{"list":"other","total":87,"rows":[{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"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":"1905.07830","title":"HellaSwag: Can a Machine Really Finish Your Sentence?","created":"2019-05-19","cited_by_count":4100},{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"2109.07958","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","created":"2021-09-08","cited_by_count":2975},{"id":"1612.00837","title":"Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering","created":"2016-12-02","cited_by_count":2516},{"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":"2311.16502","title":"MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI","created":"2023-11-27","cited_by_count":2080},{"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":"1905.00537","title":"SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems","created":"2019-05-02","cited_by_count":1729},{"id":"1904.08920","title":"Towards VQA Models That Can Read","created":"2019-04-18","cited_by_count":1718},{"id":"2310.02255","title":"MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts","created":"2023-10-03","cited_by_count":1614},{"id":"1902.10811","title":"Do ImageNet Classifiers Generalize to ImageNet?","created":"2019-02-13","cited_by_count":1515},{"id":"2203.10244","title":"ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning","created":"2022-03-19","cited_by_count":1479},{"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":"2007.00398","title":"DocVQA: A Dataset for VQA on Document Images","created":"2020-07-01","cited_by_count":1317},{"id":"2308.02490","title":"MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities","created":"2023-08-04","cited_by_count":1239},{"id":"2004.12832","title":"ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT","created":"2020-04-27","cited_by_count":1178},{"id":"1906.00067","title":"OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge","created":"2019-05-31","cited_by_count":1121},{"id":"1511.02283","title":"Generation and Comprehension of Unambiguous Object Descriptions","created":"2015-11-07","cited_by_count":904},{"id":"1802.08218","title":"VizWiz Grand Challenge: Answering Visual Questions from Blind People","created":"2018-02-22","cited_by_count":858},{"id":"2310.03714","title":"DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines","created":"2023-10-05","cited_by_count":832},{"id":"2108.13264","title":"Deep Reinforcement Learning at the Edge of the Statistical Precipice","created":"2021-08-30","cited_by_count":807},{"id":"1603.07396","title":"A Diagram Is Worth A Dozen Images","created":"2016-03-24","cited_by_count":804},{"id":"2003.11080","title":"XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalization","created":"2020-03-24","cited_by_count":742},{"id":"2206.01718","title":"A-OKVQA: A Benchmark for Visual Question Answering using World Knowledge","created":"2022-06-03","cited_by_count":710},{"id":"2304.14108","title":"DataComp: In search of the next generation of multimodal datasets","created":"2023-04-27","cited_by_count":644},{"id":"1712.07040","title":"The NarrativeQA Reading Comprehension Challenge","created":"2017-12-19","cited_by_count":597},{"id":"2304.15004","title":"Are Emergent Abilities of Large Language Models a Mirage?","created":"2023-04-28","cited_by_count":523},{"id":"2406.11939","title":"From Crowdsourced Data to High-Quality Benchmarks: Arena-Hard and BenchBuilder Pipeline","created":"2024-06-17","cited_by_count":500},{"id":"2005.04790","title":"The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes","created":"2020-05-10","cited_by_count":490},{"id":"2405.01535","title":"Prometheus 2: An Open Source Language Model Specialized in Evaluating Other Language Models","created":"2024-05-02","cited_by_count":446},{"id":"1812.08658","title":"nocaps: novel object captioning at scale","created":"2018-12-20","cited_by_count":444},{"id":"2003.12462","title":"TextCaps: a Dataset for Image Captioning with Reading Comprehension","created":"2020-03-24","cited_by_count":400},{"id":"2006.07159","title":"Are we done with ImageNet?","created":"2020-06-12","cited_by_count":333},{"id":"2402.14992","title":"tinyBenchmarks: evaluating LLMs with fewer examples","created":"2024-02-22","cited_by_count":310},{"id":"2110.08420","title":"Understanding Dataset Difficulty with $\\mathcal{V}$-Usable Information","created":"2021-10-16","cited_by_count":291},{"id":"2110.13214","title":"IconQA: A New Benchmark for Abstract Diagram Understanding and Visual Language Reasoning","created":"2021-10-25","cited_by_count":267},{"id":"1806.08730","title":"The Natural Language Decathlon: Multitask Learning as Question Answering","created":"2018-06-20","cited_by_count":236},{"id":"2203.08242","title":"Data Contamination: From Memorization to Exploitation","created":"2022-03-15","cited_by_count":236},{"id":"2104.02145","title":"What Will it Take to Fix Benchmarking in Natural Language Understanding?","created":"2021-04-05","cited_by_count":203},{"id":"2304.04370","title":"OpenAGI: When LLM Meets Domain Experts","created":"2023-04-10","cited_by_count":197},{"id":"2111.10952","title":"ExT5: Towards Extreme Multi-Task Scaling for Transfer Learning","created":"2021-11-22","cited_by_count":161},{"id":"1711.08536","title":"No Classification without Representation: Assessing Geodiversity Issues in Open Data Sets for the Developing World","created":"2017-11-22","cited_by_count":153},{"id":"2204.08790","title":"ELEVATER: A Benchmark and