{"list":"other","total":87,"rows":[{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"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":"1905.07830","title":"HellaSwag: Can a Machine Really Finish Your Sentence?","created":"2019-05-19","cited_by_count":4100},{"id":"2307.03172","title":"Lost in the Middle: How Language Models Use Long Contexts","created":"2023-07-06","cited_by_count":3455},{"id":"2004.05150","title":"Longformer: The Long-Document Transformer","created":"2020-04-10","cited_by_count":3413},{"id":"2310.06770","title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","created":"2023-10-10","cited_by_count":3373},{"id":"2109.07958","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","created":"2021-09-08","cited_by_count":2975},{"id":"1911.11641","title":"PIQA: Reasoning about Physical Commonsense in Natural Language","created":"2019-11-26","cited_by_count":2883},{"id":"2202.05262","title":"Locating and Editing Factual Associations in GPT","created":"2022-02-10","cited_by_count":2691},{"id":"2307.08691","title":"FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning","created":"2023-07-17","cited_by_count":2598},{"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":"2409.19256","title":"HybridFlow: A Flexible and Efficient RLHF Framework","created":"2024-09-28","cited_by_count":2057},{"id":"1909.01066","title":"Language Models as Knowledge Bases?","created":"2019-09-03","cited_by_count":1936},{"id":"1901.02860","title":"Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context","created":"2019-01-09","cited_by_count":1850},{"id":"1811.00937","title":"CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge","created":"2018-11-02","cited_by_count":1822},{"id":"2210.09261","title":"Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them","created":"2022-10-17","cited_by_count":1807},{"id":"2002.05202","title":"GLU Variants Improve Transformer","created":"2020-02-12","cited_by_count":1804},{"id":"1905.00537","title":"SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems","created":"2019-05-02","cited_by_count":1729},{"id":"1904.10509","title":"Generating Long Sequences with Sparse Transformers","created":"2019-04-23","cited_by_count":1546},{"id":"1910.07467","title":"Root Mean Square Layer Normalization","created":"2019-10-16","cited_by_count":1480},{"id":"2202.12837","title":"Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?","created":"2022-02-25","cited_by_count":1434},{"id":"2308.14508","title":"LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding","created":"2023-08-28","cited_by_count":1417},{"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":"2305.13245","title":"GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints","created":"2023-05-22","cited_by_count":1346},{"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":"2012.14913","title":"Transformer Feed-Forward Layers Are Key-Value Memories","created":"2020-12-29","cited_by_count":1336},{"id":"2112.04426","title":"Improving language models by retrieving from trillions of tokens","created":"2021-12-08","cited_by_count":1293},{"id":"2108.12409","title":"Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation","created":"2021-08-27","cited_by_count":1103},{"id":"1905.05950","title":"BERT Rediscovers the Classical NLP Pipeline","created":"2019-05-15","cited_by_count":1059},{"id":"1606.06031","title":"The LAMBADA dataset: Word prediction requiring a broad discourse context","created":"2016-06-20","cited_by_count":992},{"id":"1905.09418","title":"Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned","created":"2019-05-23","cited_by_count":856},{"id":"1707.06209","title":"Crowdsourcing Multiple Choice Science Questions","created":"2017-07-19","cited_by_count":765},{"id":"2306.15595","title":"Extending Context Window of Large Language Models via Positional Interpolation","created":"2023-06-27","cited_by_count":740},{"id":"1911.05507","title":"Compressive Transformers for Long-Range Sequence Modelling","created":"2019-11-13","cited_by_count":726},{"id":"2002.08910","title":"How Much Knowledge Can You Pack Into the Parameters of a Language Model?","created":"2020-02-10","cited_by_count":719},{"id":"2309.00071","title":"YaRN: Efficient Context Window Extension of Large Language Models","created":"2023-08-31","cited_by_count":601},{"id":"1808.09121","title":"WiC: the Word-in-Context Dataset for Evaluating Context-Sensitive Meaning Representations","created":"2018-08-28","cited_by_count":372},{"id":"2402.13718","title":"$\\infty$Bench: Extending Long Context Evaluation Beyond 100K Tokens","created":"2024-02-21","cited_by_count":367},{"id":"2306.03091","title":"RepoBench: Benchmarking Repository-Level Code Auto-Completion Systems","created":"2023-06-05","cited_by_count":353},{"id":"2402.13753","title":"LongRoPE: Extending LLM Context Window Beyond 2 Million Tokens","created":"2024-02-21","cited_by_count":313},{"id":"2309.16039","title":"Effective Long-Context Scaling of Foundation Models","created":"2023-09-27","cited_by_count":303},{"id":"2003.12298","title":"Information-Theoretic Probing with Minimum Description Length","created":"2020-03-27","cited_by_count":232},{"id":"2404.15574","title":"Retrieval Head Mechanistically Explains Long-Context Factuality","created":"2024-04-24","cited_by_count":232},{"id":"2004.08249","title":"Understanding the Difficulty of Training Transformers","created":"2020-04-17","cited_by_count":210},{"id":"1810.12885","title":"ReCoRD: Bridging the Gap between Human and Machine