{"list":"other","total":75,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"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":"1612.00796","title":"Overcoming catastrophic forgetting in neural networks","created":"2016-12-02","cited_by_count":4787},{"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":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"2307.03172","title":"Lost in the Middle: How Language Models Use Long Contexts","created":"2023-07-06","cited_by_count":3455},{"id":"2403.05530","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","created":"2024-03-08","cited_by_count":3224},{"id":"1704.05426","title":"A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference","created":"2017-04-18","cited_by_count":2682},{"id":"1509.01626","title":"Character-level Convolutional Networks for Text Classification","created":"2015-09-04","cited_by_count":2330},{"id":"1905.10044","title":"BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions","created":"2019-05-24","cited_by_count":2183},{"id":"2206.04615","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","created":"2022-06-09","cited_by_count":1998},{"id":"2308.14508","title":"LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding","created":"2023-08-28","cited_by_count":1417},{"id":"1803.05355","title":"FEVER: a large-scale dataset for Fact Extraction and VERification","created":"2018-03-14","cited_by_count":1375},{"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":"1805.12471","title":"Neural Network Acceptability Judgments","created":"2018-05-31","cited_by_count":958},{"id":"2205.05638","title":"Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning","created":"2022-05-11","cited_by_count":896},{"id":"2307.04657","title":"BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Dataset","created":"2023-07-10","cited_by_count":860},{"id":"2302.00093","title":"Large Language Models Can Be Easily Distracted by Irrelevant Context","created":"2023-01-31","cited_by_count":841},{"id":"2405.01470","title":"WildChat: 1M ChatGPT Interaction Logs in the Wild","created":"2024-05-02","cited_by_count":629},{"id":"2310.01889","title":"Ring Attention with Blockwise Transformers for Near-Infinite Context","created":"2023-10-03","cited_by_count":457},{"id":"2311.17035","title":"Scalable Extraction of Training Data from (Production) Language Models","created":"2023-11-28","cited_by_count":434},{"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":"1705.00648","title":"\"Liar, Liar Pants on Fire\": A New Benchmark Dataset for Fake News Detection","created":"2017-05-01","cited_by_count":363},{"id":"2308.11462","title":"LegalBench: A Collaboratively Built Benchmark for Measuring Legal Reasoning in Large Language Models","created":"2023-08-20","cited_by_count":336},{"id":"1808.09602","title":"Multi-Task Identification of Entities, Relations, and Coreference for Scientific Knowledge Graph Construction","created":"2018-08-29","cited_by_count":322},{"id":"1502.05698","title":"Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks","created":"2015-02-19","cited_by_count":314},{"id":"1307.5336","title":"Good Debt or Bad Debt: Detecting Semantic Orientations in Economic Texts","created":"2013-07-19","cited_by_count":310},{"id":"2404.02060","title":"Long-context LLMs Struggle with Long In-context Learning","created":"2024-04-02","cited_by_count":286},{"id":"2305.14160","title":"Label Words are Anchors: An Information Flow Perspective for Understanding In-Context Learning","created":"2023-05-23","cited_by_count":236},{"id":"2404.16789","title":"Continual Learning of Large Language Models: A Comprehensive Survey","created":"2024-04-25","cited_by_count":234},{"id":"2103.08541","title":"Get Your Vitamin C! Robust Fact Verification with Contrastive Evidence","created":"2021-03-15","cited_by_count":225},{"id":"2010.09926","title":"Explainable Automated Fact-Checking for Public Health Claims","created":"2020-10-19","cited_by_count":211},{"id":"2404.11018","title":"Many-Shot In-Context Learning","created":"2024-04-17","cited_by_count":206},{"id":"1809.04444","title":"Hate Speech Dataset from a White Supremacy Forum","created":"2018-09-12","cited_by_count":198},{"id":"2402.08268","title":"World Model on Million-Length Video And Language With Blockwise RingAttention","created":"2024-02-13","cited_by_count":198},{"id":"2012.00614","title":"CLIMATE-FEVER: A Dataset for Verification of Real-World Climate Claims","created":"2020-12-01","cited_by_count":196},{"id":"1906.01076","title":"Episodic Memory in Lifelong Language Learning","created":"2019-06-03","cited_by_count":188},{"id":"2402.10171","title":"Data Engineering for Scaling Language Models to 128K Context","created":"2024-02-15","cited_by_count":186},{"id":"2305.14196","title":"ZeroSCROLLS: A Zero-Shot Benchmark for Long Text Understanding","created":"2023-05-23","cited_by_count":176},{"id":"2201.03533","title":"SCROLLS: Standardized CompaRison Over Long Language