Toolkit for Evaluating Language-Augmented Visual Models","created":"2022-04-19","cited_by_count":141},{"id":"2107.07002","title":"The Benchmark Lottery","created":"2021-07-14","cited_by_count":136},{"id":"2311.03287","title":"Holistic Analysis of Hallucination in GPT-4V(ision): Bias and Interference Challenges","created":"2023-11-06","cited_by_count":131},{"id":"1505.02288","title":"Should we really use post-hoc tests based on mean-ranks?","created":"2015-05-09","cited_by_count":116},{"id":"2311.16101","title":"How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMs","created":"2023-11-27","cited_by_count":108},{"id":"2205.12522","title":"Crossmodal-3600: A Massively Multilingual Multimodal Evaluation Dataset","created":"2022-05-25","cited_by_count":100},{"id":"2309.08638","title":"Anchor Points: Benchmarking Models with Much Fewer Examples","created":"2023-09-14","cited_by_count":86},{"id":"2103.05331","title":"Active Testing: Sample-Efficient Model Evaluation","created":"2021-03-09","cited_by_count":82},{"id":"2402.19450","title":"Functional Benchmarks for Robust Evaluation of Reasoning Performance, and the Reasoning Gap","created":"2024-02-29","cited_by_count":79},{"id":"2402.11443","title":"Benchmark Self-Evolving: A Multi-Agent Framework for Dynamic LLM Evaluation","created":"2024-02-18","cited_by_count":75},{"id":"2404.04125","title":"No \"Zero-Shot\" Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performance","created":"2024-04-04","cited_by_count":75},{"id":"2203.04592","title":"Mapping global dynamics of benchmark creation and saturation in artificial intelligence","created":"2022-03-09","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":"2310.17567","title":"Skill-Mix: a Flexible and Expandable Family of Evaluations for AI models","created":"2023-10-26","cited_by_count":64},{"id":"2311.17295","title":"Elo Uncovered: Robustness and Best Practices in Language Model Evaluation","created":"2023-11-29","cited_by_count":61},{"id":"2408.14339","title":"ConceptMix: A Compositional Image Generation Benchmark with Controllable Difficulty","created":"2024-08-26","cited_by_count":61},{"id":"2402.05779","title":"Examining Gender and Racial Bias in Large Vision-Language Models Using a Novel Dataset of Parallel Images","created":"2024-02-08","cited_by_count":55},{"id":"2403.19114","title":"Top Leaderboard Ranking = Top Coding Proficiency, Always? EvoEval: Evolving Coding Benchmarks via LLM","created":"2024-03-28","cited_by_count":40},{"id":"2407.16711","title":"Benchmarks as Microscopes: A Call for Model Metrology","created":"2024-07-22","cited_by_count":35},{"id":"2407.07890","title":"Training on the Test Task Confounds Evaluation and Emergence","created":"2024-07-10","cited_by_count":34},{"id":"2112.01589","title":"InfoLM: A New Metric to Evaluate Summarization & Data2Text Generation","created":"2021-12-02","cited_by_count":33},{"id":"2110.10746","title":"Better than Average: Paired Evaluation of NLP Systems","created":"2021-10-20","cited_by_count":30},{"id":"2405.01719","title":"Inherent Trade-Offs between Diversity and Stability in Multi-Task Benchmarks","created":"2024-05-02","cited_by_count":28},{"id":"2106.05532","title":"How Robust are Model Rankings: A Leaderboard Customization Approach for Equitable Evaluation","created":"2021-06-10","cited_by_count":24},{"id":"2406.04551","title":"Improving Geo-diversity of Generated Images with Contextualized Vendi Score Guidance","created":"2024-06-06","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":"2411.18674","title":"Active Data Curation Effectively Distills Large-Scale Multimodal Models","created":"2024-11-27","cited_by_count":19},{"id":"2002.06532","title":"Active Bayesian Assessment for Black-Box Classifiers","created":"2020-02-16","cited_by_count":17},{"id":"2203.03073","title":"ILDAE: Instance-Level Difficulty Analysis of Evaluation Data","created":"2022-03-07","cited_by_count":17},{"id":"2408.03573","title":"AcTracer: Active Testing of Large Language Model via Multi-Stage Sampling","created":"2024-08-07","cited_by_count":17},{"id":"2305.10284","title":"Towards More Robust NLP System Evaluation: Handling Missing Scores in Benchmarks","created":"2023-05-17","cited_by_count":14},{"id":"2404.02112","title":"ImageNot: A contrast with ImageNet preserves model rankings","created":"2024-04-02","cited_by_count":14},{"id":"2402.09766","title":"From Variability to Stability: Advancing RecSys Benchmarking Practices","created":"2024-02-15","cited_by_count":12},{"id":"2403.16379","title":"FlashEval: Towards Fast and Accurate Evaluation of Text-to-image Diffusion Generative Models","created":"2024-03-25","cited_by_count":11},{"id":"1406.6618","title":"When is it Better to Compare than to Score?","created":"2014-06-25","cited_by_count":9},{"id":"2112.01342","title":"How not to Lie with a Benchmark: Rearranging NLP Leaderboards","created":"2021-12-02","cited_by_count":9},{"id":"2306.02821","title":"A unified analysis of likelihood-based estimators in the Plackett--Luce model","created":"2023-06-05","cited_by_count":9},{"id":"2301.01269","title":"Average Is Not Enough: Caveats of Multilingual Evaluation","created":"2023-01-03","cited_by_count":5},{"id":"2302.08572","title":"Towards Reliable Assessments of Demographic Disparities in Multi-Label Image Classifiers","created":"2023-02-16","cited_by_count":5},{"id":"2307.04532","title":"Read, Look or Listen? What's Needed for Solving a Multimodal Dataset","created":"2023-07-06","cited_by_count":2}],"next_cursor":null}