":"2006.02659","title":"MFPP: Morphological Fragmental Perturbation Pyramid for Black-Box Model Explanations","created":"2020-06-04","cited_by_count":10},{"id":"2305.18011","title":"Can We Trust Explainable AI Methods on ASR? An Evaluation on Phoneme Recognition","created":"2023-05-29","cited_by_count":10},{"id":"2103.15429","title":"Efficient Explanations from Empirical Explainers","created":"2021-03-29","cited_by_count":9},{"id":"2303.01538","title":"Feature Perturbation Augmentation for Reliable Evaluation of Importance Estimators in Neural Networks","created":"2023-03-02","cited_by_count":9},{"id":"2302.14062","title":"Explanations for Automatic Speech Recognition","created":"2023-02-27","cited_by_count":8},{"id":"1911.11081","title":"Improving Feature Attribution through Input-specific Network Pruning","created":"2019-11-25","cited_by_count":7},{"id":"2309.07733","title":"Explaining Speech Classification Models via Word-Level Audio Segments and Paralinguistic Features","created":"2023-09-14","cited_by_count":7},{"id":"2202.00673","title":"Visualizing Automatic Speech Recognition -- Means for a Better Understanding?","created":"2022-02-01","cited_by_count":6},{"id":"1807.11720","title":"Regional Multi-scale Approach for Visually Pleasing Explanations of Deep Neural Networks","created":"2018-07-31","cited_by_count":4},{"id":"2005.10929","title":"Large scale evaluation of importance maps in automatic speech recognition","created":"2020-05-21","cited_by_count":2}],"next_cursor":null}