{"list":"other","total":52,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"1910.13461","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","created":"2019-10-29","cited_by_count":5893},{"id":"1602.04938","title":"\"Why Should I Trust You?\": Explaining the Predictions of Any Classifier","created":"2016-02-16","cited_by_count":5070},{"id":"1703.01365","title":"Axiomatic Attribution for Deep Networks","created":"2017-03-04","cited_by_count":3384},{"id":"2009.01325","title":"Learning to summarize from human feedback","created":"2020-09-02","cited_by_count":2588},{"id":"1311.2901","title":"Visualizing and Understanding Convolutional Networks","created":"2013-11-12","cited_by_count":2290},{"id":"2012.07805","title":"Extracting Training Data from Large Language Models","created":"2020-12-14","cited_by_count":2189},{"id":"1909.01066","title":"Language Models as Knowledge Bases?","created":"2019-09-03","cited_by_count":1936},{"id":"1703.04730","title":"Understanding Black-box Predictions via Influence Functions","created":"2017-03-14","cited_by_count":1741},{"id":"1808.08745","title":"Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization","created":"2018-08-27","cited_by_count":1317},{"id":"1704.04368","title":"Get To The Point: Summarization with Pointer-Generator Networks","created":"2017-04-14","cited_by_count":1292},{"id":"2009.11462","title":"RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models","created":"2020-09-24","cited_by_count":1255},{"id":"1706.07269","title":"Explanation in Artificial Intelligence: Insights from the Social Sciences","created":"2017-06-22","cited_by_count":1206},{"id":"1912.08777","title":"PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization","created":"2019-12-18","cited_by_count":1102},{"id":"1506.03340","title":"Teaching Machines to Read and Comprehend","created":"2015-06-10","cited_by_count":1049},{"id":"1902.10186","title":"Attention is not Explanation","created":"2019-02-26","cited_by_count":929},{"id":"2005.00661","title":"On Faithfulness and Factuality in Abstractive Summarization","created":"2020-05-02","cited_by_count":900},{"id":"1908.04626","title":"Attention is not not Explanation","created":"2019-08-13","cited_by_count":636},{"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":"1910.12840","title":"Evaluating the Factual Consistency of Abstractive Text Summarization","created":"2019-10-28","cited_by_count":584},{"id":"1908.08345","title":"Text Summarization with Pretrained Encoders","created":"2019-08-22","cited_by_count":556},{"id":"1911.03429","title":"ERASER: A Benchmark to Evaluate Rationalized NLP Models","created":"2019-11-08","cited_by_count":530},{"id":"1806.07538","title":"Towards Robust Interpretability with Self-Explaining Neural Networks","created":"2018-06-20","cited_by_count":505},{"id":"2009.10795","title":"Dataset Cartography: Mapping and Diagnosing Datasets with Training Dynamics","created":"2020-09-22","cited_by_count":425},{"id":"1906.03731","title":"Is Attention Interpretable?","created":"2019-06-09","cited_by_count":389},{"id":"1908.08960","title":"Neural Text Summarization: A Critical Evaluation","created":"2019-08-23","cited_by_count":189},{"id":"1912.13283","title":"oLMpics -- On what Language Model Pre-training Captures","created":"2019-12-31","cited_by_count":161},{"id":"2005.06676","title":"Explaining Black Box Predictions and Unveiling Data Artifacts through Influence Functions","created":"2020-05-14","cited_by_count":144},{"id":"2104.04302","title":"Annotating and Modeling Fine-grained Factuality in Summarization","created":"2021-04-09","cited_by_count":131},{"id":"2010.05478","title":"Evaluating Factuality in Generation with Dependency-level Entailment","created":"2020-10-12","cited_by_count":122},{"id":"2010.05607","title":"The elephant in the interpretability room: Why use attention as explanation when we have saliency methods?","created":"2020-10-12","cited_by_count":122},{"id":"1909.07913","title":"Learning to Deceive with Attention-Based Explanations","created":"2019-09-17","cited_by_count":111},{"id":"1910.14142","title":"Discourse-Aware Neural Extractive Text Summarization","created":"2019-10-30","cited_by_count":105},{"id":"2010.05873","title":"Controlled Hallucinations: Learning to Generate Faithfully from Noisy Data","created":"2020-10-12","cited_by_count":84},{"id":"2010.10907","title":"Analyzing the Source and Target Contributions to Predictions in Neural Machine Translation","created":"2020-10-21","cited_by_count":71},{"id":"1810.12343","title":"Content Selection in Deep Learning Models of Summarization","created":"2018-10-29","cited_by_count":64},{"id":"1910.08684","title":"Sticking to the Facts: Confident Decoding for Faithful Data-to-Text Generation","created":"2019-10-19","cited_by_count":62},{"id":"2004.02015","title":"Generating Hierarchical Explanations on Text Classification via Feature Interaction Detection","created":"2020-04-04","cited_by_count":57},{"id":"1907.03491","title":"Searching for Effective Neural Extractive Summarization: What Works and What's Next","created":"2019-07-08","cited_by_count":38},{"id":"1902.00863","title":"Neural Extractive Text Summarization with Syntactic Compression","created":"2019-02-03","cited_by_count":37},{"id":"1809.08037","title":"Understanding Convolutional Neural Networks for Text Classification","created":"2018-09-21","cited_by_count":36},{"id":"2010.07882","title":"Understanding Neural Abstractive Summarization Models via Uncertainty","created":"2020-10-15","cited_by_count":34},{"id":"2105.11098","title":"Prevent the Language Model from being Overconfident in Neural Machine Translation","created":"2021-05-24","cited_by_count":34},{"id":"1611.07634","title":"Interpretation of Prediction Models Using the Input Gradient","created":"2016-11-23","cited_by_count":24},{"id":"1910.00203","title":"Analyzing Sentence Fusion in Abstractive Summarization","created":"2019-10-01","cited_by_count":19},{"id":"1911.10390","title":"Controlling the Amount of Verbatim Copying in Abstractive Summarization","created":"2019-11-23","cited_by_count":17},{"id":"2010.05139","title":"CDEvalSumm: An Empirical Study of Cross-Dataset Evaluation for Neural Summarization Systems","created":"2020-10-11","cited_by_count":17},{"id":"2005.01672","title":"Evaluating Explanation Methods for Neural Machine Translation","created":"2020-05-04","cited_by_count":14},{"id":"2010.03726","title":"Learning to Fuse Sentences with Transformers for Summarization","created":"2020-10-08","cited_by_count":14},{"id":"2010.07886","title":"Compressive Summarization with Plausibility and Salience Modeling","created":"2020-10-15","cited_by_count":9}],"next_cursor":null}