{"list":"other","total":60,"rows":[{"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":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"2205.11916","title":"Large Language Models are Zero-Shot Reasoners","created":"2022-05-24","cited_by_count":4374},{"id":"2307.03172","title":"Lost in the Middle: How Language Models Use Long Contexts","created":"2023-07-06","cited_by_count":3455},{"id":"2202.05262","title":"Locating and Editing Factual Associations in GPT","created":"2022-02-10","cited_by_count":2691},{"id":"2002.08909","title":"REALM: Retrieval-Augmented Language Model Pre-Training","created":"2020-02-10","cited_by_count":2141},{"id":"1909.08053","title":"Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism","created":"2019-09-17","cited_by_count":1868},{"id":"2211.17192","title":"Fast Inference from Transformers via Speculative Decoding","created":"2022-11-30","cited_by_count":1653},{"id":"2012.14913","title":"Transformer Feed-Forward Layers Are Key-Value Memories","created":"2020-12-29","cited_by_count":1336},{"id":"2211.00593","title":"Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small","created":"2022-11-01","cited_by_count":1165},{"id":"2312.07104","title":"SGLang: Efficient Execution of Structured Language Model Programs","created":"2023-12-12","cited_by_count":1141},{"id":"2104.08786","title":"Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity","created":"2021-04-18","cited_by_count":1135},{"id":"2211.01910","title":"Large Language Models Are Human-Level Prompt Engineers","created":"2022-11-03","cited_by_count":1045},{"id":"2210.07229","title":"Mass-Editing Memory in a Transformer","created":"2022-10-13","cited_by_count":1001},{"id":"2304.05128","title":"Teaching Large Language Models to Self-Debug","created":"2023-04-11","cited_by_count":988},{"id":"2302.00093","title":"Large Language Models Can Be Easily Distracted by Irrelevant Context","created":"2023-01-31","cited_by_count":841},{"id":"2305.02301","title":"Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes","created":"2023-05-03","cited_by_count":737},{"id":"2403.04652","title":"Yi: Open Foundation Models by 01.AI","created":"2024-03-07","cited_by_count":719},{"id":"1803.08475","title":"Attention, Learn to Solve Routing Problems!","created":"2018-03-22","cited_by_count":656},{"id":"2308.08747","title":"An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning","created":"2023-08-17","cited_by_count":639},{"id":"2104.08164","title":"Editing Factual Knowledge in Language Models","created":"2021-04-16","cited_by_count":553},{"id":"2203.14680","title":"Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space","created":"2022-03-28","cited_by_count":532},{"id":"2110.11309","title":"Fast Model Editing at Scale","created":"2021-10-21","cited_by_count":498},{"id":"2206.06520","title":"Memory-Based Model Editing at Scale","created":"2022-06-13","cited_by_count":447},{"id":"2309.02427","title":"Cognitive Architectures for Language Agents","created":"2023-09-05","cited_by_count":429},{"id":"2303.03846","title":"Larger language models do in-context learning differently","created":"2023-03-07","cited_by_count":394},{"id":"2303.17491","title":"Language Models can Solve Computer Tasks","created":"2023-03-30","cited_by_count":372},{"id":"2010.09885","title":"ChemBERTa: Large-Scale Self-Supervised Pretraining for Molecular Property Prediction","created":"2020-10-19","cited_by_count":337},{"id":"2305.01610","title":"Finding Neurons in a Haystack: Case Studies with Sparse Probing","created":"2023-05-02","cited_by_count":334},{"id":"1802.04240","title":"Reinforcement Learning for Solving the Vehicle Routing Problem","created":"2018-02-12","cited_by_count":333},{"id":"2305.14795","title":"MQuAKE: Assessing