{"list":"other","total":102,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"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":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2302.04761","title":"Toolformer: Language Models Can Teach Themselves to Use Tools","created":"2023-02-09","cited_by_count":4182},{"id":"2307.03172","title":"Lost in the Middle: How Language Models Use Long Contexts","created":"2023-07-06","cited_by_count":3455},{"id":"2303.16634","title":"G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment","created":"2023-03-29","cited_by_count":2276},{"id":"2404.14219","title":"Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone","created":"2024-04-22","cited_by_count":1917},{"id":"2308.00352","title":"MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework","created":"2023-08-01","cited_by_count":1808},{"id":"2305.14325","title":"Improving Factuality and Reasoning in Language Models through Multiagent Debate","created":"2023-05-23","cited_by_count":1784},{"id":"2203.10244","title":"ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning","created":"2022-03-19","cited_by_count":1479},{"id":"2203.07814","title":"Competition-Level Code Generation with AlphaCode","created":"2022-02-08","cited_by_count":1462},{"id":"2309.07864","title":"The Rise and Potential of Large Language Model Based Agents: A Survey","created":"2023-09-14","cited_by_count":1439},{"id":"2305.15334","title":"Gorilla: Large Language Model Connected with Massive APIs","created":"2023-05-24","cited_by_count":1332},{"id":"2101.06804","title":"What Makes Good In-Context Examples for GPT-$3$?","created":"2021-01-17","cited_by_count":1195},{"id":"2208.03299","title":"Atlas: Few-shot Learning with Retrieval Augmented Language Models","created":"2022-08-05","cited_by_count":952},{"id":"2310.11324","title":"Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting","created":"2023-10-17","cited_by_count":817},{"id":"2305.03111","title":"Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs","created":"2023-05-04","cited_by_count":688},{"id":"2309.00770","title":"Bias and Fairness in Large Language Models: A Survey","created":"2023-09-02","cited_by_count":639},{"id":"2211.11501","title":"DS-1000: A Natural and Reliable Benchmark for Data Science Code Generation","created":"2022-11-18","cited_by_count":452},{"id":"2310.03302","title":"MLAgentBench: Evaluating Language Agents on Machine Learning Experimentation","created":"2023-10-05","cited_by_count":366},{"id":"2304.09842","title":"Chameleon: Plug-and-Play Compositional Reasoning with Large Language Models","created":"2023-04-19","cited_by_count":356},{"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":"1909.00997","title":"PlotQA: Reasoning over Scientific Plots","created":"2019-09-03","cited_by_count":321},{"id":"2305.15771","title":"On the Planning Abilities of Large Language Models : A Critical Investigation","created":"2023-05-25","cited_by_count":312},{"id":"2401.01313","title":"A Comprehensive Survey of Hallucination Mitigation Techniques in Large Language Models","created":"2024-01-02","cited_by_count":269},{"id":"2309.02705","title":"Certifying LLM Safety against Adversarial Prompting","created":"2023-09-06","cited_by_count":266},{"id":"2307.10169","title":"Challenges and Applications of Large Language Models","created":"2023-07-19","cited_by_count":254},{"id":"2306.09896","title":"Is Self-Repair a Silver Bullet for Code Generation?","created":"2023-06-16","cited_by_count":197},{"id":"2306.07174","title":"Augmenting Language Models with Long-Term Memory","created":"2023-06-12","cited_by_count":189},{"id":"2303.16434","title":"TaskMatrix.AI: Completing Tasks by Connecting Foundation Models with Millions of APIs","created":"2023-03-29","cited_by_count":184},{"id":"2310.11248","title":"CrossCodeEval: A Diverse and Multilingual Benchmark for Cross-File Code Completion","created":"2023-10-17","cited_by_count":183},{"id":"2404.05719","title":"Ferret-UI: Grounded Mobile UI Understanding with Multimodal LLMs","created":"2024-04-08","cited_by_count":176},{"id":"2205.09911","title":"Can Foundation Models Wrangle Your Data?","created":"2022-05-20","cited_by_count":175},{"id":"2311.16483","title":"ChartLlama: A Multimodal LLM for Chart Understanding and Generation","created":"2023-11-27","cited_by_count":163},{"id":"2305.14761","title":"UniChart: A Universal Vision-language Pretrained Model for Chart Comprehension and Reasoning","created":"2023-05-24","cited_by_count":160},{"id":"2201.11227","title":"Synchromesh: Reliable code generation from pre-trained language models","created":"2022-01-26","cited_by_count":156},{"id":"2402.07939","title":"UFO: