{"list":"other","total":64,"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":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2205.11916","title":"Large Language Models are Zero-Shot Reasoners","created":"2022-05-24","cited_by_count":4374},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2304.03442","title":"Generative Agents: Interactive Simulacra of Human Behavior","created":"2023-04-07","cited_by_count":3568},{"id":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024},{"id":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576},{"id":"2312.10997","title":"Retrieval-Augmented Generation for Large Language Models: A Survey","created":"2023-12-18","cited_by_count":2212},{"id":"2303.03378","title":"PaLM-E: An Embodied Multimodal Language Model","created":"2023-03-06","cited_by_count":2071},{"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":"1909.01066","title":"Language Models as Knowledge Bases?","created":"2019-09-03","cited_by_count":1936},{"id":"1903.10676","title":"SciBERT: A Pretrained Language Model for Scientific Text","created":"2019-03-26","cited_by_count":1414},{"id":"2012.15723","title":"Making Pre-trained Language Models Better Few-shot Learners","created":"2020-12-31","cited_by_count":1256},{"id":"2106.10199","title":"BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models","created":"2021-06-18","cited_by_count":1245},{"id":"1911.02685","title":"A Comprehensive Survey on Transfer Learning","created":"2019-11-07","cited_by_count":1160},{"id":"1803.02999","title":"On First-Order Meta-Learning Algorithms","created":"2018-03-08","cited_by_count":1018},{"id":"2004.05439","title":"Meta-Learning in Neural Networks: A Survey","created":"2020-04-11","cited_by_count":950},{"id":"2306.13549","title":"A Survey on Multimodal Large Language Models","created":"2023-06-23","cited_by_count":909},{"id":"2302.00923","title":"Multimodal Chain-of-Thought Reasoning in Language Models","created":"2023-02-02","cited_by_count":752},{"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":"2304.06364","title":"AGIEval: A Human-Centric Benchmark for Evaluating Foundation Models","created":"2023-04-13","cited_by_count":716},{"id":"2302.00083","title":"In-Context Retrieval-Augmented Language Models","created":"2023-01-31","cited_by_count":702},{"id":"2002.00388","title":"A Survey on Knowledge Graphs: Representation, Acquisition and Applications","created":"2020-02-02","cited_by_count":643},{"id":"2304.05376","title":"ChemCrow: Augmenting large-language models with chemistry tools","created":"2023-04-11","cited_by_count":631},{"id":"2402.01030","title":"Executable Code Actions Elicit Better LLM Agents","created":"2024-02-01","cited_by_count":564},{"id":"2302.14045","title":"Language Is Not All You Need: Aligning Perception with Language Models","created":"2023-02-27","cited_by_count":543},{"id":"2208.10264","title":"Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studies","created":"2022-08-18","cited_by_count":515},{"id":"2003.05002","title":"TyDi QA: A Benchmark for Information-Seeking Question Answering in Typologically Diverse Languages","created":"2020-03-10","cited_by_count":488},{"id":"1708.05866","title":"A Brief Survey of Deep Reinforcement Learning","created":"2017-08-19","cited_by_count":483},{"id":"2304.13712","title":"Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyond","created":"2023-04-26","cited_by_count":411},{"id":"2305.17216","title":"Generating Images with Multimodal Language Models","created":"2023-05-26","cited_by_count":260},{"id":"2310.03128","title":"MetaTool Benchmark for Large Language Models: Deciding Whether to Use Tools and Which to Use","created":"2023-10-04","cited_by_count":217},{"id":"1811.12560","title":"An Introduction to Deep Reinforcement Learning","created":"2018-11-30","cited_by_count":206},{"id":"2111.00643","title":"Learning Distilled Collaboration Graph for Multi-Agent Perception","created":"2021-11-01","cited_by_count":194},{"id":"2009.08553","title":"Generation-Augmented Retrieval for Open-domain Question Answering","created":"2020-09-17","cited_by_count":186},{"id":"2312.04511","title":"An LLM Compiler for Parallel Function Calling","created":"2023-12-07","cited_by_count":179},{"id":"2402.18013","title":"A Survey on Recent Advances in LLM-Based Multi-turn Dialogue Systems","created":"2024-02-28","cited_by_count":170},{"id":"2304.01852","title":"Summary of ChatGPT-Related Research and Perspective Towards the Future of Large Language Models","created":"2023-04-04","cited_by_count":154},{"id":"2108.11601","title":"Retrieval Augmented Code Generation and Summarization","created":"2021-08-26","cited_by_count":149},{"id":"2403.07714","title":"StableToolBench: Towards Stable Large-Scale Benchmarking on Tool Learning of Large Language Models","created":"2024-03-12","cited_by_count":132},{"id":"2103.11943","title":"BERT: A Review of Applications in Natural Language Processing and Understanding","created":"2021-03-22","cited_by_count":109},{"id":"2001.02314","title":"Bridging Knowledge Graphs to Generate Scene Graphs","created":"2020-01-07","cited_by_count":86},{"id":"2208.05051","title":"Limitations of Language Models in Arithmetic and Symbolic Induction","created":"2022-08-09","cited_by_count":71},{"id":"2312.02913","title":"Let the LLMs Talk: Simulating Human-to-Human Conversational QA via Zero-Shot LLM-to-LLM Interactions","created":"2023-12-05","cited_by_count":70},{"id":"2401.02038","title":"Understanding LLMs: A Comprehensive Overview from Training to Inference","created":"2024-01-04","cited_by_count":59},{"id":"2104.14085","title":"Bridge to Answer: Structure-aware Graph Interaction Network for Video Question Answering","created":"2021-04-29","cited_by_count":56},{"id":"1411.2738","title":"word2vec Parameter Learning Explained","created":"2014-11-11","cited_by_count":53},{"id":"2303.08268","title":"Chat with the Environment: Interactive Multimodal Perception Using Large Language Models","created":"2023-03-14","cited_by_count":43},{"id":"2305.14497","title":"Self-Polish: Enhance Reasoning in Large Language Models via Problem Refinement","created":"2023-05-23","cited_by_count":43},{"id":"2004.14129","title":"How fine can fine-tuning be? Learning efficient language models","created":"2020-04-24","cited_by_count":41},{"id":"2405.04645","title":"Enhancing LLM-Based Feedback: Insights from Intelligent Tutoring Systems and the Learning Sciences","created":"2024-05-07","cited_by_count":37},{"id":"2305.10263","title":"M3KE: A Massive Multi-Level Multi-Subject Knowledge Evaluation Benchmark for Chinese Large Language Models","created":"2023-05-17","cited_by_count":30},{"id":"2304.12986","title":"Measuring Massive Multitask Chinese Understanding","created":"2023-04-25","cited_by_count":25},{"id":"2403.01304","title":"Improving the Validity of Automatically Generated Feedback via Reinforcement Learning","created":"2024-03-02","cited_by_count":20},{"id":"2405.15646","title":"LLM-based Robot Task Planning with Exceptional Handling for General Purpose Service Robots","created":"2024-05-24","cited_by_count":16},{"id":"2405.19255","title":"Towards Next-Generation Urban Decision Support Systems through AI-Powered Construction of Scientific Ontology using Large Language Models -- A Case in Optimizing Intermodal Freight Transportation","created":"2024-05-29","cited_by_count":10},{"id":"2405.19578","title":"The Accuracy of Domain Specific and Descriptive Analysis Generated by Large Language Models","created":"2024-05-30","cited_by_count":1}],"next_cursor":null}