{"list":"other","total":122,"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":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"1705.07874","title":"A Unified Approach to Interpreting Model Predictions","created":"2017-05-22","cited_by_count":6555},{"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":"1904.09675","title":"BERTScore: Evaluating Text Generation with BERT","created":"2019-04-21","cited_by_count":5512},{"id":"1602.04938","title":"\"Why Should I Trust You?\": Explaining the Predictions of Any Classifier","created":"2016-02-16","cited_by_count":5070},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"2004.04906","title":"Dense Passage Retrieval for Open-Domain Question Answering","created":"2020-04-10","cited_by_count":3824},{"id":"1809.09600","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","created":"2018-09-25","cited_by_count":3754},{"id":"1310.4546","title":"Distributed Representations of Words and Phrases and their Compositionality","created":"2013-10-16","cited_by_count":3474},{"id":"1703.01365","title":"Axiomatic Attribution for Deep Networks","created":"2017-03-04","cited_by_count":3384},{"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":"1802.05365","title":"Deep contextualized word representations","created":"2018-02-15","cited_by_count":2290},{"id":"1508.05326","title":"A large annotated corpus for learning natural language inference","created":"2015-08-21","cited_by_count":1847},{"id":"1611.09268","title":"MS MARCO: A Human Generated MAchine Reading COmprehension Dataset","created":"2016-11-28","cited_by_count":1605},{"id":"1702.08608","title":"Towards A Rigorous Science of Interpretable Machine Learning","created":"2017-02-28","cited_by_count":1416},{"id":"1803.05355","title":"FEVER: a large-scale dataset for Fact Extraction and VERification","created":"2018-03-14","cited_by_count":1375},{"id":"1610.01644","title":"Understanding intermediate layers using linear classifier probes","created":"2016-10-05","cited_by_count":1353},{"id":"2104.08663","title":"BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models","created":"2021-04-17","cited_by_count":1252},{"id":"2112.09118","title":"Unsupervised Dense Information Retrieval with Contrastive Learning","created":"2021-12-16","cited_by_count":1216},{"id":"2004.12832","title":"ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT","created":"2020-04-27","cited_by_count":1178},{"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":"2102.12452","title":"Probing Classifiers: Promises, Shortcomings, and Advances","created":"2021-02-24","cited_by_count":876},{"id":"1905.09418","title":"Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned","created":"2019-05-23","cited_by_count":856},{"id":"2007.00808","title":"Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval","created":"2020-07-01","cited_by_count":849},{"id":"2002.12327","title":"A Primer in BERTology: What we know about how BERT works","created":"2020-02-27","cited_by_count":815},{"id":"2005.00928","title":"Quantifying Attention Flow in Transformers","created":"2020-05-02","cited_by_count":775},{"id":"2101.02235","title":"Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies","created":"2021-01-06","cited_by_count":743},{"id":"1606.03490","title":"The Mythos of Model Interpretability","created":"2016-06-10","cited_by_count":721},{"id":"1901.04085","title":"Passage Re-ranking with BERT","created":"2019-01-13","cited_by_count":645},{"id":"1908.04626","title":"Attention is not not Explanation","created":"2019-08-13","cited_by_count":636},{"id":"1811.01241","title":"Wizard of Wikipedia: Knowledge-Powered Conversational agents","created":"2018-11-03","cited_by_count":530},{"id":"1911.03429","title":"ERASER: A Benchmark to Evaluate Rationalized NLP Models","created":"2019-11-08","cited_by_count":530},{"id":"1805.01070","title":"What