{"list":"other","total":56,"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":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"1705.03551","title":"TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension","created":"2017-05-09","cited_by_count":2955},{"id":"2202.05262","title":"Locating and Editing Factual Associations in GPT","created":"2022-02-10","cited_by_count":2691},{"id":"1910.03771","title":"HuggingFace's Transformers: State-of-the-art Natural Language Processing","created":"2019-10-09","cited_by_count":2218},{"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":"2210.07229","title":"Mass-Editing Memory in a Transformer","created":"2022-10-13","cited_by_count":1001},{"id":"1911.12543","title":"How Can We Know What Language Models Know?","created":"2019-11-28","cited_by_count":959},{"id":"2302.00093","title":"Large Language Models Can Be Easily Distracted by Irrelevant Context","created":"2023-01-31","cited_by_count":841},{"id":"2002.12327","title":"A Primer in BERTology: What we know about how BERT works","created":"2020-02-27","cited_by_count":815},{"id":"2202.07646","title":"Quantifying Memorization Across Neural Language Models","created":"2022-02-15","cited_by_count":763},{"id":"2002.08910","title":"How Much Knowledge Can You Pack Into the Parameters of a Language Model?","created":"2020-02-10","cited_by_count":719},{"id":"2104.08696","title":"Knowledge Neurons in Pretrained Transformers","created":"2021-04-18","cited_by_count":601},{"id":"2110.11309","title":"Fast Model Editing at Scale","created":"2021-10-21","cited_by_count":498},{"id":"1906.05317","title":"COMET: Commonsense Transformers for Automatic Knowledge Graph Construction","created":"2019-06-12","cited_by_count":450},{"id":"2102.01017","title":"Measuring and Improving Consistency in Pretrained Language Models","created":"2021-02-01","cited_by_count":364},{"id":"2012.13048","title":"ProofWriter: Generating Implications, Proofs, and Abductive Statements over Natural Language","created":"2020-12-24","cited_by_count":324},{"id":"1810.09502","title":"How to train your MAML","created":"2018-10-22","cited_by_count":309},{"id":"1908.05739","title":"Abductive Commonsense Reasoning","created":"2019-08-15","cited_by_count":301},{"id":"2209.10063","title":"Generate rather than Retrieve: Large Language Models are Strong Context Generators","created":"2022-09-21","cited_by_count":298},{"id":"2002.05867","title":"Transformers as Soft Reasoners over Language","created":"2020-02-14","cited_by_count":270},{"id":"2010.05953","title":"COMET-ATOMIC 2020: On Symbolic and Neural Commonsense Knowledge Graphs","created":"2020-10-12","cited_by_count":254},{"id":"1704.05179","title":"SearchQA: A New Q&A Dataset Augmented with Context from a Search Engine","created":"2017-04-18","cited_by_count":225},{"id":"2005.04611","title":"How Context Affects Language Models' Factual Predictions","created":"2020-05-10","cited_by_count":181},{"id":"1908.06177","title":"CLUTRR: A Diagnostic Benchmark for Inductive Reasoning from Text","created":"2019-08-16","cited_by_count":162},{"id":"2205.11822","title":"Maieutic Prompting: Logically Consistent Reasoning with Recursive Explanations","created":"2022-05-24","cited_by_count":159},{"id":"2104.08661","title":"Explaining Answers with Entailment Trees","created":"2021-04-17","cited_by_count":152},{"id":"1603.06318","title":"Harnessing Deep Neural Networks with Logic Rules","created":"2016-03-21","cited_by_count":135},{"id":"2011.00209","title":"Meta-Learning with Adaptive Hyperparameters","created":"2020-10-31","cited_by_count":79},{"id":"2111.13654","title":"Do Language Models Have Beliefs? Methods for Detecting, Updating, and Visualizing Model Beliefs","created":"2021-11-26","cited_by_count":79},{"id":"2004.06748","title":"Balancing Training for Multilingual Neural Machine Translation","created":"2020-04-14","cited_by_count":72},{"id":"1909.00126","title":"A Logic-Driven Framework for Consistency of Neural Models","created":"2019-08-31","cited_by_count":64},{"id":"2205.12443","title":"Generating Natural Language Proofs with Verifier-Guided Search","created":"2022-05-25","cited_by_count":52},{"id":"2009.14786","title":"Measuring Systematic Generalization in Neural Proof Generation with Transformers","created":"2020-09-30","cited_by_count":43},{"id":"2210.12217","title":"Entailer: Answering Questions with Faithful and Truthful Chains of Reasoning","created":"2022-10-21","cited_by_count":38},{"id":"2201.05742","title":"Kformer: Knowledge Injection in Transformer Feed-Forward Layers","created":"2022-01-15","cited_by_count":37},{"id":"2101.00297","title":"Analyzing Commonsense Emergence in Few-shot Knowledge Models","created":"2021-01-01","cited_by_count":34},{"id":"2004.14839","title":"Do Neural Models Learn Systematicity of Monotonicity Inference in Natural Language?","created":"2020-04-30","cited_by_count":29},{"id":"2104.06511","title":"\"I'm Not Mad\": Commonsense Implications of Negation and Contradiction","created":"2021-04-13","cited_by_count":26},{"id":"2105.14167","title":"NeuralLog: Natural Language Inference with Joint Neural and Logical Reasoning","created":"2021-05-29","cited_by_count":25},{"id":"2109.13006","title":"RuleBert: Teaching Soft Rules to Pre-trained Language Models","created":"2021-09-24","cited_by_count":25},{"id":"1910.08772","title":"MonaLog: a Lightweight System for Natural Language Inference Based on Monotonicity","created":"2019-10-19","cited_by_count":21},{"id":"2112.09054","title":"Pushing the Limits of Rule Reasoning in Transformers through Natural Language Satisfiability","created":"2021-12-16","cited_by_count":18},{"id":"2205.02593","title":"METGEN: A Module-Based Entailment Tree Generation Framework for Answer Explanation","created":"2022-05-05","cited_by_count":17},{"id":"1708.09417","title":"LangPro: Natural Language Theorem Prover","created":"2017-08-30","cited_by_count":15},{"id":"2106.01354","title":"multiPRover: Generating Multiple Proofs for Improved Interpretability in Rule Reasoning","created":"2021-06-02","cited_by_count":15},{"id":"2010.15413","title":"Measuring and Harnessing Transference in Multi-Task Learning","created":"2020-10-29","cited_by_count":11},{"id":"1804.07656","title":"Acquisition of Phrase Correspondences using Natural Deduction Proofs","created":"2018-04-20","cited_by_count":9},{"id":"2110.01552","title":"Perhaps PTLMs Should Go to School -- A Task to Assess Open Book and Closed Book QA","created":"2021-10-04","cited_by_count":8},{"id":"2204.06283","title":"Curriculum: A Broad-Coverage Benchmark for Linguistic Phenomena in Natural Language Understanding","created":"2022-04-13","cited_by_count":3},{"id":"2205.00047","title":"Logically Consistent Adversarial Attacks for Soft Theorem Provers","created":"2022-04-29","cited_by_count":2}],"next_cursor":null}