{"list":"other","total":73,"rows":[{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"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":"1611.09268","title":"MS MARCO: A Human Generated MAchine Reading COmprehension Dataset","created":"2016-11-28","cited_by_count":1605},{"id":"2006.05525","title":"Knowledge Distillation: A Survey","created":"2020-06-09","cited_by_count":1603},{"id":"2311.05232","title":"A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions","created":"2023-11-09","cited_by_count":1601},{"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":"2307.03109","title":"A Survey on Evaluation of Large Language Models","created":"2023-07-06","cited_by_count":1242},{"id":"2403.04132","title":"Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference","created":"2024-03-07","cited_by_count":1184},{"id":"1903.00161","title":"DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs","created":"2019-03-01","cited_by_count":903},{"id":"2103.13630","title":"A Survey of Quantization Methods for Efficient Neural Network Inference","created":"2021-03-25","cited_by_count":815},{"id":"2309.01219","title":"Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models","created":"2023-09-03","cited_by_count":698},{"id":"2307.06435","title":"A Comprehensive Overview of Large Language Models","created":"2023-07-12","cited_by_count":648},{"id":"2309.00770","title":"Bias and Fairness in Large Language Models: A Survey","created":"2023-09-02","cited_by_count":639},{"id":"2308.10792","title":"Instruction Tuning for Large Language Models: A Survey","created":"2023-08-21","cited_by_count":623},{"id":"2004.05785","title":"Learning under Concept Drift: A Review","created":"2020-04-13","cited_by_count":477},{"id":"2402.04788","title":"MLLM-as-a-Judge: Assessing Multimodal LLM-as-a-Judge with Vision-Language Benchmark","created":"2024-02-07","cited_by_count":372},{"id":"2302.09419","title":"A Comprehensive Survey on Pretrained Foundation Models: A History from BERT to ChatGPT","created":"2023-02-18","cited_by_count":368},{"id":"2309.05922","title":"A Survey of Hallucination in Large Foundation Models","created":"2023-09-12","cited_by_count":368},{"id":"2402.14992","title":"tinyBenchmarks: evaluating LLMs with fewer examples","created":"2024-02-22","cited_by_count":310},{"id":"2311.12320","title":"A Survey on Multimodal Large Language Models for Autonomous Driving","created":"2023-11-21","cited_by_count":290},{"id":"2308.07633","title":"A Survey on Model Compression for Large Language Models","created":"2023-08-15","cited_by_count":269},{"id":"2212.09597","title":"Reasoning with Language Model Prompting: A Survey","created":"2022-12-19","cited_by_count":252},{"id":"2309.15025","title":"Large Language Model Alignment: A Survey","created":"2023-09-26","cited_by_count":243},{"id":"2310.17623","title":"Proving Test Set Contamination in Black Box Language Models","created":"2023-10-26","cited_by_count":230},{"id":"2307.08177","title":"Using an LLM to Help With Code Understanding","created":"2023-07-17","cited_by_count":228},{"id":"2206.15000","title":"Grounded Copilot: How Programmers Interact with Code-Generating Models","created":"2022-06-30","cited_by_count":218},{"id":"2310.19736","title":"Evaluating Large Language Models: A Comprehensive Survey","created":"2023-10-30","cited_by_count":202},{"id":"2311.04850","title":"Rethinking Benchmark and Contamination for Language Models with Rephrased Samples","created":"2023-11-08","cited_by_count":195},{"id":"2311.13165","title":"Multimodal Large Language Models: A Survey","created":"2023-11-22","cited_by_count":195},{"id":"2310.16218","title":"Knowledge Editing for Large Language Models: A Survey","created":"2023-10-24","cited_by_count":194},{"id":"1811.12808","title":"Model Evaluation, Model Selection, and Algorithm Selection in Machine Learning","created":"2018-11-13","cited_by_count":157},{"id":"2206.15331","title":"GitHub Copilot AI pair programmer: Asset or Liability?","created":"2022-06-30","cited_by_count":152},{"id":"2402.01781","title":"When Benchmarks are Targets: Revealing the Sensitivity of Large Language Model Leaderboards","created":"2024-02-01","cited_by_count":137},{"id":"2311.01043","title":"LLM4Drive: A Survey of Large Language Models for Autonomous Driving","created":"2023-11-02","cited_by_count":136},{"id":"2401.06805","title":"Exploring the Reasoning Abilities of Multimodal Large Language Models (MLLMs): A Comprehensive Survey on