{"list":"other","total":60,"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":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"1602.04938","title":"\"Why Should I Trust You?\": Explaining the Predictions of Any Classifier","created":"2016-02-16","cited_by_count":5070},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"2004.04906","title":"Dense Passage Retrieval for Open-Domain Question Answering","created":"2020-04-10","cited_by_count":3824},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"2305.14314","title":"QLoRA: Efficient Finetuning of Quantized LLMs","created":"2023-05-23","cited_by_count":3418},{"id":"1904.09751","title":"The Curious Case of Neural Text Degeneration","created":"2019-04-22","cited_by_count":2916},{"id":"1806.07572","title":"Neural Tangent Kernel: Convergence and Generalization in Neural Networks","created":"2018-06-20","cited_by_count":2621},{"id":"2202.03629","title":"Survey of Hallucination in Natural Language Generation","created":"2022-02-08","cited_by_count":2075},{"id":"2202.12837","title":"Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?","created":"2022-02-25","cited_by_count":1434},{"id":"2212.03533","title":"Text Embeddings by Weakly-Supervised Contrastive Pre-training","created":"2022-12-07","cited_by_count":1253},{"id":"2304.12244","title":"WizardLM: Empowering large pre-trained language models to follow complex instructions","created":"2023-04-24","cited_by_count":1125},{"id":"2007.00808","title":"Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval","created":"2020-07-01","cited_by_count":849},{"id":"1704.00051","title":"Reading Wikipedia to Answer Open-Domain Questions","created":"2017-03-31","cited_by_count":777},{"id":"2306.15595","title":"Extending Context Window of Large Language Models via Positional Interpolation","created":"2023-06-27","cited_by_count":740},{"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":"1906.00300","title":"Latent Retrieval for Weakly Supervised Open Domain Question Answering","created":"2019-06-01","cited_by_count":695},{"id":"2210.07316","title":"MTEB: Massive Text Embedding Benchmark","created":"2022-10-13","cited_by_count":640},{"id":"2306.04751","title":"How Far Can Camels Go? Exploring the State of Instruction Tuning on Open Resources","created":"2023-06-07","cited_by_count":408},{"id":"1911.03894","title":"CamemBERT: a Tasty French Language Model","created":"2019-11-10","cited_by_count":368},{"id":"1906.02361","title":"Explain Yourself! Leveraging Language Models for Commonsense Reasoning","created":"2019-06-06","cited_by_count":367},{"id":"1606.04155","title":"Rationalizing Neural Predictions","created":"2016-06-13","cited_by_count":281},{"id":"1705.00652","title":"Efficient Natural Language Response Suggestion for Smart Reply","created":"2017-05-01","cited_by_count":229},{"id":"1906.02059","title":"Neural Legal Judgment Prediction in English","created":"2019-06-05","cited_by_count":209},{"id":"1907.04307","title":"Multilingual Universal Sentence Encoder for Semantic Retrieval","created":"2019-07-09","cited_by_count":193},{"id":"2103.06332","title":"Hurdles to Progress in Long-form Question Answering","created":"2021-03-10","cited_by_count":167},{"id":"2010.12762","title":"Measuring Association Between Labels and Free-Text Rationales","created":"2020-10-24","cited_by_count":160},{"id":"2004.14546","title":"WT5?! Training Text-to-Text Models to Explain their Predictions","created":"2020-04-30","cited_by_count":148},{"id":"1905.08160","title":"Interpretable Neural Predictions with Differentiable Binary Variables","created":"2019-05-20","cited_by_count":126},{"id":"1911.12011","title":"JEC-QA: A Legal-Domain Question Answering Dataset","created":"2019-11-27","cited_by_count":116},{"id":"2305.18201","title":"A Critical Evaluation of Evaluations for Long-form Question Answering","created":"2023-05-29","cited_by_count":111},{"id":"1805.03677","title":"The Dataset Nutrition Label: A Framework To Drive Higher Data Quality Standards","created":"2018-05-09","cited_by_count":97},{"id":"2005.12116","title":"NILE : Natural Language Inference with Faithful Natural Language Explanations","created":"2020-05-25","cited_by_count":96},{"id":"2103.13084","title":"Paragraph-level Rationale Extraction through Regularization: A case study on European Court of Human Rights Cases","created":"2021-03-24","cited_by_count":77},{"id":"1706.07881","title":"On Sampling Strategies for Neural Network-based Collaborative Filtering","created":"2017-06-23","cited_by_count":71},{"id":"1910.03065","title":"Make Up Your Mind! Adversarial Generation of Inconsistent Natural Language Explanations","created":"2019-10-07","cited_by_count":71},{"id":"2005.00652","title":"An Information Bottleneck Approach for Controlling Conciseness in Rationale Extraction","created":"2020-05-01","cited_by_count":69},{"id":"1801.05453","title":"Beyond Word Importance: Contextual Decomposition to Extract Interactions from LSTMs","created":"2018-01-16","cited_by_count":67},{"id":"1911.00841","title":"Question Answering for Privacy Policies: Combining Computational and Legal Perspectives","created":"2019-11-03","cited_by_count":67},{"id":"2005.05257","title":"A Dataset for Statutory Reasoning in Tax Law Entailment and Question Answering","created":"2020-05-11","cited_by_count":62},{"id":"1706.09799","title":"Relevance of Unsupervised Metrics in Task-Oriented Dialogue for Evaluating Natural Language Generation","created":"2017-06-29","cited_by_count":61},{"id":"2212.02199","title":"Legal Prompt Engineering for Multilingual Legal Judgement Prediction","created":"2022-12-05","cited_by_count":55},{"id":"1704.06194","title":"Improved Neural Relation Detection for Knowledge Base Question Answering","created":"2017-04-20","cited_by_count":44},{"id":"1704.08300","title":"Diversity driven Attention Model for Query-based Abstractive Summarization","created":"2017-04-26","cited_by_count":42},{"id":"2108.11792","title":"A Statutory Article Retrieval Dataset in French","created":"2021-08-26","cited_by_count":40},{"id":"1801.07704","title":"Query Focused Abstractive Summarization: Incorporating Query Relevance, Multi-Document Coverage, and Summary Length Constraints into seq2seq Models","created":"2018-01-23","cited_by_count":39},{"id":"2004.05569","title":"Explaining Question Answering Models through Text Generation","created":"2020-04-12","cited_by_count":33},{"id":"1912.09156","title":"CJRC: A Reliable Human-Annotated Benchmark DataSet for Chinese Judicial Reading Comprehension","created":"2019-12-19","cited_by_count":26},{"id":"2210.07544","title":"Legal Case Document Summarization: Extractive and Abstractive Methods and their Evaluation","created":"2022-10-14","cited_by_count":24},{"id":"2108.07140","title":"MTG: A Benchmark Suite for Multilingual Text Generation","created":"2021-08-13","cited_by_count":22},{"id":"2012.15482","title":"FiD-Ex: Improving Sequence-to-Sequence Models for Extractive Rationale Generation","created":"2020-12-31","cited_by_count":21},{"id":"1606.07548","title":"A Sentence Compression Based Framework to Query-Focused Multi-Document Summarization","created":"2016-06-24","cited_by_count":8},{"id":"2205.09278","title":"Modeling Exemplification in Long-form Question Answering via Retrieval","created":"2022-05-19","cited_by_count":7},{"id":"2304.05611","title":"FALQU: Finding Answers to Legal Questions","created":"2023-04-12","cited_by_count":3}],"next_cursor":null}