{"list":"other","total":96,"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":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"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":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"2302.04761","title":"Toolformer: Language Models Can Teach Themselves to Use Tools","created":"2023-02-09","cited_by_count":4182},{"id":"2304.03442","title":"Generative Agents: Interactive Simulacra of Human Behavior","created":"2023-04-07","cited_by_count":3568},{"id":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344},{"id":"2212.10560","title":"Self-Instruct: Aligning Language Models with Self-Generated Instructions","created":"2022-12-20","cited_by_count":2724},{"id":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576},{"id":"2308.11432","title":"A Survey on Large Language Model based Autonomous Agents","created":"2023-08-22","cited_by_count":2242},{"id":"2307.16789","title":"ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs","created":"2023-07-31","cited_by_count":1947},{"id":"2110.08207","title":"Multitask Prompted Training Enables Zero-Shot Task Generalization","created":"2021-10-15","cited_by_count":1470},{"id":"2303.17760","title":"CAMEL: Communicative Agents for \"Mind\" Exploration of Large Language Model Society","created":"2023-03-31","cited_by_count":1395},{"id":"2206.14858","title":"Solving Quantitative Reasoning Problems with Language Models","created":"2022-06-29","cited_by_count":1392},{"id":"2305.15334","title":"Gorilla: Large Language Model Connected with Massive APIs","created":"2023-05-24","cited_by_count":1332},{"id":"2405.04434","title":"DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model","created":"2024-05-07","cited_by_count":1135},{"id":"2304.12244","title":"WizardLM: Empowering large pre-trained language models to follow complex instructions","created":"2023-04-24","cited_by_count":1125},{"id":"2406.12793","title":"ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools","created":"2024-06-18","cited_by_count":1121},{"id":"2409.12122","title":"Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement","created":"2024-09-18","cited_by_count":1090},{"id":"2405.14734","title":"SimPO: Simple Preference Optimization with a Reference-Free Reward","created":"2024-05-23","cited_by_count":963},{"id":"2308.09687","title":"Graph of Thoughts: Solving Elaborate Problems with Large Language Models","created":"2023-08-18","cited_by_count":886},{"id":"2209.06899","title":"Out of One, Many: Using Language Models to Simulate Human Samples","created":"2022-09-14","cited_by_count":752},{"id":"2302.00083","title":"In-Context Retrieval-Augmented Language Models","created":"2023-01-31","cited_by_count":702},{"id":"2211.15661","title":"What learning algorithm is in-context learning? Investigations with linear models","created":"2022-11-28","cited_by_count":684},{"id":"2304.05376","title":"ChemCrow: Augmenting large-language models with chemistry tools","created":"2023-04-11","cited_by_count":631},{"id":"2306.15626","title":"LeanDojo: Theorem Proving with Retrieval-Augmented Language Models","created":"2023-06-27","cited_by_count":427},{"id":"2206.14576","title":"Using cognitive psychology to understand GPT-3","created":"2022-06-21","cited_by_count":398},{"id":"2310.10631","title":"Llemma: An Open Language Model For Mathematics","created":"2023-10-16","cited_by_count":388},{"id":"2305.17126","title":"Large Language Models as Tool Makers","created":"2023-05-26","cited_by_count":303},{"id":"2305.15005","title":"Sentiment Analysis in the Era of Large Language Models: A Reality Check","created":"2023-05-24","cited_by_count":268},{"id":"2312.11970","title":"Large Language Models Empowered Agent-based Modeling and Simulation: A Survey and Perspectives","created":"2023-12-19","cited_by_count":257},{"id":"2405.14333","title":"DeepSeek-Prover: Advancing Theorem Proving in LLMs through Large-Scale Synthetic Data","created":"2024-05-23","cited_by_count":234},{"id":"2405.02957","title":"Agent Hospital: A Simulacrum of Hospital with Evolvable Medical Agents","created":"2024-05-05","cited_by_count":218},{"id":"2205.11491","title":"HyperTree