Emerging Trends in Multimodal Reasoning","created":"2024-01-10","cited_by_count":136},{"id":"2205.02302","title":"Machine Learning Operations (MLOps): Overview, Definition, and Architecture","created":"2022-05-04","cited_by_count":128},{"id":"2404.18824","title":"Benchmarking Benchmark Leakage in Large Language Models","created":"2024-04-29","cited_by_count":106},{"id":"2309.09128","title":"ChainForge: A Visual Toolkit for Prompt Engineering and LLM Hypothesis Testing","created":"2023-09-17","cited_by_count":88},{"id":"2310.12321","title":"A Survey of GPT-3 Family Large Language Models Including ChatGPT and GPT-4","created":"2023-10-04","cited_by_count":81},{"id":"2203.04592","title":"Mapping global dynamics of benchmark creation and saturation in artificial intelligence","created":"2022-03-09","cited_by_count":71},{"id":"2205.10583","title":"Automated Repair of Programs from Large Language Models","created":"2022-05-21","cited_by_count":71},{"id":"2102.01818","title":"Memorization vs. Generalization: Quantifying Data Leakage in NLP Performance Evaluation","created":"2021-02-03","cited_by_count":70},{"id":"2311.18743","title":"AlignBench: Benchmarking Chinese Alignment of Large Language Models","created":"2023-11-30","cited_by_count":68},{"id":"2303.11568","title":"Large AI Models in Health Informatics: Applications, Challenges, and the Future","created":"2023-03-21","cited_by_count":61},{"id":"2110.12773","title":"Scientific Machine Learning Benchmarks","created":"2021-10-25","cited_by_count":60},{"id":"2307.05532","title":"Opening up ChatGPT: Tracking openness, transparency, and accountability in instruction-tuned text generators","created":"2023-07-08","cited_by_count":56},{"id":"2004.14356","title":"AxCell: Automatic Extraction of Results from Machine Learning Papers","created":"2020-04-29","cited_by_count":48},{"id":"2007.07399","title":"Bringing the People Back In: Contesting Benchmark Machine Learning Datasets","created":"2020-07-14","cited_by_count":43},{"id":"2306.01987","title":"Prompting Is All You Need: Automated Android Bug Replay with Large Language Models","created":"2023-06-03","cited_by_count":40},{"id":"2309.14365","title":"An In-depth Survey of Large Language Model-based Artificial Intelligence Agents","created":"2023-09-23","cited_by_count":31},{"id":"2209.15259","title":"On the Impossible Safety of Large AI Models","created":"2022-09-30","cited_by_count":28},{"id":"2311.05876","title":"Trends in Integration of Knowledge and Large Language Models: A Survey and Taxonomy of Methods, Benchmarks, and Applications","created":"2023-11-10","cited_by_count":28},{"id":"2401.07654","title":"Foundation Models for Biomedical Image Segmentation: A Survey","created":"2024-01-15","cited_by_count":28},{"id":"1811.07643","title":"What's in a GitHub Star? Understanding Repository Starring Practices in a Social Coding Platform","created":"2018-11-19","cited_by_count":25},{"id":"2303.07616","title":"The Life Cycle of Knowledge in Big Language Models: A Survey","created":"2023-03-14","cited_by_count":23},{"id":"1910.05040","title":"BiPaR: A Bilingual Parallel Dataset for Multilingual and Cross-lingual Reading Comprehension on Novels","created":"2019-10-11","cited_by_count":17},{"id":"2109.13089","title":"Automated Mining of Leaderboards for Empirical AI Research","created":"2021-08-31","cited_by_count":16},{"id":"2402.16268","title":"Foundation Model Transparency Reports","created":"2024-02-26","cited_by_count":14},{"id":"2310.03715","title":"Artificial Intelligence Index Report 2023","created":"2023-10-05","cited_by_count":13},{"id":"2305.11068","title":"ORKG-Leaderboards: A Systematic Workflow for Mining Leaderboards as a Knowledge Graph","created":"2023-05-10","cited_by_count":11},{"id":"2307.02088","title":"Trust in Software Supply Chains: Blockchain-Enabled SBOM and the AIBOM Future","created":"2023-07-05","cited_by_count":8},{"id":"2404.04902","title":"AI2Apps: A Visual IDE for Building LLM-based AI Agent Applications","created":"2024-04-07","cited_by_count":5},{"id":"2010.14573","title":"Dependency Smells in JavaScript Projects","created":"2020-10-27","cited_by_count":4},{"id":"2212.08966","title":"Graph Learning and Its Advancements on Large Language Models: A Holistic Survey","created":"2022-12-17","cited_by_count":4},{"id":"2301.01235","title":"An Empirical Investigation into the Reproduction of Bug Reports for Android Apps","created":"2023-01-03","cited_by_count":4}],"next_cursor":null}