{"list":"other","total":127,"rows":[{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2305.10601","title":"Tree of Thoughts: Deliberate Problem Solving with Large Language Models","created":"2023-05-17","cited_by_count":3211},{"id":"2311.12022","title":"GPQA: A Graduate-Level Google-Proof Q&A Benchmark","created":"2023-11-20","cited_by_count":2879},{"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":"2209.09513","title":"Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering","created":"2022-09-20","cited_by_count":1919},{"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":"2306.14824","title":"Kosmos-2: Grounding Multimodal Large Language Models to the World","created":"2023-06-26","cited_by_count":1089},{"id":"2303.17564","title":"BloombergGPT: A Large Language Model for Finance","created":"2023-03-30","cited_by_count":939},{"id":"2309.00770","title":"Bias and Fairness in Large Language Models: A Survey","created":"2023-09-02","cited_by_count":639},{"id":"2403.14624","title":"MathVerse: Does Your Multi-modal LLM Truly See the Diagrams in Visual Math Problems?","created":"2024-03-21","cited_by_count":586},{"id":"2109.00122","title":"FinQA: A Dataset of Numerical Reasoning over Financial Data","created":"2021-09-01","cited_by_count":562},{"id":"2302.14045","title":"Language Is Not All You Need: Aligning Perception with Language Models","created":"2023-02-27","cited_by_count":543},{"id":"2312.14150","title":"DriveLM: Driving with Graph Visual Question Answering","created":"2023-12-21","cited_by_count":536},{"id":"2306.15626","title":"LeanDojo: Theorem Proving with Retrieval-Augmented Language Models","created":"2023-06-27","cited_by_count":427},{"id":"2308.05374","title":"Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment","created":"2023-08-10","cited_by_count":401},{"id":"2311.12320","title":"A Survey on Multimodal Large Language Models for Autonomous Driving","created":"2023-11-21","cited_by_count":290},{"id":"2002.00469","title":"WeatherBench: A benchmark dataset for data-driven weather forecasting","created":"2020-02-02","cited_by_count":275},{"id":"2311.11944","title":"FinanceBench: A New Benchmark for Financial Question Answering","created":"2023-11-20","cited_by_count":270},{"id":"2308.11483","title":"Large Language Models Sensitivity to The Order of Options in Multiple-Choice Questions","created":"2023-08-22","cited_by_count":263},{"id":"2305.14836","title":"NuScenes-QA: A Multi-modal Visual Question Answering Benchmark for Autonomous Driving Scenario","created":"2023-05-24","cited_by_count":262},{"id":"2308.15560","title":"WeatherBench 2: A benchmark for the next generation of data-driven global weather models","created":"2023-08-29","cited_by_count":236},{"id":"2306.05443","title":"PIXIU: A Large Language Model, Instruction Data and Evaluation Benchmark for Finance","created":"2023-06-08","cited_by_count":222},{"id":"2210.03849","title":"ConvFinQA: Exploring the Chain of Numerical Reasoning in Conversational Finance Question Answering","created":"2022-10-07","cited_by_count":196},{"id":"2406.04127","title":"Are We Done with MMLU?","created":"2024-06-06","cited_by_count":194},{"id":"2305.18365","title":"What can Large Language Models do in chemistry? A comprehensive benchmark on eight tasks","created":"2023-05-27","cited_by_count":185},{"id":"2309.14556","title":"Art or Artifice? Large Language Models and the False Promise of Creativity","created":"2023-09-25","cited_by_count":172},{"id":"2403.15412","title":"Towards Measuring and Modeling \"Culture\" in LLMs: A Survey","created":"2024-03-05","cited_by_count":167},{"id":"2404.00578","title":"M3D: