{"list":"other","total":55,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"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":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"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":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"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":"2307.03172","title":"Lost in the Middle: How Language Models Use Long Contexts","created":"2023-07-06","cited_by_count":3455},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"1705.03551","title":"TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension","created":"2017-05-09","cited_by_count":2955},{"id":"1911.11641","title":"PIQA: Reasoning about Physical Commonsense in Natural Language","created":"2019-11-26","cited_by_count":2883},{"id":"2307.08691","title":"FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning","created":"2023-07-17","cited_by_count":2598},{"id":"2309.17453","title":"Efficient Streaming Language Models with Attention Sinks","created":"2023-09-29","cited_by_count":2186},{"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":"1811.00937","title":"CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge","created":"2018-11-02","cited_by_count":1822},{"id":"2404.06654","title":"RULER: What's the Real Context Size of Your Long-Context Language Models?","created":"2024-04-09","cited_by_count":1346},{"id":"2112.09118","title":"Unsupervised Dense Information Retrieval with Contrastive Learning","created":"2021-12-16","cited_by_count":1216},{"id":"1704.04683","title":"RACE: Large-scale ReAding Comprehension Dataset From Examinations","created":"2017-04-15","cited_by_count":861},{"id":"2305.06161","title":"StarCoder: may the source be with you!","created":"2023-05-09","cited_by_count":799},{"id":"2306.15595","title":"Extending Context Window of Large Language Models via Positional Interpolation","created":"2023-06-27","cited_by_count":740},{"id":"1506.01186","title":"Cyclical Learning Rates for Training Neural Networks","created":"2015-06-03","cited_by_count":629},{"id":"2401.02385","title":"TinyLlama: An Open-Source Small Language Model","created":"2024-01-04","cited_by_count":618},{"id":"2309.00071","title":"YaRN: Efficient Context Window Extension of Large Language Models","created":"2023-08-31","cited_by_count":601},{"id":"2406.15877","title":"BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions","created":"2024-06-22","cited_by_count":546},{"id":"2305.19466","title":"The Impact of Positional Encoding on Length Generalization in Transformers","created":"2023-05-31","cited_by_count":327},{"id":"2309.16039","title":"Effective Long-Context Scaling of Foundation Models","created":"2023-09-27","cited_by_count":303},{"id":"2112.08608","title":"QuALITY: Question Answering with Long Input Texts, Yes!","created":"2021-12-16","cited_by_count":208},{"id":"2410.10781","title":"When Attention Sink Emerges in Language Models: An Empirical View","created":"2024-10-14","cited_by_count":208},{"id":"2402.10171","title":"Data Engineering for Scaling Language Models to 128K Context","created":"2024-02-15","cited_by_count":186},{"id":"2410.02660","title":"How to Train Long-Context Language Models (Effectively)","created":"2024-10-03","cited_by_count":146},{"id":"2401.01325","title":"LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning","created":"2024-01-02","cited_by_count":136},{"id":"2410.02694","title":"HELMET: How to Evaluate Long-Context Language Models Effectively and Thoroughly","created":"2024-10-03","cited_by_count":125},{"id":"2406.08446","title":"OLMES: A Standard for Language Model Evaluations","created":"2024-06-12","cited_by_count":106},{"id":"2310.10638","title":"In-context Pretraining: Language Modeling Beyond Document Boundaries","created":"2023-10-16","cited_by_count":79},{"id":"2410.18745","title":"Why Does the Effective Context Length of LLMs Fall Short?","created":"2024-10-24","cited_by_count":63},{"id":"2405.14591","title":"Base of RoPE Bounds Context Length","created":"2024-05-23","cited_by_count":52},{"id":"2409.17115","title":"Programming Every Example: Lifting Pre-training Data Quality Like Experts at Scale","created":"2024-09-25","cited_by_count":37},{"id":"2108.06084","title":"The Stability-Efficiency Dilemma: Investigating Sequence Length Warmup for Training GPT Models","created":"2021-08-13","cited_by_count":36},{"id":"2404.10830","title":"Fewer Truncations Improve Language Modeling","created":"2024-04-16","cited_by_count":35},{"id":"2405.13226","title":"Dataset Decomposition: Faster LLM Training with Variable Sequence Length Curriculum","created":"2024-05-21","cited_by_count":26},{"id":"2409.12181","title":"A Controlled Study on Long Context Extension and Generalization in LLMs","created":"2024-09-18","cited_by_count":26},{"id":"2412.16545","title":"Attention Entropy is a Key Factor: An Analysis of Parallel Context Encoding with Full-attention-based Pre-trained Language Models","created":"2024-12-21","cited_by_count":26},{"id":"2402.13991","title":"Analysing The Impact of Sequence Composition on Language Model Pre-Training","created":"2024-02-21","cited_by_count":25},{"id":"1711.05345","title":"Supervised and Unsupervised Transfer Learning for Question Answering","created":"2017-11-14","cited_by_count":24},{"id":"1608.06378","title":"Towards Machine Comprehension of Spoken Content: Initial TOEFL Listening Comprehension Test by Machine","created":"2016-08-23","cited_by_count":23},{"id":"2406.00605","title":"LongSkywork: A Training Recipe for Efficiently Extending Context Length in Large Language Models","created":"2024-06-02","cited_by_count":19},{"id":"2411.13476","title":"When Precision Meets Position: BFloat16 Breaks Down RoPE in Long-Context Training","created":"2024-11-20","cited_by_count":15},{"id":"2011.03138","title":"Semi-supervised URL Segmentation with Recurrent Neural Networks Pre-trained on Knowledge Graph Entities","created":"2020-11-05","cited_by_count":11},{"id":"2310.00576","title":"GrowLength: Accelerating LLMs Pretraining by Progressively Growing Training Length","created":"2023-10-01","cited_by_count":11}],"next_cursor":null}