Proof Search for Neural Theorem Proving","created":"2022-05-23","cited_by_count":197},{"id":"2110.03215","title":"Towards Continual Knowledge Learning of Language Models","created":"2021-10-07","cited_by_count":174},{"id":"2203.06125","title":"Protein Representation Learning by Geometric Structure Pretraining","created":"2022-03-11","cited_by_count":162},{"id":"2310.10436","title":"EconAgent: Large Language Model-Empowered Agents for Simulating Macroeconomic Activities","created":"2023-10-16","cited_by_count":154},{"id":"1908.05656","title":"PHYRE: A New Benchmark for Physical Reasoning","created":"2019-08-15","cited_by_count":137},{"id":"2406.19226","title":"Simulating Classroom Education with LLM-Empowered Agents","created":"2024-06-27","cited_by_count":127},{"id":"2304.09102","title":"Solving Math Word Problems by Combining Language Models With Symbolic Solvers","created":"2023-04-16","cited_by_count":124},{"id":"2404.02831","title":"Empowering Biomedical Discovery with AI Agents","created":"2024-04-03","cited_by_count":118},{"id":"2304.09667","title":"GeneGPT: Augmenting Large Language Models with Domain Tools for Improved Access to Biomedical Information","created":"2023-04-19","cited_by_count":117},{"id":"2309.12342","title":"Cultural Alignment in Large Language Models: An Explanatory Analysis Based on Hofstede's Cultural Dimensions","created":"2023-08-25","cited_by_count":112},{"id":"2310.00656","title":"LEGO-Prover: Neural Theorem Proving with Growing Libraries","created":"2023-10-01","cited_by_count":109},{"id":"2308.09442","title":"BioMedGPT: Open Multimodal Generative Pre-trained Transformer for BioMedicine","created":"2023-08-18","cited_by_count":100},{"id":"2405.18357","title":"Faithful Logical Reasoning via Symbolic Chain-of-Thought","created":"2024-05-28","cited_by_count":100},{"id":"2407.01603","title":"A Review of Large Language Models and Autonomous Agents in Chemistry","created":"2024-06-26","cited_by_count":99},{"id":"2205.10893","title":"Thor: Wielding Hammers to Integrate Language Models and Automated Theorem Provers","created":"2022-05-22","cited_by_count":98},{"id":"2310.00305","title":"Towards LLM-based Fact Verification on News Claims with a Hierarchical Step-by-Step Prompting Method","created":"2023-09-30","cited_by_count":97},{"id":"2112.15594","title":"A Neural Network Solves, Explains, and Generates University Math Problems by Program Synthesis and Few-Shot Learning at Human Level","created":"2021-12-31","cited_by_count":96},{"id":"2311.16208","title":"InstructMol: Multi-Modal Integration for Building a Versatile and Reliable Molecular Assistant in Drug Discovery","created":"2023-11-27","cited_by_count":86},{"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":"2402.01789","title":"The Political Preferences of LLMs","created":"2024-02-02","cited_by_count":84},{"id":"2401.13923","title":"Towards 3D Molecule-Text Interpretation in Language Models","created":"2024-01-25","cited_by_count":66},{"id":"2401.06949","title":"ORGANA: A Robotic Assistant for Automated Chemistry Experimentation and Characterization","created":"2024-01-13","cited_by_count":61},{"id":"2402.16445","title":"ProLLaMA: A Protein Large Language Model for Multi-Task Protein Language Processing","created":"2024-02-26","cited_by_count":53},{"id":"2310.10047","title":"Improving Large Language Model Fine-tuning for Solving Math Problems","created":"2023-10-16","cited_by_count":49},{"id":"2310.10632","title":"BioPlanner: Automatic Evaluation of LLMs on Protocol Planning in Biology","created":"2023-10-16","cited_by_count":43},{"id":"2408.01107","title":"BioRAG: A RAG-LLM Framework for Biological Question Reasoning","created":"2024-08-02","cited_by_count":43},{"id":"2309.06126","title":"AstroLLaMA: Towards Specialized Foundation Models in Astronomy","created":"2023-09-12","cited_by_count":41},{"id":"2407.09811","title":"CellAgent: An LLM-driven Multi-Agent Framework for Automated Single-cell Data Analysis","created":"2024-07-13","cited_by_count":39},{"id":"2311.08089","title":"Improving In-context Learning of Multilingual Generative Language Models with