Advancing 3D Medical Image Analysis with Multi-Modal Large Language Models","created":"2024-03-31","cited_by_count":162},{"id":"2403.09630","title":"GenAD: Generalized Predictive Model for Autonomous Driving","created":"2024-03-14","cited_by_count":150},{"id":"2311.01043","title":"LLM4Drive: A Survey of Large Language Models for Autonomous Driving","created":"2023-11-02","cited_by_count":136},{"id":"2402.09391","title":"LlaSMol: Advancing Large Language Models for Chemistry with a Large-Scale, Comprehensive, High-Quality Instruction Tuning Dataset","created":"2024-02-14","cited_by_count":128},{"id":"2209.10767","title":"DRAMA: Joint Risk Localization and Captioning in Driving","created":"2022-09-22","cited_by_count":126},{"id":"2312.03661","title":"Reason2Drive: Towards Interpretable and Chain-based Reasoning for Autonomous Driving","created":"2023-12-06","cited_by_count":123},{"id":"2211.00083","title":"WHEN FLUE MEETS FLANG: Benchmarks and Large Pre-trained Language Model for Financial Domain","created":"2022-10-31","cited_by_count":117},{"id":"2309.04379","title":"Language Prompt for Autonomous Driving","created":"2023-09-08","cited_by_count":111},{"id":"1709.04555","title":"Predicting Organic Reaction Outcomes with Weisfeiler-Lehman Network","created":"2017-09-13","cited_by_count":103},{"id":"2409.02889","title":"LongLLaVA: Scaling Multi-modal LLMs to 1000 Images Efficiently via a Hybrid Architecture","created":"2024-09-04","cited_by_count":102},{"id":"2408.03361","title":"GMAI-MMBench: A Comprehensive Multimodal Evaluation Benchmark Towards General Medical AI","created":"2024-08-06","cited_by_count":96},{"id":"2406.12708","title":"AgentReview: Exploring Peer Review Dynamics with LLM Agents","created":"2024-06-18","cited_by_count":93},{"id":"2110.12010","title":"ClimateBert: A Pretrained Language Model for Climate-Related Text","created":"2021-10-22","cited_by_count":90},{"id":"2401.00988","title":"Holistic Autonomous Driving Understanding by Bird's-Eye-View Injected Multi-Modal Large Models","created":"2024-01-02","cited_by_count":76},{"id":"2406.12036","title":"MedCalc-Bench: Evaluating Large Language Models for Medical Calculations","created":"2024-06-17","cited_by_count":70},{"id":"2410.06234","title":"TEOChat: A Large Vision-Language Assistant for Temporal Earth Observation Data","created":"2024-10-08","cited_by_count":70},{"id":"2307.10485","title":"FinGPT: Democratizing Internet-scale Data for Financial Large Language Models","created":"2023-07-19","cited_by_count":67},{"id":"2307.03875","title":"Large Language Models for Supply Chain Optimization","created":"2023-07-08","cited_by_count":64},{"id":"2309.06597","title":"Rank2Tell: A Multimodal Driving Dataset for Joint Importance Ranking and Reasoning","created":"2023-09-12","cited_by_count":63},{"id":"2401.06915","title":"DocFinQA: A Long-Context Financial Reasoning Dataset","created":"2024-01-12","cited_by_count":60},{"id":"2312.15223","title":"A Survey on Large Language Models for Software Engineering","created":"2023-12-23","cited_by_count":59},{"id":"2401.09003","title":"Augmenting Math Word Problems via Iterative Question Composing","created":"2024-01-17","cited_by_count":59},{"id":"2410.11761","title":"SlideChat: A Large Vision-Language Assistant for Whole-Slide Pathology Image Understanding","created":"2024-10-15","cited_by_count":57},{"id":"2502.03461","title":"Do Large Language Model Benchmarks Test Reliability?","created":"2025-02-05","cited_by_count":54},{"id":"2411.19325","title":"GEOBench-VLM: Benchmarking Vision-Language Models for Geospatial Tasks","created":"2024-11-28","cited_by_count":51},{"id":"2408.01337","title":"MuChoMusic: