{"list":"other","total":54,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"1603.02754","title":"XGBoost: A Scalable Tree Boosting System","created":"2016-03-09","cited_by_count":5166},{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"2407.10671","title":"Qwen2 Technical Report","created":"2024-07-15","cited_by_count":2120},{"id":"2406.01574","title":"MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark","created":"2024-06-03","cited_by_count":1848},{"id":"2506.05176","title":"Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models","created":"2025-06-05","cited_by_count":1261},{"id":"2403.07815","title":"Chronos: Learning the Language of Time Series","created":"2024-03-12","cited_by_count":759},{"id":"2310.01728","title":"Time-LLM: Time Series Forecasting by Reprogramming Large Language Models","created":"2023-10-03","cited_by_count":700},{"id":"2310.10688","title":"A decoder-only foundation model for time-series forecasting","created":"2023-10-14","cited_by_count":692},{"id":"2310.07820","title":"Large Language Models Are Zero-Shot Time Series Forecasters","created":"2023-10-11","cited_by_count":500},{"id":"2402.14992","title":"tinyBenchmarks: evaluating LLMs with fewer examples","created":"2024-02-22","cited_by_count":310},{"id":"2401.00368","title":"Improving Text Embeddings with Large Language Models","created":"2023-12-31","cited_by_count":303},{"id":"1902.03545","title":"Task2Vec: Task Embedding for Meta-Learning","created":"2019-02-10","cited_by_count":205},{"id":"2310.04948","title":"TEMPO: Prompt-based Generative Pre-trained Transformer for Time Series Forecasting","created":"2023-10-08","cited_by_count":174},{"id":"2406.16964","title":"Are Language Models Actually Useful for Time Series Forecasting?","created":"2024-06-22","cited_by_count":168},{"id":"2409.19839","title":"ForecastBench: A Dynamic Benchmark of AI Forecasting Capabilities","created":"2024-09-30","cited_by_count":110},{"id":"2402.18563","title":"Approaching Human-Level Forecasting with Language Models","created":"2024-02-28","cited_by_count":107},{"id":"2305.07141","title":"The ConceptARC Benchmark: Evaluating Understanding and Generalization in the ARC Domain","created":"2023-05-11","cited_by_count":101},{"id":"2505.14489","title":"Reasoning Models Better Express Their Confidence","created":"2025-05-20","cited_by_count":65},{"id":"2206.15474","title":"Forecasting Future World Events with Neural Networks","created":"2022-06-30","cited_by_count":63},{"id":"2404.07544","title":"From Words to Numbers: Your Large Language Model Is Secretly A Capable Regressor When Given In-Context Examples","created":"2024-04-11","cited_by_count":57},{"id":"2311.09247","title":"Comparing Humans, GPT-4, and GPT-4V On Abstraction and Reasoning Tasks","created":"2023-11-14","cited_by_count":55},{"id":"2405.12856","title":"LLM Processes: Numerical Predictive Distributions Conditioned on Natural Language","created":"2024-05-21","cited_by_count":55},{"id":"1906.09317","title":"Identification of Tasks, Datasets, Evaluation Metrics, and Numeric Scores for Scientific Leaderboards Construction","created":"2019-06-21","cited_by_count":50},{"id":"2005.00870","title":"Predicting Performance for Natural Language Processing Tasks","created":"2020-05-02","cited_by_count":49},{"id":"2004.14356","title":"AxCell: Automatic Extraction of Results from Machine Learning Papers","created":"2020-04-29","cited_by_count":48},{"id":"2503.07649","title":"TS-RAG: Retrieval-Augmented Generation based Time Series Foundation Models are Stronger Zero-Shot Forecaster","created":"2025-03-06","cited_by_count":40},{"id":"2503.01013","title":"TimeXL: Explainable Multi-modal Time Series Prediction with LLM-in-the-Loop","created":"2025-03-02","cited_by_count":39},{"id":"2107.02153","title":"FaVIQ: FAct Verification from Information-seeking Questions","created":"2021-07-05","cited_by_count":36},{"id":"2501.01028","title":"KaLM-Embedding: Superior Training Data Brings A Stronger Embedding Model","created":"2025-01-02","cited_by_count":36},{"id":"2305.14947","title":"How Predictable Are Large Language Model Capabilities? A Case Study on BIG-bench","created":"2023-05-24","cited_by_count":34},{"id":"2402.14547","title":"OmniPred: Language Models as Universal Regressors","created":"2024-02-22","cited_by_count":34},{"id":"2310.16712","title":"LLM Performance Predictors are good initializers for Architecture Search","created":"2023-10-25","cited_by_count":29},{"id":"2311.01152","title":"Predicting Question-Answering Performance of Large Language Models through Semantic Consistency","created":"2023-11-02","cited_by_count":28},{"id":"2102.05486","title":"Towards More Fine-grained and Reliable NLP Performance Prediction","created":"2021-02-10","cited_by_count":26},{"id":"2305.14336","title":"Schema-Driven Information Extraction from Heterogeneous Tables","created":"2023-05-23","cited_by_count":25},{"id":"2110.08875","title":"Predicting the Performance of Multilingual NLP Models","created":"2021-10-17","cited_by_count":24},{"id":"2310.13014","title":"Large Language Model Prediction Capabilities: Evidence from a Real-World Forecasting Tournament","created":"2023-10-17","cited_by_count":24},{"id":"2409.03563","title":"100 instances is all you need: predicting the success of a new LLM on unseen data by testing on a few instances","created":"2024-09-05","cited_by_count":24},{"id":"2205.06130","title":"Multi Task Learning For Zero Shot Performance Prediction of Multilingual Models","created":"2022-05-12","cited_by_count":20},{"id":"2406.09334","title":"ProxyLM: Predicting Language Model Performance on Multilingual Tasks via Proxy Models","created":"2024-06-13","cited_by_count":20},{"id":"2506.00794","title":"Predicting Empirical AI Research Outcomes with Language Models","created":"2025-06-01","cited_by_count":17},{"id":"2312.06941","title":"Humans vs Large Language Models: Judgmental Forecasting in an Era of Advanced AI","created":"2023-12-12","cited_by_count":11},{"id":"2409.12656","title":"Efficient Performance Tracking: Leveraging Large Language Models for Automated Construction of Scientific Leaderboards","created":"2024-09-19","cited_by_count":10},{"id":"1802.04538","title":"Automated Early Leaderboard Generation From Comparative Tables","created":"2018-02-13","cited_by_count":9},{"id":"2010.06127","title":"Model Selection for Cross-Lingual Transfer","created":"2020-10-13","cited_by_count":9},{"id":"2410.10112","title":"Can We Predict Performance of Large Models across Vision-Language Tasks?","created":"2024-10-14","cited_by_count":6},{"id":"2405.18344","title":"The Battle of LLMs: A Comparative Study in Conversational QA Tasks","created":"2024-05-28","cited_by_count":5},{"id":"2502.18791","title":"Can LLMs Help Uncover Insights about LLMs? A Large-Scale, Evolving Literature Analysis of Frontier LLMs","created":"2025-02-26","cited_by_count":3},{"id":"2508.01203","title":"Importance Sampling is All You Need: Predict LLM's performance on new benchmark by reusing existing benchmark","created":"2025-08-02","cited_by_count":2}],"next_cursor":null}