Sequences","created":"2022-01-10","cited_by_count":170},{"id":"2205.12393","title":"Fine-tuned Language Models are Continual Learners","created":"2022-05-24","cited_by_count":156},{"id":"2012.09823","title":"Continual Lifelong Learning in Natural Language Processing: A Survey","created":"2020-12-17","cited_by_count":152},{"id":"2402.14848","title":"Same Task, More Tokens: the Impact of Input Length on the Reasoning Performance of Large Language Models","created":"2024-02-19","cited_by_count":152},{"id":"2204.08582","title":"MASSIVE: A 1M-Example Multilingual Natural Language Understanding Dataset with 51 Typologically-Diverse Languages","created":"2022-04-18","cited_by_count":146},{"id":"2104.08704","title":"A Token-level Reference-free Hallucination Detection Benchmark for Free-form Text Generation","created":"2021-04-18","cited_by_count":138},{"id":"2112.09153","title":"An Empirical Investigation of the Role of Pre-training in Lifelong Learning","created":"2021-12-16","cited_by_count":134},{"id":"2307.03170","title":"Focused Transformer: Contrastive Training for Context Scaling","created":"2023-07-06","cited_by_count":133},{"id":"2405.00200","title":"In-Context Learning with Long-Context Models: An In-Depth Exploration","created":"2024-04-30","cited_by_count":128},{"id":"1710.06071","title":"PubMed 200k RCT: a Dataset for Sequential Sentence Classification in Medical Abstracts","created":"2017-10-17","cited_by_count":124},{"id":"2308.16137","title":"LM-Infinite: Zero-Shot Extreme Length Generalization for Large Language Models","created":"2023-08-30","cited_by_count":124},{"id":"2404.16811","title":"Make Your LLM Fully Utilize the Context","created":"2024-04-25","cited_by_count":119},{"id":"2205.12688","title":"ProsocialDialog: A Prosocial Backbone for Conversational Agents","created":"2022-05-25","cited_by_count":109},{"id":"2110.12010","title":"ClimateBert: A Pretrained Language Model for Climate-Related Text","created":"2021-10-22","cited_by_count":90},{"id":"2011.03870","title":"Explainable Automated Fact-Checking: A Survey","created":"2020-11-07","cited_by_count":83},{"id":"2006.08328","title":"ETHOS: an Online Hate Speech Detection Dataset","created":"2020-06-11","cited_by_count":66},{"id":"2305.14938","title":"Do LLMs Understand Social Knowledge? Evaluating the Sociability of Large Language Models with SocKET Benchmark","created":"2023-05-24","cited_by_count":63},{"id":"2005.05257","title":"A Dataset for Statutory Reasoning in Tax Law Entailment and Question Answering","created":"2020-05-11","cited_by_count":62},{"id":"2212.10378","title":"Data Curation Alone Can Stabilize In-context Learning","created":"2022-12-20","cited_by_count":59},{"id":"2305.12907","title":"Meta-in-context learning in large language models","created":"2023-05-22","cited_by_count":59},{"id":"2008.13546","title":"Effective Transfer Learning for Identifying Similar Questions: Matching User Questions to COVID-19 FAQs","created":"2020-08-04","cited_by_count":48},{"id":"2011.02686","title":"Investigating Societal Biases in a Poetry Composition System","created":"2020-11-05","cited_by_count":48},{"id":"2104.06893","title":"I Wish I Would Have Loved This One, But I Didn't -- A Multilingual Dataset for Counterfactual Detection in Product Reviews","created":"2021-04-14","cited_by_count":45},{"id":"1709.05404","title":"Creating and Characterizing a Diverse Corpus of Sarcasm in Dialogue","created":"2017-09-15","cited_by_count":43},{"id":"1610.09786","title":"Stop Clickbait: Detecting and Preventing Clickbaits in Online News Media","created":"2016-10-31","cited_by_count":39},{"id":"2009.11152","title":"Hierarchical Pre-training for Sequence Labelling in Spoken Dialog","created":"2020-09-23","cited_by_count":36},{"id":"2010.03450","title":"\"I'd rather just go to bed\": Understanding Indirect Answers","created":"2020-10-07","cited_by_count":36},{"id":"2104.08808","title":"Learn Continually, Generalize Rapidly: Lifelong Knowledge Accumulation for Few-shot Learning","created":"2021-04-18","cited_by_count":35},{"id":"2302.14691","title":"Investigating the Effectiveness of Task-Agnostic Prefix Prompt for Instruction Following","created":"2023-02-28","cited_by_count":33},{"id":"1905.06290","title":"A Surprisingly Robust Trick for Winograd Schema Challenge","created":"2019-05-15","cited_by_count":30},{"id":"2212.09246","title":"I2D2: Inductive Knowledge Distillation with NeuroLogic and Self-Imitation","created":"2022-12-19","cited_by_count":21},{"id":"2310.15941","title":"This is not a Dataset: A Large Negation Benchmark to Challenge Large Language Models","created":"2023-10-24","cited_by_count":18},{"id":"1603.08702","title":"Nine Features in a Random Forest to Learn Taxonomical Semantic Relations","created":"2016-03-29","cited_by_count":7},{"id":"2406.13131","title":"When Parts Are Greater Than Sums: Individual LLM Components Can Outperform Full Models","created":"2024-06-19","cited_by_count":6}],"next_cursor":null}