Evaluating Music Understanding in Multimodal Audio-Language Models","created":"2024-08-02","cited_by_count":44},{"id":"2401.16355","title":"PathMMU: A Massive Multimodal Expert-Level Benchmark for Understanding and Reasoning in Pathology","created":"2024-01-29","cited_by_count":43},{"id":"2501.01282","title":"CultureVLM: Characterizing and Improving Cultural Understanding of Vision-Language Models for over 100 Countries","created":"2025-01-02","cited_by_count":42},{"id":"2311.09797","title":"FinanceMath: Knowledge-Intensive Math Reasoning in Finance Domains","created":"2023-11-16","cited_by_count":40},{"id":"2401.17600","title":"Good at captioning, bad at counting: Benchmarking GPT-4V on Earth observation data","created":"2024-01-31","cited_by_count":39},{"id":"2404.01266","title":"IsoBench: Benchmarking Multimodal Foundation Models on Isomorphic Representations","created":"2024-04-01","cited_by_count":38},{"id":"2405.14785","title":"EditWorld: Simulating World Dynamics for Instruction-Following Image Editing","created":"2024-05-23","cited_by_count":38},{"id":"2501.04678","title":"RadGPT: Constructing 3D Image-Text Tumor Datasets","created":"2025-01-08","cited_by_count":36},{"id":"2405.19334","title":"LLMs Meet Multimodal Generation and Editing: A Survey","created":"2024-05-29","cited_by_count":35},{"id":"2311.14656","title":"Charting New Territories: Exploring the Geographic and Geospatial Capabilities of Multimodal LLMs","created":"2023-11-24","cited_by_count":34},{"id":"2404.01475","title":"Are large language models superhuman chemists?","created":"2024-04-01","cited_by_count":34},{"id":"2401.12975","title":"HAZARD Challenge: Embodied Decision Making in Dynamically Changing Environments","created":"2024-01-23","cited_by_count":32},{"id":"2404.07917","title":"DesignQA: A Multimodal Benchmark for Evaluating Large Language Models' Understanding of Engineering Documentation","created":"2024-04-11","cited_by_count":32},{"id":"2410.09988","title":"HARDMath: A Benchmark Dataset for Challenging Problems in Applied Mathematics","created":"2024-10-13","cited_by_count":32},{"id":"2502.04424","title":"EmoBench-M: Benchmarking Emotional Intelligence for Multimodal Large Language Models","created":"2025-02-06","cited_by_count":32},{"id":"2502.12532","title":"CityEQA: A Hierarchical LLM Agent on Embodied Question Answering Benchmark in City Space","created":"2025-02-18","cited_by_count":32},{"id":"2503.13399","title":"MicroVQA: A Multimodal Reasoning Benchmark for Microscopy-Based Scientific Research","created":"2025-03-17","cited_by_count":32},{"id":"2412.05679","title":"RSUniVLM: A Unified Vision Language Model for Remote Sensing via Granularity-oriented Mixture of Experts","created":"2024-12-07","cited_by_count":29},{"id":"2405.11966","title":"Multiple-Choice Questions are Efficient and Robust LLM Evaluators","created":"2024-05-20","cited_by_count":28},{"id":"2405.19444","title":"MathChat: Benchmarking Mathematical Reasoning and Instruction Following in Multi-Turn Interactions","created":"2024-05-29","cited_by_count":26},{"id":"2503.21411","title":"Exploring the Roles of Large Language Models in Reshaping Transportation Systems: A Survey, Framework, and Roadmap","created":"2025-03-27","cited_by_count":26},{"id":"2303.01212","title":"Grid-Centric Traffic Scenario Perception for Autonomous Driving: A Comprehensive Review","created":"2023-03-02","cited_by_count":25},{"id":"2407.19617","title":"Leveraging Vision Language Models for Specialized Agricultural Tasks","created":"2024-07-29","cited_by_count":25},{"id":"2406.05392","title":"Deconstructing