A UI-Focused Agent for Windows OS Interaction","created":"2024-02-08","cited_by_count":148},{"id":"2305.04320","title":"Unified Demonstration Retriever for In-Context Learning","created":"2023-05-07","cited_by_count":142},{"id":"2311.09206","title":"TableLlama: Towards Open Large Generalist Models for Tables","created":"2023-11-15","cited_by_count":137},{"id":"2305.03403","title":"Large Language Models for Automated Data Science: Introducing CAAFE for Context-Aware Automated Feature Engineering","created":"2023-05-05","cited_by_count":127},{"id":"2402.14016","title":"Is LLM-as-a-Judge Robust? Investigating Universal Adversarial Attacks on Zero-shot LLM Assessment","created":"2024-02-21","cited_by_count":126},{"id":"2305.15852","title":"Self-contradictory Hallucinations of Large Language Models: Evaluation, Detection and Mitigation","created":"2023-05-25","cited_by_count":124},{"id":"2305.05662","title":"InternGPT: Solving Vision-Centric Tasks by Interacting with ChatGPT Beyond Language","created":"2023-05-09","cited_by_count":96},{"id":"2312.10893","title":"The Metacognitive Demands and Opportunities of Generative AI","created":"2023-12-18","cited_by_count":87},{"id":"2303.02927","title":"LIDA: A Tool for Automatic Generation of Grammar-Agnostic Visualizations and Infographics using Large Language Models","created":"2023-03-06","cited_by_count":82},{"id":"2010.09142","title":"Chart-to-Text: Generating Natural Language Descriptions for Charts by Adapting the Transformer Model","created":"2020-10-18","cited_by_count":78},{"id":"2312.02296","title":"LLMs Accelerate Annotation for Medical Information Extraction","created":"2023-12-04","cited_by_count":77},{"id":"2408.09667","title":"BLADE: Benchmarking Language Model Agents for Data-Driven Science","created":"2024-08-19","cited_by_count":77},{"id":"2008.10723","title":"NL4DV: A Toolkit for Generating Analytic Specifications for Data Visualization from Natural Language Queries","created":"2020-08-24","cited_by_count":74},{"id":"2311.01920","title":"ChartGPT: Leveraging LLMs to Generate Charts from Abstract Natural Language","created":"2023-11-03","cited_by_count":73},{"id":"2305.15038","title":"Is GPT-4 a Good Data Analyst?","created":"2023-05-24","cited_by_count":70},{"id":"2310.09263","title":"Table-GPT: Table-tuned GPT for Diverse Table Tasks","created":"2023-10-13","cited_by_count":69},{"id":"1901.08152","title":"Veridical Data Science","created":"2019-01-23","cited_by_count":66},{"id":"2305.11473","title":"Graphologue: Exploring Large Language Model Responses with Interactive Diagrams","created":"2023-05-19","cited_by_count":66},{"id":"2402.17644","title":"Are LLMs Capable of Data-based Statistical and Causal Reasoning? Benchmarking Advanced Quantitative Reasoning with Data","created":"2024-02-27","cited_by_count":63},{"id":"2308.15022","title":"Recursively Summarizing Enables Long-Term Dialogue Memory in Large Language Models","created":"2023-08-29","cited_by_count":62},{"id":"2109.03506","title":"Towards Natural Language Interfaces for Data Visualization: A Survey","created":"2021-09-08","cited_by_count":59},{"id":"2310.08992","title":"CodeChain: Towards Modular Code Generation Through Chain of Self-revisions with Representative Sub-modules","created":"2023-10-13","cited_by_count":58},{"id":"2403.12027","title":"From Pixels to Insights: A Survey on Automatic Chart Understanding in the Era of Large Foundation Models","created":"2024-03-18","cited_by_count":53},{"id":"2306.00024","title":"Self-Verification Improves Few-Shot Clinical Information Extraction","created":"2023-05-30","cited_by_count":52},{"id":"2208.05950","title":"Interactive Code Generation via Test-Driven User-Intent Formalization","created":"2022-08-11","cited_by_count":50},{"id":"1910.02216","title":"JuICe: A Large Scale Distantly Supervised Dataset for Open Domain Context-based Code Generation","created":"2019-10-05","cited_by_count":49},{"id":"2310.10358","title":"Tabular Representation, Noisy Operators, and Impacts on Table Structure Understanding Tasks in LLMs","created":"2023-10-16","cited_by_count":49},{"id":"2304.06597","title":"\"What It Wants Me To Say\": Bridging the Abstraction Gap Between End-User Programmers and Code-Generating Large Language Models","created":"2023-04-13","cited_by_count":48},{"id":"2305.11483","title":"Sensecape: Enabling Multilevel Exploration and Sensemaking with Large Language Models","created":"2023-05-19","cited_by_count":48},{"id":"2201.09745","title":"Table Pre-training: A Survey on Model Architectures, Pre-training Objectives, and Downstream