Commonsense Reading Comprehension","created":"2018-10-30","cited_by_count":200},{"id":"2404.07143","title":"Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention","created":"2024-04-10","cited_by_count":200},{"id":"2402.10171","title":"Data Engineering for Scaling Language Models to 128K Context","created":"2024-02-15","cited_by_count":186},{"id":"2101.12176","title":"On the Origin of Implicit Regularization in Stochastic Gradient Descent","created":"2021-01-28","cited_by_count":184},{"id":"2009.11162","title":"Implicit Gradient Regularization","created":"2020-09-23","cited_by_count":146},{"id":"2306.15063","title":"Pretraining task diversity and the emergence of non-Bayesian in-context learning for regression","created":"2023-06-26","cited_by_count":146},{"id":"2410.02660","title":"How to Train Long-Context Language Models (Effectively)","created":"2024-10-03","cited_by_count":146},{"id":"2407.07071","title":"Lookback Lens: Detecting and Mitigating Contextual Hallucinations in Large Language Models Using Only Attention Maps","created":"2024-07-09","cited_by_count":142},{"id":"2206.03126","title":"Signal Propagation in Transformers: Theoretical Perspectives and the Role of Rank Collapse","created":"2022-06-07","cited_by_count":141},{"id":"2402.18154","title":"Cutting Off the Head Ends the Conflict: A Mechanism for Interpreting and Mitigating Knowledge Conflicts in Language Models","created":"2024-02-28","cited_by_count":91},{"id":"1802.07044","title":"The Description Length of Deep Learning Models","created":"2018-02-20","cited_by_count":72},{"id":"2410.18745","title":"Why Does the Effective Context Length of LLMs Fall Short?","created":"2024-10-24","cited_by_count":63},{"id":"2006.16362","title":"Multi-Head Attention: Collaborate Instead of Concatenate","created":"2020-06-29","cited_by_count":60},{"id":"1908.11365","title":"Improving Deep Transformer with Depth-Scaled Initialization and Merged Attention","created":"2019-08-29","cited_by_count":59},{"id":"2403.12958","title":"Dated Data: Tracing Knowledge Cutoffs in Large Language Models","created":"2024-03-19","cited_by_count":51},{"id":"2210.05675","title":"Transformers generalize differently from information stored in context vs in weights","created":"2022-10-11","cited_by_count":49},{"id":"2306.04050","title":"LLMZip: Lossless Text Compression using Large Language Models","created":"2023-06-06","cited_by_count":44},{"id":"2407.06645","title":"Entropy Law: The Story Behind Data Compression and LLM Performance","created":"2024-07-09","cited_by_count":44},{"id":"2402.18819","title":"Dual Operating Modes of In-Context Learning","created":"2024-02-29","cited_by_count":43},{"id":"2209.13083","title":"Why neural networks find simple solutions: the many regularizers of geometric complexity","created":"2022-09-27","cited_by_count":39},{"id":"1908.08484","title":"Minimum Description Length Revisited","created":"2019-08-21","cited_by_count":37},{"id":"2405.13226","title":"Dataset Decomposition: Faster LLM Training with Variable Sequence Length Curriculum","created":"2024-05-21","cited_by_count":26},{"id":"2203.15955","title":"Investigating the Properties of Neural Network Representations in Reinforcement Learning","created":"2022-03-30","cited_by_count":24},{"id":"2501.12766","title":"NExtLong: Toward Effective Long-Context Training without Long Documents","created":"2025-01-22","cited_by_count":20},{"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":"2409.17141","title":"FineZip : Pushing the Limits of Large Language Models for Practical Lossless Text Compression","created":"2024-09-25","cited_by_count":18},{"id":"2406.00053","title":"Dual Process Learning: Controlling Use of In-Context vs. In-Weights Strategies with Weight Forgetting","created":"2024-05-28","cited_by_count":15},{"id":"2502.01481","title":"Intrinsic Entropy of Context Length Scaling in LLMs","created":"2025-02-03","cited_by_count":14},{"id":"2502.07365","title":"LongReD: Mitigating Short-Text Degradation of Long-Context Large Language Models via Restoration Distillation","created":"2025-02-11","cited_by_count":14},{"id":"2210.07931","title":"Sequential Learning Of Neural Networks for Prequential MDL","created":"2022-10-14","cited_by_count":13},{"id":"2310.00576","title":"GrowLength: Accelerating LLMs Pretraining by Progressively Growing Training Length","created":"2023-10-01","cited_by_count":11},{"id":"2503.02502","title":"LADM: Long-context Training Data Selection with Attention-based Dependency Measurement for LLMs","created":"2025-03-04","cited_by_count":11},{"id":"2411.01101","title":"Self-Consistency Falls Short! The Adverse Effects of Positional Bias on Long-Context Problems","created":"2024-11-02","cited_by_count":7},{"id":"2412.16642","title":"L3TC: Leveraging RWKV for Learned Lossless Low-Complexity Text Compression","created":"2024-12-21","cited_by_count":7},{"id":"2505.18148","title":"Hidden in the Haystack: Smaller Needles are More Difficult for LLMs to Find","created":"2025-05-23","cited_by_count":7},{"id":"2503.15450","title":"SkyLadder: Better and Faster Pretraining via Context Window Scheduling","created":"2025-03-19","cited_by_count":6},{"id":"2409.04318","title":"Learning vs Retrieval: The Role of In-Context Examples in Regression with Large Language Models","created":"2024-09-06","cited_by_count":5},{"id":"2504.19395","title":"ICL CIPHERS: Quantifying \"Learning\" in In-Context Learning via Substitution Ciphers","created":"2025-04-28","cited_by_count":4}],"next_cursor":null}