{"list":"other","total":73,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"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":"1312.6114","title":"Auto-Encoding Variational Bayes","created":"2013-12-20","cited_by_count":4053},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"2004.05150","title":"Longformer: The Long-Document Transformer","created":"2020-04-10","cited_by_count":3413},{"id":"1904.09751","title":"The Curious Case of Neural Text Degeneration","created":"2019-04-22","cited_by_count":2916},{"id":"1906.08237","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","created":"2019-06-19","cited_by_count":2811},{"id":"2212.10560","title":"Self-Instruct: Aligning Language Models with Self-Generated Instructions","created":"2022-12-20","cited_by_count":2724},{"id":"2009.01325","title":"Learning to summarize from human feedback","created":"2020-09-02","cited_by_count":2588},{"id":"1909.08593","title":"Fine-Tuning Language Models from Human Preferences","created":"2019-09-18","cited_by_count":2150},{"id":"1901.08746","title":"BioBERT: a pre-trained biomedical language representation model for biomedical text mining","created":"2019-01-25","cited_by_count":1947},{"id":"1609.08144","title":"Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation","created":"2016-09-26","cited_by_count":1475},{"id":"2205.10625","title":"Least-to-Most Prompting Enables Complex Reasoning in Large Language Models","created":"2022-05-21","cited_by_count":1407},{"id":"1704.04368","title":"Get To The Point: Summarization with Pointer-Generator Networks","created":"2017-04-14","cited_by_count":1292},{"id":"1805.04833","title":"Hierarchical Neural Story Generation","created":"2018-05-13","cited_by_count":1193},{"id":"1801.07243","title":"Personalizing Dialogue Agents: I have a dog, do you have pets too?","created":"2018-01-22","cited_by_count":828},{"id":"1912.02164","title":"Plug and Play Language Models: A Simple Approach to Controlled Text Generation","created":"2019-12-04","cited_by_count":799},{"id":"1909.05858","title":"CTRL: A Conditional Transformer Language Model for Controllable Generation","created":"2019-09-11","cited_by_count":762},{"id":"2211.09085","title":"Galactica: A Large Language Model for Science","created":"2022-11-16","cited_by_count":744},{"id":"1908.07125","title":"Universal Adversarial Triggers for Attacking and Analyzing NLP","created":"2019-08-20","cited_by_count":722},{"id":"2103.10385","title":"GPT Understands, Too","created":"2021-03-18","cited_by_count":716},{"id":"2210.03493","title":"Automatic Chain of Thought Prompting in Large Language Models","created":"2022-10-07","cited_by_count":688},{"id":"1511.06349","title":"Generating Sentences from a Continuous Space","created":"2015-11-19","cited_by_count":612},{"id":"1511.06732","title":"Sequence Level Training with Recurrent Neural Networks","created":"2015-11-20","cited_by_count":576},{"id":"1811.01241","title":"Wizard of Wikipedia: Knowledge-Powered Conversational agents","created":"2018-11-03","cited_by_count":530},{"id":"1908.04319","title":"Neural Text Generation with Unlikelihood Training","created":"2019-08-12","cited_by_count":503},{"id":"1506.07503","title":"Attention-Based Models for Speech Recognition","created":"2015-06-24","cited_by_count":401},{"id":"1705.04304","title":"A Deep Reinforced Model for Abstractive Summarization","created":"2017-05-11","cited_by_count":365},{"id":"2302.12813","title":"Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedback","created":"2023-02-24","cited_by_count":353},{"id":"1603.06155","title":"A Persona-Based Neural Conversation Model","created":"2016-03-19","cited_by_count":223},{"id":"2305.08291","title":"Large Language Model Guided Tree-of-Thought","created":"2023-05-15","cited_by_count":221},{"id":"1803.06535","title":"Dear Sir or Madam, May I introduce the GYAFC Dataset: Corpus, Benchmarks and Metrics for Formality Style Transfer","created":"2018-03-17","cited_by_count":211},{"id":"2004.08795","title":"Extractive Summarization as Text Matching","created":"2020-04-19","cited_by_count":189},{"id":"1711.06861","title":"Style Transfer in Text: Exploration and Evaluation","created":"2017-11-18","cited_by_count":146},{"id":"1702.01932","title":"A Knowledge-Grounded Neural Conversation Model","created":"2017-02-07","cited_by_count":136},{"id":"1508.01745","title":"Semantically Conditioned LSTM-based