Knowledge Editing in Language Models via Multi-Hop Questions","created":"2023-05-24","cited_by_count":300},{"id":"2310.19102","title":"Atom: Low-bit Quantization for Efficient and Accurate LLM Serving","created":"2023-10-29","cited_by_count":272},{"id":"2211.11031","title":"Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptors","created":"2022-11-20","cited_by_count":271},{"id":"2012.00363","title":"Modifying Memories in Transformer Models","created":"2020-12-01","cited_by_count":224},{"id":"2106.06130","title":"ChemRL-GEM: Geometry Enhanced Molecular Representation Learning for Property Prediction","created":"2021-06-11","cited_by_count":204},{"id":"1810.00337","title":"Learning to Perform Local Rewriting for Combinatorial Optimization","created":"2018-09-30","cited_by_count":185},{"id":"2006.10782","title":"AI Feynman 2.0: Pareto-optimal symbolic regression exploiting graph modularity","created":"2020-06-18","cited_by_count":144},{"id":"2209.07686","title":"Text and Patterns: For Effective Chain of Thought, It Takes Two to Tango","created":"2022-09-16","cited_by_count":128},{"id":"2302.12170","title":"Language Model Crossover: Variation through Few-Shot Prompting","created":"2023-02-23","cited_by_count":122},{"id":"2311.07361","title":"The Impact of Large Language Models on Scientific Discovery: a Preliminary Study using GPT-4","created":"2023-11-13","cited_by_count":112},{"id":"1503.06733","title":"Yara Parser: A Fast and Accurate Dependency Parser","created":"2015-03-23","cited_by_count":111},{"id":"2007.15646","title":"Rewriting a Deep Generative Model","created":"2020-07-30","cited_by_count":107},{"id":"2306.06615","title":"Empowering Molecule Discovery for Molecule-Caption Translation with Large Language Models: A ChatGPT Perspective","created":"2023-06-11","cited_by_count":92},{"id":"2405.09783","title":"LLM and Simulation as Bilevel Optimizers: A New Paradigm to Advance Physical Scientific Discovery","created":"2024-05-16","cited_by_count":86},{"id":"2408.11850","title":"PEARL: Parallel Speculative Decoding with Adaptive Draft Length","created":"2024-08-13","cited_by_count":85},{"id":"2312.11795","title":"MELO: Enhancing Model Editing with Neuron-Indexed Dynamic LoRA","created":"2023-12-19","cited_by_count":80},{"id":"2303.16749","title":"Improving Code Generation by Training with Natural Language Feedback","created":"2023-03-28","cited_by_count":76},{"id":"2408.07246","title":"ChemVLM: Exploring the Power of Multimodal Large Language Models in Chemistry Area","created":"2024-08-14","cited_by_count":71},{"id":"2304.14369","title":"Learning Neural Constitutive Laws From Motion Observations for Generalizable PDE Dynamics","created":"2023-04-27","cited_by_count":57},{"id":"2303.17071","title":"DERA: Enhancing Large Language Model Completions with Dialog-Enabled Resolving Agents","created":"2023-03-30","cited_by_count":52},{"id":"2310.16795","title":"QMoE: Practical Sub-1-Bit Compression of Trillion-Parameter Models","created":"2023-10-25","cited_by_count":42},{"id":"2002.10640","title":"Differentiable Reasoning over a Virtual Knowledge Base","created":"2020-02-25","cited_by_count":39},{"id":"2304.03262","title":"When do you need Chain-of-Thought Prompting for ChatGPT?","created":"2023-04-06","cited_by_count":35},{"id":"2101.00297","title":"Analyzing Commonsense Emergence in Few-shot Knowledge Models","created":"2021-01-01","cited_by_count":34},{"id":"2410.02811","title":"SAC-KG: Exploiting Large Language Models as Skilled Automatic Constructors for Domain Knowledge Graphs","created":"2024-09-22","cited_by_count":31},{"id":"2407.08642","title":"Towards Building Specialized Generalist AI with System 1 and System 2 Fusion","created":"2024-07-11","cited_by_count":8}],"next_cursor":null}