{"list":"other","total":61,"rows":[{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"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":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"id":"1803.05457","title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","created":"2018-03-14","cited_by_count":4886},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"1905.07830","title":"HellaSwag: Can a Machine Really Finish Your Sentence?","created":"2019-05-19","cited_by_count":4100},{"id":"1809.09600","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","created":"2018-09-25","cited_by_count":3754},{"id":"2108.07732","title":"Program Synthesis with Large Language Models","created":"2021-08-16","cited_by_count":3637},{"id":"2109.07958","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","created":"2021-09-08","cited_by_count":2975},{"id":"2311.12022","title":"GPQA: A Graduate-Level Google-Proof Q&A Benchmark","created":"2023-11-20","cited_by_count":2879},{"id":"1905.10044","title":"BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions","created":"2019-05-24","cited_by_count":2183},{"id":"1809.02789","title":"Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering","created":"2018-09-08","cited_by_count":2164},{"id":"2403.07974","title":"LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code","created":"2024-03-12","cited_by_count":2004},{"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":"1811.00937","title":"CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge","created":"2018-11-02","cited_by_count":1822},{"id":"1905.00537","title":"SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems","created":"2019-05-02","cited_by_count":1729},{"id":"2002.10957","title":"MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers","created":"2020-02-25","cited_by_count":1463},{"id":"2009.13081","title":"What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams","created":"2020-09-28","cited_by_count":1356},{"id":"2004.09297","title":"MPNet: Masked and Permuted Pre-training for Language Understanding","created":"2020-04-20","cited_by_count":981},{"id":"2103.07191","title":"Are NLP Models really able to Solve Simple Math Word Problems?","created":"2021-03-12","cited_by_count":878},{"id":"1707.06209","title":"Crowdsourcing Multiple Choice Science Questions","created":"2017-07-19","cited_by_count":765},{"id":"2008.02275","title":"Aligning AI With Shared Human Values","created":"2020-08-05","cited_by_count":723},{"id":"2304.06364","title":"AGIEval: A Human-Centric Benchmark for Evaluating Foundation Models","created":"2023-04-13","cited_by_count":716},{"id":"1808.07042","title":"CoQA: A Conversational Question Answering Challenge","created":"2018-08-21","cited_by_count":683},{"id":"2406.18665","title":"RouteLLM: Learning to Route LLMs with Preference Data","created":"2024-06-26","cited_by_count":682},{"id":"1905.13319","title":"MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalisms","created":"2019-05-30","cited_by_count":662},{"id":"1705.04146","title":"Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problems","created":"2017-05-11","cited_by_count":650},{"id":"1712.07040","title":"The NarrativeQA Reading Comprehension Challenge","created":"2017-12-19","cited_by_count":597},{"id":"1910.11856","title":"On the Cross-lingual Transferability of Monolingual Representations","created":"2019-10-25","cited_by_count":578},{"id":"2109.00122","title":"FinQA: A Dataset of Numerical Reasoning over Financial Data","created":"2021-09-01","cited_by_count":562},{"id":"2203.14371","title":"MedMCQA : A Large-scale Multi-Subject Multi-Choice Dataset for Medical domain Question Answering","created":"2022-03-27","cited_by_count":543},{"id":"2003.05002","title":"TyDi QA: A Benchmark for Information-Seeking Question Answering in Typologically Diverse Languages","created":"2020-03-10","cited_by_count":488},{"id":"1808.07036","title":"QuAC : Question Answering in Context","created":"2018-08-21","cited_by_count":381},{"id":"1910.07475","title":"MLQA: Evaluating Cross-lingual Extractive Question Answering","created":"2019-10-16","cited_by_count":340},{"id":"1611.09830","title":"NewsQA: A Machine Comprehension Dataset","created":"2016-11-29","cited_by_count":331},{"id":"2106.15772","title":"A Diverse Corpus for Evaluating and Developing English Math Word Problem Solvers","created":"2021-06-30","cited_by_count":318},{"id":"1910.11473","title":"QASC: A Dataset for Question Answering via Sentence Composition","created":"2019-10-25","cited_by_count":252},{"id":"2403.12031","title":"RouterBench: A Benchmark for Multi-LLM Routing System","created":"2024-03-18","cited_by_count":238},{"id":"1704.05179","title":"SearchQA: A New Q&A Dataset Augmented with Context from a Search Engine","created":"2017-04-18","cited_by_count":225},{"id":"2104.08671","title":"When Does Pretraining Help? Assessing Self-Supervised Learning for Law and the CaseHOLD Dataset","created":"2021-04-18","cited_by_count":201},{"id":"1710.06481","title":"Constructing Datasets for Multi-hop Reading Comprehension Across Documents","created":"2017-10-17","cited_by_count":190},{"id":"2410.03834","title":"GraphRouter: A Graph-based Router for LLM Selections","created":"2024-10-04","cited_by_count":165},{"id":"2308.06077","title":"Fly-Swat or Cannon? Cost-Effective Language Model Choice via Meta-Modeling","created":"2023-08-11","cited_by_count":95},{"id":"2409.19886","title":"RouterDC: Query-Based Router by Dual Contrastive Learning for Assembling Large Language Models","created":"2024-09-30","cited_by_count":88},{"id":"2502.08773","title":"Universal Model Routing for Efficient LLM Inference","created":"2025-02-12","cited_by_count":86},{"id":"2506.09033","title":"Router-R1: Teaching LLMs Multi-Round Routing and Aggregation via Reinforcement Learning","created":"2025-06-10","cited_by_count":72},{"id":"2506.01048","title":"IRT-Router: Effective and Interpretable Multi-LLM Routing via Item Response Theory","created":"2025-06-01","cited_by_count":40},{"id":"2502.03261","title":"CARROT: A Cost Aware Rate Optimal Router","created":"2025-02-05","cited_by_count":39},{"id":"2601.07206","title":"LLMRouterBench: A Massive Benchmark and Unified Framework for LLM Routing","created":"2026-01-12","cited_by_count":38},{"id":"1904.04792","title":"Quizbowl: The Case for Incremental Question Answering","created":"2019-04-09","cited_by_count":36},{"id":"2409.15518","title":"Eagle: Efficient Training-Free Router for Multi-LLM Inference","created":"2024-09-23","cited_by_count":35},{"id":"2508.12631","title":"Beyond GPT-5: Making LLMs Cheaper and Better via Performance-Efficiency Optimized Routing","created":"2025-08-18","cited_by_count":34},{"id":"2502.14855","title":"Prompt-to-Leaderboard","created":"2025-02-20","cited_by_count":30},{"id":"2510.00202","title":"RouterArena: An Open Platform for Comprehensive Comparison of LLM Routers","created":"2025-09-30","cited_by_count":22},{"id":"2505.19970","title":"CP-Router: An Uncertainty-Aware Router Between LLM and LRM","created":"2025-05-26","cited_by_count":20},{"id":"2602.02823","title":"R2-Router: A New Paradigm for LLM Routing with Reasoning","created":"2026-02-02","cited_by_count":14},{"id":"2509.02718","title":"Efficient Training-Free Online Routing for High-Volume Multi-LLM Serving","created":"2025-09-02","cited_by_count":13},{"id":"2505.12601","title":"Rethinking Predictive Modeling for LLM Routing: When Simple kNN Beats Complex Learned Routers","created":"2025-05-19","cited_by_count":11},{"id":"2602.03478","title":"When Routing Collapses: On the Degenerate Convergence of LLM Routers","created":"2026-02-03","cited_by_count":10},{"id":"2505.19947","title":"MESS+: Dynamically Learned Inference-Time LLM Routing in Model Zoos with Service Level Guarantees","created":"2025-05-26","cited_by_count":9}],"next_cursor":null}