{"list":"other","total":53,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"id":"1603.02754","title":"XGBoost: A Scalable Tree Boosting System","created":"2016-03-09","cited_by_count":5166},{"id":"2305.10355","title":"Evaluating Object Hallucination in Large Vision-Language Models","created":"2023-05-17","cited_by_count":1729},{"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":"2411.15594","title":"A Survey on LLM-as-a-Judge","created":"2024-11-23","cited_by_count":1423},{"id":"2404.07972","title":"OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments","created":"2024-04-11","cited_by_count":1195},{"id":"2104.08773","title":"Cross-Task Generalization via Natural Language Crowdsourcing Instructions","created":"2021-04-18","cited_by_count":699},{"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":"2102.01454","title":"MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Frontiers","created":"2021-02-02","cited_by_count":470},{"id":"2401.13919","title":"WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models","created":"2024-01-25","cited_by_count":438},{"id":"1906.08158","title":"BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning","created":"2019-06-19","cited_by_count":432},{"id":"2212.09689","title":"Unnatural Instructions: Tuning Language Models with (Almost) No Human Labor","created":"2022-12-19","cited_by_count":397},{"id":"2310.18018","title":"NLP Evaluation in trouble: On the Need to Measure LLM Data Contamination for each Benchmark","created":"2023-10-27","cited_by_count":348},{"id":"1502.02761","title":"Generative Moment Matching Networks","created":"2015-02-10","cited_by_count":257},{"id":"2308.06394","title":"Detecting and Preventing Hallucinations in Large Vision Language Models","created":"2023-08-11","cited_by_count":256},{"id":"2307.01850","title":"Self-Consuming Generative Models Go MAD","created":"2023-07-04","cited_by_count":250},{"id":"2306.15895","title":"Large Language Model as Attributed Training Data Generator: A Tale of Diversity and Bias","created":"2023-06-28","cited_by_count":232},{"id":"2411.07763","title":"Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflows","created":"2024-11-12","cited_by_count":232},{"id":"2310.17623","title":"Proving Test Set Contamination in Black Box Language Models","created":"2023-10-26","cited_by_count":230},{"id":"2402.03927","title":"Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMs","created":"2024-02-06","cited_by_count":229},{"id":"2202.07922","title":"ZeroGen: Efficient Zero-shot Learning via Dataset Generation","created":"2022-02-16","cited_by_count":211},{"id":"2402.13446","title":"Large Language Models for Data Annotation and Synthesis: A Survey","created":"2024-02-21","cited_by_count":205},{"id":"2406.18518","title":"APIGen: Automated Pipeline for Generating Verifiable and Diverse Function-Calling Datasets","created":"2024-06-26","cited_by_count":198},{"id":"2402.16347","title":"CodeS: Towards Building Open-source Language Models for Text-to-SQL","created":"2024-02-26","cited_by_count":187},{"id":"2407.01492","title":"RegMix: Data Mixture as Regression for Language Model Pre-training","created":"2024-07-01","cited_by_count":177},{"id":"2412.19723","title":"OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis","created":"2024-12-27","cited_by_count":163},{"id":"2412.09605","title":"AgentTrek: Agent Trajectory Synthesis via Guiding Replay with Web Tutorials","created":"2024-12-12","cited_by_count":130},{"id":"2407.12580","title":"E5-V: Universal Embeddings with Multimodal Large Language Models","created":"2024-07-17","cited_by_count":126},{"id":"2201.04684","title":"BigDatasetGAN: Synthesizing ImageNet with Pixel-wise Annotations","created":"2022-01-12","cited_by_count":99},{"id":"2406.14532","title":"RL on Incorrect Synthetic Data Scales the Efficiency of LLM Math Reasoning by Eight-Fold","created":"2024-06-20","cited_by_count":99},{"id":"2408.00764","title":"AgentGen: Enhancing Planning Abilities for Large Language Model based Agent via Environment and Task Generation","created":"2024-08-01","cited_by_count":83},{"id":"2311.16822","title":"Large Language Models Suffer From Their Own Output: An Analysis of the Self-Consuming Training Loop","created":"2023-11-28","cited_by_count":79},{"id":"2211.08095","title":"Will Large-scale Generative Models Corrupt Future Datasets?","created":"2022-11-15","cited_by_count":59},{"id":"2410.02907","title":"NNetNav: Unsupervised Learning of Browser Agents Through Environment Interaction in the Wild","created":"2024-10-03","cited_by_count":59},{"id":"2408.03256","title":"Synthesizing Text-to-SQL Data from Weak and Strong LLMs","created":"2024-08-06","cited_by_count":54},{"id":"2503.05061","title":"No Free Labels: Limitations of LLM-as-a-Judge Without Human Grounding","created":"2025-03-07","cited_by_count":54},{"id":"2205.12679","title":"Self-Guided Noise-Free Data Generation for Efficient Zero-Shot Learning","created":"2022-05-25","cited_by_count":50},{"id":"2412.13194","title":"Proposer-Agent-Evaluator(PAE): Autonomous Skill Discovery For Foundation Model Internet Agents","created":"2024-12-17","cited_by_count":50},{"id":"1810.05691","title":"Faster k-Medoids Clustering: Improving the PAM, CLARA, and CLARANS Algorithms","created":"2018-10-12","cited_by_count":44},{"id":"2504.11393","title":"DataDecide: How to Predict Best Pretraining Data with Small Experiments","created":"2025-04-15","cited_by_count":40},{"id":"1901.00735","title":"Dataset search: a survey","created":"2019-01-03","cited_by_count":36},{"id":"2304.13861","title":"The Parrot Dilemma: Human-Labeled vs. LLM-augmented Data in Classification Tasks","created":"2023-04-26","cited_by_count":35},{"id":"2409.16986","title":"Harnessing Diversity for Important Data Selection in Pretraining Large Language Models","created":"2024-09-25","cited_by_count":34},{"id":"2409.18153","title":"Most Influential Subset Selection: Challenges, Promises, and Beyond","created":"2024-09-25","cited_by_count":32},{"id":"2012.09673","title":"Combating Mode Collapse in GAN training: An Empirical Analysis using Hessian Eigenvalues","created":"2020-12-17","cited_by_count":27},{"id":"2101.06030","title":"Directed Diversity: Leveraging Language Embedding Distances for Collective Creativity in Crowd Ideation","created":"2021-01-15","cited_by_count":23},{"id":"2406.05184","title":"The Unmet Promise of Synthetic Training Images: Using Retrieved Real Images Performs Better","created":"2024-06-07","cited_by_count":19},{"id":"1805.11191","title":"Learning From Less Data: Diversified Subset Selection and Active Learning in Image Classification Tasks","created":"2018-05-28","cited_by_count":10}],"next_cursor":null}