Tasks","created":"2022-01-24","cited_by_count":42},{"id":"2210.01922","title":"Semantics-aware Dataset Discovery from Data Lakes with Contextualized Column-based Representation Learning","created":"2022-10-04","cited_by_count":38},{"id":"2401.10880","title":"DynaVis: Dynamically Synthesized UI Widgets for Visualization Editing","created":"2024-01-19","cited_by_count":37},{"id":"2206.03865","title":"Fault-Aware Neural Code Rankers","created":"2022-06-04","cited_by_count":33},{"id":"2309.10094","title":"Data Formulator: AI-powered Concept-driven Visualization Authoring","created":"2023-09-18","cited_by_count":32},{"id":"2310.03691","title":"DirectGPT: A Direct Manipulation Interface to Interact with Large Language Models","created":"2023-10-05","cited_by_count":32},{"id":"2110.00680","title":"Collecting and Characterizing Natural Language Utterances for Specifying Data Visualizations","created":"2021-10-01","cited_by_count":31},{"id":"2112.12926","title":"nvBench: A Large-Scale Synthesized Dataset for Cross-Domain Natural Language to Visualization Task","created":"2021-12-24","cited_by_count":28},{"id":"2301.11178","title":"On the Design of AI-powered Code Assistants for Notebooks","created":"2023-01-26","cited_by_count":28},{"id":"2309.10947","title":"How Do Analysts Understand and Verify AI-Assisted Data Analyses?","created":"2023-09-19","cited_by_count":26},{"id":"2309.10108","title":"How Do Data Analysts Respond to AI Assistance? A Wizard-of-Oz Study","created":"2023-09-18","cited_by_count":24},{"id":"2305.09434","title":"Chatting with GPT-3 for Zero-Shot Human-Like Mobile Automated GUI Testing","created":"2023-05-16","cited_by_count":20},{"id":"2408.15247","title":"AutoGen Studio: A No-Code Developer Tool for Building and Debugging Multi-Agent Systems","created":"2024-08-09","cited_by_count":20},{"id":"2301.10385","title":"XNLI: Explaining and Diagnosing NLI-based Visual Data Analysis","created":"2023-01-25","cited_by_count":19},{"id":"2301.13779","title":"FLAME: A small language model for spreadsheet formulas","created":"2023-01-31","cited_by_count":15},{"id":"2202.00965","title":"GANSlider: How Users Control Generative Models for Images using Multiple Sliders with and without Feedforward Information","created":"2022-02-02","cited_by_count":13},{"id":"2306.05052","title":"Interpretable Medical Diagnostics with Structured Data Extraction by Large Language Models","created":"2023-06-08","cited_by_count":13},{"id":"2311.00272","title":"ChatCoder: Chat-based Refine Requirement Improves LLMs' Code Generation","created":"2023-11-01","cited_by_count":13},{"id":"2210.00848","title":"Toward Trustworthy Neural Program Synthesis","created":"2022-09-29","cited_by_count":11},{"id":"2307.07922","title":"InkSight: Leveraging Sketch Interaction for Documenting Chart Findings in Computational Notebooks","created":"2023-07-16","cited_by_count":11},{"id":"2103.03996","title":"ChartStory: Automated Partitioning, Layout, and Captioning of Charts into Comic-Style Narratives","created":"2021-03-06","cited_by_count":10},{"id":"1904.05387","title":"Tea: A High-level Language and Runtime System for Automating Statistical Analysis","created":"2019-04-10","cited_by_count":8},{"id":"2309.01957","title":"Automatic Data Transformation Using Large Language Model: An Experimental Study on Building Energy Data","created":"2023-09-05","cited_by_count":8},{"id":"2311.05590","title":"Conversational AI Threads for Visualizing Multidimensional Datasets","created":"2023-11-09","cited_by_count":8},{"id":"2308.01157","title":"LLMs Understand Glass-Box Models, Discover Surprises, and Suggest Repairs","created":"2023-08-02","cited_by_count":7},{"id":"2402.08073","title":"Grounding Data Science Code Generation with Input-Output Specifications","created":"2024-02-12","cited_by_count":7},{"id":"2208.03175","title":"MEDLEY: Intent-based Recommendations to Support Dashboard Composition","created":"2022-08-05","cited_by_count":6},{"id":"2308.10922","title":"DataVinci: Learning Syntactic and Semantic String Repairs","created":"2023-08-21","cited_by_count":6},{"id":"2201.02705","title":"Tisane: Authoring Statistical Models via Formal Reasoning from Conceptual and Data Relationships","created":"2022-01-07","cited_by_count":5},{"id":"2310.01297","title":"Co-audit: tools to help humans double-check AI-generated content","created":"2023-10-02","cited_by_count":5},{"id":"2211.15395","title":"CodeExp: Explanatory Code Document Generation","created":"2022-11-25","cited_by_count":4},{"id":"2408.11438","title":"Benchmarking AI-based data assimilation to advance data-driven global weather forecasting","created":"2024-08-21","cited_by_count":3}],"next_cursor":"100"}