Natural Language Generation for Spoken Dialogue Systems","created":"2015-08-07","cited_by_count":134},{"id":"2203.05115","title":"Internet-augmented language models through few-shot prompting for open-domain question answering","created":"2022-03-10","cited_by_count":131},{"id":"1904.01608","title":"Structural Scaffolds for Citation Intent Classification in Scientific Publications","created":"2019-04-02","cited_by_count":130},{"id":"1903.03094","title":"Learning to Speak and Act in a Fantasy Text Adventure Game","created":"2019-03-07","cited_by_count":122},{"id":"1805.06087","title":"Learning to Write with Cooperative Discriminators","created":"2018-05-16","cited_by_count":119},{"id":"2302.12822","title":"Automatic Prompt Augmentation and Selection with Chain-of-Thought from Labeled Data","created":"2023-02-24","cited_by_count":119},{"id":"1809.07358","title":"A Dataset for Document Grounded Conversations","created":"2018-09-19","cited_by_count":104},{"id":"2302.11520","title":"Guiding Large Language Models via Directional Stimulus Prompting","created":"2023-02-22","cited_by_count":95},{"id":"1908.09368","title":"Transforming Delete, Retrieve, Generate Approach for Controlled Text Style Transfer","created":"2019-08-25","cited_by_count":81},{"id":"1909.01214","title":"Better Rewards Yield Better Summaries: Learning to Summarise Without References","created":"2019-09-03","cited_by_count":77},{"id":"1707.07402","title":"Reinforcement Learning for Bandit Neural Machine Translation with Simulated Human Feedback","created":"2017-07-24","cited_by_count":72},{"id":"1906.09531","title":"Bias Correction of Learned Generative Models using Likelihood-Free Importance Weighting","created":"2019-06-23","cited_by_count":70},{"id":"1905.11553","title":"Target-Guided Open-Domain Conversation","created":"2019-05-28","cited_by_count":66},{"id":"1804.07036","title":"Learning to Extract Coherent Summary via Deep Reinforcement Learning","created":"2018-04-19","cited_by_count":64},{"id":"1805.03162","title":"Polite Dialogue Generation Without Parallel Data","created":"2018-05-08","cited_by_count":59},{"id":"1902.02192","title":"Non-Monotonic Sequential Text Generation","created":"2019-02-05","cited_by_count":55},{"id":"2005.01822","title":"Exploring Controllable Text Generation Techniques","created":"2020-05-04","cited_by_count":55},{"id":"1811.01135","title":"Content preserving text generation with attribute controls","created":"2018-11-03","cited_by_count":47},{"id":"1904.13015","title":"Towards Coherent and Engaging Spoken Dialog Response Generation Using Automatic Conversation Evaluators","created":"2019-04-30","cited_by_count":35},{"id":"2002.00317","title":"Explaining Relationships Between Scientific Documents","created":"2020-02-02","cited_by_count":35},{"id":"1905.12926","title":"Controllable Unsupervised Text Attribute Transfer via Editing Entangled Latent Representation","created":"2019-05-30","cited_by_count":34},{"id":"1705.09207","title":"Learning Structured Text Representations","created":"2017-05-25","cited_by_count":24},{"id":"1702.02429","title":"Trainable Greedy Decoding for Neural Machine Translation","created":"2017-02-08","cited_by_count":23},{"id":"2303.01580","title":"Mixture of Soft Prompts for Controllable Data Generation","created":"2023-03-02","cited_by_count":23},{"id":"1909.13425","title":"Augmenting Non-Collaborative Dialog Systems with Explicit Semantic and Strategic Dialog History","created":"2019-09-30","cited_by_count":20},{"id":"1808.09042","title":"Adversarial Decomposition of Text Representation","created":"2018-08-27","cited_by_count":18},{"id":"1701.06549","title":"Learning to Decode for Future Success","created":"2017-01-23","cited_by_count":16},{"id":"2305.17116","title":"Improving accuracy of GPT-3/4 results on biomedical data using a retrieval-augmented language model","created":"2023-05-26","cited_by_count":15},{"id":"2112.01332","title":"Towards Generating Citation Sentences for Multiple References with Intent Control","created":"2021-12-02","cited_by_count":9},{"id":"2002.02878","title":"I love your chain mail! Making knights smile in a fantasy game world: Open-domain goal-oriented dialogue agents","created":"2020-02-07","cited_by_count":7},{"id":"2211.07066","title":"Controllable Citation Sentence Generation with Language Models","created":"2022-11-14","cited_by_count":4}],"next_cursor":null}