{"list":"other","total":51,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"id":"2101.00027","title":"The Pile: An 800GB Dataset of Diverse Text for Language Modeling","created":"2020-12-31","cited_by_count":2411},{"id":"1610.05820","title":"Membership Inference Attacks against Machine Learning Models","created":"2016-10-18","cited_by_count":2281},{"id":"2012.07805","title":"Extracting Training Data from Large Language Models","created":"2020-12-14","cited_by_count":2189},{"id":"2304.01373","title":"Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling","created":"2023-04-03","cited_by_count":1786},{"id":"1911.11763","title":"SuperGlue: Learning Feature Matching with Graph Neural Networks","created":"2019-11-26","cited_by_count":1443},{"id":"2012.14913","title":"Transformer Feed-Forward Layers Are Key-Value Memories","created":"2020-12-29","cited_by_count":1336},{"id":"2004.06165","title":"Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks","created":"2020-04-13","cited_by_count":1214},{"id":"2004.04696","title":"BLEURT: Learning Robust Metrics for Text Generation","created":"2020-04-09","cited_by_count":1203},{"id":"2112.03570","title":"Membership Inference Attacks From First Principles","created":"2021-12-07","cited_by_count":878},{"id":"2201.02177","title":"Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets","created":"2022-01-06","cited_by_count":629},{"id":"2402.00838","title":"OLMo: Accelerating the Science of Language Models","created":"2024-02-01","cited_by_count":613},{"id":"2304.14767","title":"Dissecting Recall of Factual Associations in Auto-Regressive Language Models","created":"2023-04-28","cited_by_count":528},{"id":"2104.08758","title":"Documenting Large Webtext Corpora: A Case Study on the Colossal Clean Crawled Corpus","created":"2021-04-18","cited_by_count":492},{"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":"2305.18462","title":"Membership Inference Attacks against Language Models via Neighbourhood Comparison","created":"2023-05-29","cited_by_count":258},{"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":"2311.04850","title":"Rethinking Benchmark and Contamination for Language Models with Rephrased Samples","created":"2023-11-08","cited_by_count":195},{"id":"2311.01964","title":"Don't Make Your LLM an Evaluation Benchmark Cheater","created":"2023-11-03","cited_by_count":194},{"id":"2406.04244","title":"Benchmark Data Contamination of Large Language Models: A Survey","created":"2024-06-06","cited_by_count":147},{"id":"2305.10160","title":"Stop Uploading Test Data in Plain Text: Practical Strategies for Mitigating Data Contamination by Evaluation Benchmarks","created":"2023-05-17","cited_by_count":142},{"id":"2310.19341","title":"Skywork: A More Open Bilingual Foundation Model","created":"2023-10-30","cited_by_count":112},{"id":"2312.16337","title":"Task Contamination: Language Models May Not Be Few-Shot Anymore","created":"2023-12-26","cited_by_count":99},{"id":"2204.08110","title":"Language Contamination Helps Explain the Cross-lingual Capabilities of English Pretrained Models","created":"2022-04-17","cited_by_count":92},{"id":"2401.06059","title":"Investigating Data Contamination for Pre-training Language Models","created":"2024-01-11","cited_by_count":91},{"id":"2402.09910","title":"DE-COP: Detecting Copyrighted Content in Language Models Training Data","created":"2024-02-15","cited_by_count":74},{"id":"2403.04811","title":"Quantifying Contamination in Evaluating Code Generation Capabilities of Language Models","created":"2024-03-06","cited_by_count":65},{"id":"2303.12767","title":"Can we trust the evaluation on ChatGPT?","created":"2023-03-22","cited_by_count":63},{"id":"2210.03588","title":"Understanding Transformer Memorization Recall Through Idioms","created":"2022-10-07","cited_by_count":62},{"id":"1905.13453","title":"MultiQA: An Empirical Investigation of Generalization and Transfer in Reading Comprehension","created":"2019-05-31","cited_by_count":60},{"id":"2102.10073","title":"Pyserini: An Easy-to-Use Python Toolkit to Support Replicable IR Research with Sparse and Dense Representations","created":"2021-02-19","cited_by_count":60},{"id":"2312.12343","title":"LatestEval: Addressing Data Contamination in Language Model Evaluation through Dynamic and Time-Sensitive Test Construction","created":"2023-12-19","cited_by_count":58},{"id":"2309.10677","title":"Estimating Contamination via Perplexity: Quantifying Memorisation in Language Model Evaluation","created":"2023-09-19","cited_by_count":48},{"id":"2310.10628","title":"Data Contamination Through the Lens of Time","created":"2023-10-16","cited_by_count":40},{"id":"2309.08632","title":"Pretraining on the Test Set Is All You Need","created":"2023-09-13","cited_by_count":33},{"id":"2302.14035","title":"The ROOTS Search Tool: Data Transparency for LLMs","created":"2023-02-27","cited_by_count":31},{"id":"2402.02823","title":"Evading Data Contamination Detection for Language Models is (too) Easy","created":"2024-02-05","cited_by_count":30},{"id":"2401.10463","title":"Critical Data Size of Language Models from a Grokking Perspective","created":"2024-01-19","cited_by_count":24},{"id":"2405.11930","title":"Data Contamination Calibration for Black-box LLMs","created":"2024-05-20","cited_by_count":24},{"id":"2402.08100","title":"Investigating the Impact of Data Contamination of Large Language Models in Text-to-SQL Translation","created":"2024-02-12","cited_by_count":21},{"id":"2203.16639","title":"FALCON: Fast Visual Concept Learning by Integrating Images, Linguistic descriptions, and Conceptual Relations","created":"2022-03-30","cited_by_count":20},{"id":"2403.06644","title":"Elephants Never Forget: Testing Language Models for Memorization of Tabular Data","created":"2024-03-11","cited_by_count":19},{"id":"2306.01481","title":"GAIA Search: Hugging Face and Pyserini Interoperability for NLP Training Data Exploration","created":"2023-06-02","cited_by_count":8}],"next_cursor":null}