you can cram into a single vector: Probing sentence embeddings for linguistic properties","created":"2018-05-03","cited_by_count":457},{"id":"1905.06316","title":"What do you learn from context? Probing for sentence structure in contextualized word representations","created":"2019-05-15","cited_by_count":438},{"id":"1906.03731","title":"Is Attention Interpretable?","created":"2019-06-09","cited_by_count":389},{"id":"1908.08474","title":"The many Shapley values for model explanation","created":"2019-08-22","cited_by_count":344},{"id":"1602.02068","title":"From Softmax to Sparsemax: A Sparse Model of Attention and Multi-Label Classification","created":"2016-02-05","cited_by_count":341},{"id":"1907.13528","title":"What BERT is not: Lessons from a new suite of psycholinguistic diagnostics for language models","created":"2019-07-31","cited_by_count":320},{"id":"1908.08593","title":"Revealing the Dark Secrets of BERT","created":"2019-08-21","cited_by_count":301},{"id":"1803.05449","title":"SentEval: An Evaluation Toolkit for Universal Sentence Representations","created":"2018-03-14","cited_by_count":294},{"id":"2003.07820","title":"Overview of the TREC 2019 deep learning track","created":"2020-03-17","cited_by_count":286},{"id":"1802.03888","title":"Consistent Individualized Feature Attribution for Tree Ensembles","created":"2018-02-12","cited_by_count":285},{"id":"1812.08951","title":"Analysis Methods in Neural Language Processing: A Survey","created":"2018-12-21","cited_by_count":277},{"id":"2010.06467","title":"Pretrained Transformers for Text Ranking: BERT and Beyond","created":"2020-10-13","cited_by_count":267},{"id":"1612.08220","title":"Understanding Neural Networks through Representation Erasure","created":"2016-12-24","cited_by_count":224},{"id":"1907.07355","title":"Probing Neural Network Comprehension of Natural Language Arguments","created":"2019-07-17","cited_by_count":214},{"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":"1810.12885","title":"ReCoRD: Bridging the Gap between Human and Machine Commonsense Reading Comprehension","created":"2018-10-30","cited_by_count":200},{"id":"2102.07662","title":"Overview of the TREC 2020 deep learning track","created":"2021-02-15","cited_by_count":196},{"id":"1901.05287","title":"Assessing BERT's Syntactic Abilities","created":"2019-01-16","cited_by_count":192},{"id":"2108.04840","title":"Post-hoc Interpretability for Neural NLP: A Survey","created":"2021-08-10","cited_by_count":156},{"id":"1711.08611","title":"A Deep Relevance Matching Model for Ad-hoc Retrieval","created":"2017-11-23","cited_by_count":126},{"id":"2004.11207","title":"Self-Attention Attribution: Interpreting Information Interactions Inside Transformer","created":"2020-04-23","cited_by_count":125},{"id":"1306.2597","title":"Introducing LETOR 4.0 Datasets","created":"2013-06-09","cited_by_count":121},{"id":"1906.01698","title":"Open Sesame: Getting Inside BERT's Linguistic Knowledge","created":"2019-06-04","cited_by_count":120},{"id":"1905.09217","title":"Deeper Text Understanding for IR with Contextual Neural Language Modeling","created":"2019-05-22","cited_by_count":113},{"id":"1708.00107","title":"Learned in Translation: Contextualized Word Vectors","created":"2017-08-01","cited_by_count":104},{"id":"2102.11090","title":"Position Information in Transformers: An Overview","created":"2021-02-22","cited_by_count":103},{"id":"1503.03244","title":"Convolutional Neural Network Architectures for Matching Natural Language Sentences","created":"2015-03-11","cited_by_count":82},{"id":"2006.01067","title":"Aligning Faithful Interpretations with their Social Attribution","created":"2020-06-01","cited_by_count":79},{"id":"2103.01378","title":"Contrastive Explanations for Model Interpretability","created":"2021-03-02","cited_by_count":75},{"id":"1610.08136","title":"Learning