Cross-lingual Alignment","created":"2023-11-14","cited_by_count":33},{"id":"2405.00972","title":"CACTUS: Chemistry Agent Connecting Tool-Usage to Science","created":"2024-05-02","cited_by_count":33},{"id":"2403.13312","title":"LeanReasoner: Boosting Complex Logical Reasoning with Lean","created":"2024-03-20","cited_by_count":28},{"id":"2412.06864","title":"Political-LLM: Large Language Models in Political Science","created":"2024-12-09","cited_by_count":27},{"id":"2311.10776","title":"Chemist-X: Large Language Model-empowered Agent for Reaction Condition Recommendation in Chemical Synthesis","created":"2023-11-16","cited_by_count":25},{"id":"2412.00821","title":"Improving Physics Reasoning in Large Language Models Using Mixture of Refinement Agents","created":"2024-12-01","cited_by_count":24},{"id":"2412.08389","title":"SweetieChat: A Strategy-Enhanced Role-playing Framework for Diverse Scenarios Handling Emotional Support Agent","created":"2024-12-11","cited_by_count":24},{"id":"2305.17653","title":"Prompt-Guided Retrieval Augmentation for Non-Knowledge-Intensive Tasks","created":"2023-05-28","cited_by_count":21},{"id":"2403.07920","title":"ProtLLM: An Interleaved Protein-Language LLM with Protein-as-Word Pre-Training","created":"2024-02-28","cited_by_count":21},{"id":"2405.19744","title":"X-Instruction: Aligning Language Model in Low-resource Languages with Self-curated Cross-lingual Instructions","created":"2024-05-30","cited_by_count":18},{"id":"2303.06074","title":"Susceptibility to Influence of Large Language Models","created":"2023-03-10","cited_by_count":17},{"id":"2404.08704","title":"MM-PhyQA: Multimodal Physics Question-Answering With Multi-Image CoT Prompting","created":"2024-04-11","cited_by_count":15},{"id":"2406.13193","title":"PRESTO: Progressive Pretraining Enhances Synthetic Chemistry Outcomes","created":"2024-06-19","cited_by_count":14},{"id":"2401.01916","title":"AstroLLaMA-Chat: Scaling AstroLLaMA with Conversational and Diverse Datasets","created":"2024-01-03","cited_by_count":13},{"id":"2306.11648","title":"Harnessing the Power of Adversarial Prompting and Large Language Models for Robust Hypothesis Generation in Astronomy","created":"2023-06-20","cited_by_count":11},{"id":"2412.19994","title":"From Generalist to Specialist: A Survey of Large Language Models for Chemistry","created":"2024-12-28","cited_by_count":11},{"id":"2404.14467","title":"Integrating Chemistry Knowledge in Large Language Models via Prompt Engineering","created":"2024-04-22","cited_by_count":10},{"id":"2309.02045","title":"Enhance Multi-domain Sentiment Analysis of Review Texts through Prompting Strategies","created":"2023-09-05","cited_by_count":7},{"id":"2409.19750","title":"AstroMLab 2: AstroLLaMA-2-70B Model and Benchmarking Specialised LLMs for Astronomy","created":"2024-09-29","cited_by_count":6},{"id":"2412.06827","title":"Enhancing LLMs for Physics Problem-Solving using Reinforcement Learning with Human-AI Feedback","created":"2024-12-06","cited_by_count":6},{"id":"2309.00135","title":"Construction Grammar and Artificial Intelligence","created":"2023-08-31","cited_by_count":5},{"id":"2310.10808","title":"If the Sources Could Talk: Evaluating Large Language Models for Research Assistance in History","created":"2023-10-16","cited_by_count":5},{"id":"2405.07828","title":"Can LLMs Help Predict Elections? (Counter)Evidence from the World's Largest Democracy","created":"2024-05-13","cited_by_count":5},{"id":"2411.09978","title":"HistoLens: An LLM-Powered Framework for Multi-Layered Analysis of Historical Texts -- A Case Application of Yantie Lun","created":"2024-11-15","cited_by_count":5},{"id":"2412.08846","title":"Exploring Large Language Models on Cross-Cultural Values in Connection with Training Methodology","created":"2024-12-12","cited_by_count":4},{"id":"2406.18535","title":"DRAK: Unlocking Molecular Insights with Domain-Specific Retrieval-Augmented Knowledge in LLMs","created":"2024-03-04","cited_by_count":3},{"id":"2412.18156","title":"scReader: Prompting Large Language Models to Interpret scRNA-seq Data","created":"2024-12-24","cited_by_count":3}],"next_cursor":null}