The Ethics of Large Language Models from Long-standing Issues to New-emerging Dilemmas: A Survey","created":"2024-06-08","cited_by_count":23},{"id":"2409.15477","title":"MediConfusion: Can you trust your AI radiologist? Probing the reliability of multimodal medical foundation models","created":"2024-09-23","cited_by_count":23},{"id":"2406.11217","title":"WeatherQA: Can Multimodal Language Models Reason about Severe Weather?","created":"2024-06-17","cited_by_count":22},{"id":"2411.08561","title":"LogLLM: Log-based Anomaly Detection Using Large Language Models","created":"2024-11-13","cited_by_count":22},{"id":"2401.05443","title":"LLM4PLC: Harnessing Large Language Models for Verifiable Programming of PLCs in Industrial Control Systems","created":"2024-01-08","cited_by_count":21},{"id":"2401.17882","title":"I Think, Therefore I am: Benchmarking Awareness of Large Language Models Using AwareBench","created":"2024-01-31","cited_by_count":21},{"id":"2411.00177","title":"LLM4Mat-Bench: Benchmarking Large Language Models for Materials Property Prediction","created":"2024-10-31","cited_by_count":21},{"id":"2402.09871","title":"MuChin: A Chinese Colloquial Description Benchmark for Evaluating Language Models in the Field of Music","created":"2024-02-15","cited_by_count":16},{"id":"2403.06838","title":"ACFIX: Guiding LLMs with Mined Common RBAC Practices for Context-Aware Repair of Access Control Vulnerabilities in Smart Contracts","created":"2024-03-11","cited_by_count":15},{"id":"2404.08704","title":"MM-PhyQA: Multimodal Physics Question-Answering With Multi-Image CoT Prompting","created":"2024-04-11","cited_by_count":15},{"id":"2405.06690","title":"DrugLLM: Open Large Language Model for Few-shot Molecule Generation","created":"2024-05-07","cited_by_count":15},{"id":"2406.19693","title":"MMRo: Are Multimodal LLMs Eligible as the Brain for In-Home Robotics?","created":"2024-06-28","cited_by_count":15},{"id":"2407.01791","title":"{\\mu}-Bench: A Vision-Language Benchmark for Microscopy Understanding","created":"2024-07-01","cited_by_count":15},{"id":"2412.05288","title":"StackEval: Benchmarking LLMs in Coding Assistance","created":"2024-11-21","cited_by_count":15},{"id":"2406.13193","title":"PRESTO: Progressive Pretraining Enhances Synthetic Chemistry Outcomes","created":"2024-06-19","cited_by_count":14},{"id":"2406.15444","title":"Cutting Through the Noise: Boosting LLM Performance on Math Word Problems","created":"2024-05-30","cited_by_count":14},{"id":"2407.17152","title":"XMeCap: Meme Caption Generation with Sub-Image Adaptability","created":"2024-07-24","cited_by_count":14},{"id":"2308.16622","title":"Developing a Scalable Benchmark for Assessing Large Language Models in Knowledge Graph Engineering","created":"2023-08-31","cited_by_count":13},{"id":"2409.13730","title":"VisScience: An Extensive Benchmark for Evaluating K12 Educational Multi-modal Scientific Reasoning","created":"2024-09-10","cited_by_count":13},{"id":"2412.18573","title":"Top General Performance = Top Domain Performance? DomainCodeBench: A Multi-domain Code Generation Benchmark","created":"2024-12-24","cited_by_count":13},{"id":"2411.09547","title":"Piecing It All Together: Verifying Multi-Hop Multimodal Claims","created":"2024-11-14","cited_by_count":12},{"id":"2503.19598","title":"The Greatest Good Benchmark: Measuring LLMs' Alignment with Utilitarian Moral Dilemmas","created":"2025-03-25","cited_by_count":12},{"id":"2308.09115","title":"MaScQA: A Question Answering Dataset for Investigating Materials Science Knowledge of Large Language Models","created":"2023-08-17","cited_by_count":11}],"next_cursor":"100"}