to Match Using Local and Distributed Representations of Text for Web Search","created":"2016-10-26","cited_by_count":68},{"id":"1801.05453","title":"Beyond Word Importance: Contextual Decomposition to Extract Interactions from LSTMs","created":"2018-01-16","cited_by_count":67},{"id":"2002.12538","title":"Explainable $k$-Means and $k$-Medians Clustering","created":"2020-02-28","cited_by_count":67},{"id":"1806.05337","title":"Hierarchical interpretations for neural network predictions","created":"2018-06-14","cited_by_count":66},{"id":"1602.06359","title":"Text Matching as Image Recognition","created":"2016-02-20","cited_by_count":59},{"id":"2004.02015","title":"Generating Hierarchical Explanations on Text Classification via Feature Interaction Detection","created":"2020-04-04","cited_by_count":57},{"id":"1502.06922","title":"Deep Sentence Embedding Using Long Short-Term Memory Networks: Analysis and Application to Information Retrieval","created":"2015-02-24","cited_by_count":54},{"id":"2104.15135","title":"Explanation-Based Human Debugging of NLP Models: A Survey","created":"2021-04-30","cited_by_count":53},{"id":"2106.09992","title":"Exploring Counterfactual Explanations Through the Lens of Adversarial Examples: A Theoretical and Empirical Analysis","created":"2021-06-18","cited_by_count":52},{"id":"1904.07531","title":"Understanding the Behaviors of BERT in Ranking","created":"2019-04-16","cited_by_count":49},{"id":"2004.14243","title":"Towards Transparent and Explainable Attention Models","created":"2020-04-29","cited_by_count":47},{"id":"2204.01321","title":"PRADA: Practical Black-Box Adversarial Attacks against Neural Ranking Models","created":"2022-04-04","cited_by_count":44},{"id":"2210.06929","title":"On the Explainability of Natural Language Processing Deep Models","created":"2022-10-13","cited_by_count":38},{"id":"2201.08808","title":"Conversational Information Seeking","created":"2022-01-21","cited_by_count":37},{"id":"1805.04218","title":"Deep RNNs Encode Soft Hierarchical Syntax","created":"2018-05-11","cited_by_count":34},{"id":"2106.01087","title":"Is Sparse Attention more Interpretable?","created":"2021-06-02","cited_by_count":31},{"id":"1810.11975","title":"On Controllable Sparse Alternatives to Softmax","created":"2018-10-29","cited_by_count":27},{"id":"2006.10174","title":"MIMICS: A Large-Scale Data Collection for Search Clarification","created":"2020-06-17","cited_by_count":27},{"id":"1812.08718","title":"RNNs Implicitly Implement Tensor Product Representations","created":"2018-12-20","cited_by_count":26},{"id":"2004.14245","title":"Expansion via Prediction of Importance with Contextualization","created":"2020-04-29","cited_by_count":26},{"id":"1905.08957","title":"ANTIQUE: A Non-Factoid Question Answering Benchmark","created":"2019-05-22","cited_by_count":24},{"id":"2011.00696","title":"ABNIRML: Analyzing the Behavior of Neural IR Models","created":"2020-11-02","cited_by_count":23},{"id":"1805.03797","title":"WikiPassageQA: A Benchmark Collection for Research on Non-factoid Answer Passage Retrieval","created":"2018-05-10","cited_by_count":19},{"id":"1907.06484","title":"A study on the Interpretability of Neural Retrieval Models using DeepSHAP","created":"2019-07-15","cited_by_count":19},{"id":"1809.03857","title":"EXS: Explainable Search Using Local Model Agnostic Interpretability","created":"2018-09-11","cited_by_count":18},{"id":"1605.07891","title":"Query Expansion with Locally-Trained Word Embeddings","created":"2016-05-25","cited_by_count":17},{"id":"2108.05018","title":"Are Neural Ranking Models Robust?","created":"2021-08-11","cited_by_count":16},{"id":"2108.13759","title":"Enjoy the Salience: Towards Better Transformer-based Faithful Explanations with Word Salience","created":"2021-08-31","cited_by_count":16}],"next_cursor":"100"}