{"list":"other","total":63,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"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":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"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":"1802.03426","title":"UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction","created":"2018-02-09","cited_by_count":2898},{"id":"2204.01691","title":"Do As I Can, Not As I Say: Grounding Language in Robotic Affordances","created":"2022-04-04","cited_by_count":2348},{"id":"2206.04615","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","created":"2022-06-09","cited_by_count":1998},{"id":"2112.09332","title":"WebGPT: Browser-assisted question-answering with human feedback","created":"2021-12-17","cited_by_count":1745},{"id":"1606.06565","title":"Concrete Problems in AI Safety","created":"2016-06-21","cited_by_count":1642},{"id":"2010.03768","title":"ALFWorld: Aligning Text and Embodied Environments for Interactive Learning","created":"2020-10-08","cited_by_count":1205},{"id":"2207.05608","title":"Inner Monologue: Embodied Reasoning through Planning with Language Models","created":"2022-07-12","cited_by_count":1081},{"id":"1706.05098","title":"An Overview of Multi-Task Learning in Deep Neural Networks","created":"2017-06-15","cited_by_count":803},{"id":"2103.03097","title":"Generalizing to Unseen Domains: A Survey on Domain Generalization","created":"2021-03-02","cited_by_count":766},{"id":"2307.15217","title":"Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback","created":"2023-07-27","cited_by_count":759},{"id":"1707.00600","title":"Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Ugly","created":"2017-07-03","cited_by_count":538},{"id":"2209.14375","title":"Improving alignment of dialogue agents via targeted human judgements","created":"2022-09-28","cited_by_count":531},{"id":"2202.02005","title":"BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learning","created":"2022-02-04","cited_by_count":523},{"id":"2001.09768","title":"Artificial Intelligence, Values and Alignment","created":"2020-01-13","cited_by_count":448},{"id":"2304.11406","title":"LaMP: When Large Language Models Meet Personalization","created":"2023-04-22","cited_by_count":437},{"id":"2305.17493","title":"The Curse of Recursion: Training on Generated Data Makes Models Forget","created":"2023-05-27","cited_by_count":356},{"id":"2012.07463","title":"Parameter-Efficient Transfer Learning with Diff Pruning","created":"2020-12-14","cited_by_count":352},{"id":"1801.04354","title":"Black-box Generation of Adversarial Text Sequences to Evade Deep Learning Classifiers","created":"2018-01-13","cited_by_count":345},{"id":"2310.10158","title":"Character-LLM: A Trainable Agent for Role-Playing","created":"2023-10-16","cited_by_count":339},{"id":"2002.01808","title":"K-Adapter: Infusing Knowledge into Pre-Trained Models with Adapters","created":"2020-02-05","cited_by_count":319},{"id":"2306.14898","title":"InterCode: Standardizing and Benchmarking Interactive Coding with Execution Feedback","created":"2023-06-26","cited_by_count":238},{"id":"1301.3666","title":"Zero-Shot Learning Through Cross-Modal Transfer","created":"2013-01-16","cited_by_count":237},{"id":"2310.02124","title":"Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology View","created":"2023-10-03","cited_by_count":222},{"id":"2404.18231","title":"From Persona to Personalization: A Survey on Role-Playing Language Agents","created":"2024-04-28","cited_by_count":212},{"id":"2311.04892","title":"Bias Runs Deep: Implicit Reasoning Biases in Persona-Assigned LLMs","created":"2023-11-08","cited_by_count":199},{"id":"2208.03188","title":"BlenderBot 3: a deployed conversational agent that continually learns to responsibly engage","created":"2022-08-05","cited_by_count":198},{"id":"2310.00746","title":"RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language Models","created":"2023-10-01","cited_by_count":175},{"id":"1712.03586","title":"Fairness in Machine Learning: Lessons from Political Philosophy","created":"2017-12-10","cited_by_count":149},{"id":"2106.03164","title":"On the Effectiveness of Adapter-based Tuning for Pretrained Language Model Adaptation","created":"2021-06-06","cited_by_count":147},{"id":"2305.14688","title":"ExpertPrompting: Instructing Large Language Models to be Distinguished Experts","created":"2023-05-24","cited_by_count":142},{"id":"2012.15738","title":"Moral Stories: Situated Reasoning about Norms, Intents, Actions, and their Consequences","created":"2020-12-31","cited_by_count":135},{"id":"2311.04155","title":"Black-Box Prompt Optimization: Aligning Large Language Models without Model Training","created":"2023-11-07","cited_by_count":122},{"id":"2410.12954","title":"A Note on Shumailov et al. (2024): `AI Models Collapse When Trained on Recursively Generated Data'","created":"2024-10-16","cited_by_count":115},{"id":"1503.06733","title":"Yara Parser: A Fast and Accurate Dependency Parser","created":"2015-03-23","cited_by_count":111},{"id":"1706.05064","title":"Zero-Shot Task Generalization with Multi-Task Deep Reinforcement Learning","created":"2017-06-15","cited_by_count":98},{"id":"1602.03506","title":"Research Priorities for Robust and Beneficial Artificial Intelligence","created":"2016-02-10","cited_by_count":74},{"id":"2206.04564","title":"TwiBot-22: Towards Graph-Based Twitter Bot Detection","created":"2022-06-09","cited_by_count":44},{"id":"2402.09269","title":"Personalized Large Language Models","created":"2024-02-14","cited_by_count":44},{"id":"2106.13092","title":"BotRGCN: Twitter Bot Detection with Relational Graph Convolutional Networks","created":"2021-06-24","cited_by_count":39},{"id":"2204.13074","title":"Towards Teachable Reasoning Systems: Using a Dynamic Memory of User Feedback for Continual System Improvement","created":"2022-04-27","cited_by_count":37},{"id":"2408.11779","title":"Personality Alignment of Large Language Models","created":"2024-08-21","cited_by_count":36},{"id":"2112.06346","title":"ValueNet: A New Dataset for Human Value Driven Dialogue System","created":"2021-12-12","cited_by_count":34},{"id":"1812.03980","title":"Building Ethically Bounded AI","created":"2018-12-10","cited_by_count":22},{"id":"2305.15064","title":"AutoPlan: Automatic Planning of Interactive Decision-Making Tasks With Large Language Models","created":"2023-05-24","cited_by_count":13},{"id":"2403.00145","title":"Guidelines for Integrating Value Sensitive Design in Responsible AI Toolkits","created":"2024-02-29","cited_by_count":10},{"id":"2303.05092","title":"Task Aware Dreamer for Task Generalization in Reinforcement Learning","created":"2023-03-09","cited_by_count":5}],"next_cursor":null}