{"list":"other","total":89,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"id":"2204.05862","title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","created":"2022-04-12","cited_by_count":3720},{"id":"2307.03172","title":"Lost in the Middle: How Language Models Use Long Contexts","created":"2023-07-06","cited_by_count":3455},{"id":"2212.08073","title":"Constitutional AI: Harmlessness from AI Feedback","created":"2022-12-15","cited_by_count":3050},{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024},{"id":"2212.10560","title":"Self-Instruct: Aligning Language Models with Self-Generated Instructions","created":"2022-12-20","cited_by_count":2724},{"id":"2202.12837","title":"Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?","created":"2022-02-25","cited_by_count":1434},{"id":"2102.09690","title":"Calibrate Before Use: Improving Few-Shot Performance of Language Models","created":"2021-02-19","cited_by_count":1392},{"id":"2303.17580","title":"HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face","created":"2023-03-30","cited_by_count":1190},{"id":"2305.10403","title":"PaLM 2 Technical Report","created":"2023-05-17","cited_by_count":1162},{"id":"2104.08786","title":"Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity","created":"2021-04-18","cited_by_count":1135},{"id":"2212.10511","title":"When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories","created":"2022-12-20","cited_by_count":1128},{"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":"2202.03286","title":"Red Teaming Language Models with Language Models","created":"2022-02-07","cited_by_count":1026},{"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":"2110.04366","title":"Towards a Unified View of Parameter-Efficient Transfer Learning","created":"2021-10-08","cited_by_count":872},{"id":"2204.07705","title":"Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks","created":"2022-04-16","cited_by_count":868},{"id":"2301.13688","title":"The Flan Collection: Designing Data and Methods for Effective Instruction Tuning","created":"2023-01-31","cited_by_count":739},{"id":"2209.07858","title":"Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned","created":"2022-08-23","cited_by_count":729},{"id":"2008.02275","title":"Aligning AI With Shared Human Values","created":"2020-08-05","cited_by_count":723},{"id":"2104.08773","title":"Cross-Task Generalization via Natural Language Crowdsourcing Instructions","created":"2021-04-18","cited_by_count":699},{"id":"2304.06767","title":"RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment","created":"2023-04-13","cited_by_count":686},{"id":"2003.08271","title":"Pre-trained Models for Natural Language Processing: A Survey","created":"2020-03-18","cited_by_count":505},{"id":"2302.06476","title":"Is ChatGPT a General-Purpose Natural Language Processing Task Solver?","created":"2023-02-08","cited_by_count":488},{"id":"2309.05653","title":"MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuning","created":"2023-09-11","cited_by_count":487},{"id":"2005.00547","title":"GoEmotions: A Dataset of Fine-Grained Emotions","created":"2020-05-01","cited_by_count":486},{"id":"2001.09768","title":"Artificial Intelligence, Values and Alignment","created":"2020-01-13","cited_by_count":448},{"id":"1811.07871","title":"Scalable agent alignment via reward modeling: a research direction","created":"2018-11-19","cited_by_count":447},{"id":"2303.03846","title":"Larger language models do in-context learning differently","created":"2023-03-07","cited_by_count":394},{"id":"2109.05052","title":"Entity-Based Knowledge Conflicts in Question Answering","created":"2021-09-10","cited_by_count":356},{"id":"2304.09842","title":"Chameleon: Plug-and-Play Compositional Reasoning with Large Language Models","created":"2023-04-19","cited_by_count":356},{"id":"2305.13300","title":"Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge Conflicts","created":"2023-05-22","cited_by_count":341},{"id":"2109.01247","title":"Do Prompt-Based Models Really Understand the Meaning of their Prompts?","created":"2021-09-02","cited_by_count":326},{"id":"2305.03047","title":"Principle-Driven Self-Alignment of Language Models from Scratch with Minimal Human Supervision","created":"2023-05-04","cited_by_count":318},{"id":"2305.14795","title":"MQuAKE: Assessing Knowledge Editing in Language Models via Multi-Hop Questions","created":"2023-05-24","cited_by_count":300},{"id":"2205.05131","title":"UL2: Unifying Language Learning Paradigms","created":"2022-05-10","cited_by_count":295},{"id":"2301.13867","title":"Mathematical Capabilities of ChatGPT","created":"2023-01-31","cited_by_count":268},{"id":"2307.10169","title":"Challenges and Applications of Large Language Models","created":"2023-07-19","cited_by_count":254},{"id":"1906.06127","title":"DocRED: A Large-Scale Document-Level Relation Extraction Dataset","created":"2019-06-14","cited_by_count":239},{"id":"2212.12017","title":"OPT-IML: Scaling Language Model Instruction Meta Learning through the Lens of Generalization","created":"2022-12-22","cited_by_count":236},{"id":"2306.15895","title":"Large Language Model as Attributed Training Data Generator: A Tale of Diversity and Bias","created":"2023-06-28","cited_by_count":232},{"id":"1811.01088","title":"Sentence Encoders on STILTs: Supplementary Training on Intermediate Labeled-data Tasks","created":"2018-11-02","cited_by_count":215},{"id":"2302.10724","title":"ChatGPT: Jack of all trades, master of none","created":"2023-02-21","cited_by_count":204},{"id":"2304.03439","title":"Evaluating the Logical Reasoning Ability of ChatGPT and GPT-4","created":"2023-04-07","cited_by_count":202},{"id":"2203.06904","title":"Delta Tuning: A Comprehensive Study of Parameter Efficient Methods for Pre-trained Language Models","created":"2022-03-14","cited_by_count":180},{"id":"2109.07830","title":"Reframing Instructional Prompts to GPTk's Language","created":"2021-09-16","cited_by_count":176},{"id":"2301.08745","title":"Is ChatGPT A Good Translator? Yes With GPT-4 As The Engine","created":"2023-01-20","cited_by_count":176},{"id":"2201.03533","title":"SCROLLS: Standardized CompaRison Over Long Language Sequences","created":"2022-01-10","cited_by_count":170},{"id":"2103.14659","title":"Alignment of Language Agents","created":"2021-03-26","cited_by_count":168},{"id":"2308.10168","title":"Head-to-Tail: How Knowledgeable are Large Language Models (LLMs)? A.K.A. Will LLMs Replace Knowledge Graphs?","created":"2023-08-20","cited_by_count":168},{"id":"2102.02503","title":"Understanding the Capabilities, Limitations, and Societal Impact of Large Language Models","created":"2021-02-04","cited_by_count":160},{"id":"2309.07124","title":"RAIN: Your Language Models Can Align Themselves without Finetuning","created":"2023-09-13","cited_by_count":157},{"id":"2105.07464","title":"Few-NERD: A Few-Shot Named Entity Recognition Dataset","created":"2021-05-16","cited_by_count":152},{"id":"2305.09731","title":"What In-Context Learning \"Learns\" In-Context: Disentangling Task Recognition and Task Learning","created":"2023-05-16","cited_by_count":152},{"id":"2304.11633","title":"Evaluating ChatGPT's Information Extraction Capabilities: An Assessment of Performance, Explainability, Calibration, and Faithfulness","created":"2023-04-23","cited_by_count":130},{"id":"2004.13590","title":"MAVEN: A Massive General Domain Event Detection Dataset","created":"2020-04-28","cited_by_count":104},{"id":"1910.07124","title":"FewRel 2.0: Towards More Challenging Few-Shot Relation Classification","created":"2019-10-16","cited_by_count":94},{"id":"2010.05006","title":"Automated Concatenation of Embeddings for Structured Prediction","created":"2020-10-10","cited_by_count":86},{"id":"2306.09296","title":"KoLA: Carefully Benchmarking World Knowledge of Large Language Models","created":"2023-06-15","cited_by_count":85},{"id":"2203.08410","title":"Thinking about GPT-3 In-Context Learning for Biomedical IE? Think Again","created":"2022-03-16","cited_by_count":83},{"id":"2303.11315","title":"Context-faithful Prompting for Large Language Models","created":"2023-03-20","cited_by_count":80},{"id":"2303.03836","title":"Exploring the Feasibility of ChatGPT for Event Extraction","created":"2023-03-07","cited_by_count":76},{"id":"1804.07828","title":"A Multi-Axis Annotation Scheme for Event Temporal Relations","created":"2018-04-20","cited_by_count":75},{"id":"1911.04118","title":"TANDA: Transfer and Adapt Pre-Trained Transformer Models for Answer Sentence Selection","created":"2019-11-11","cited_by_count":74},{"id":"2308.00675","title":"Tool Documentation Enables Zero-Shot Tool-Usage with Large Language Models","created":"2023-08-01","cited_by_count":68},{"id":"2211.07342","title":"MAVEN-ERE: A Unified Large-scale Dataset for Event Coreference, Temporal, Causal, and Subevent Relation Extraction","created":"2022-11-14","cited_by_count":66},{"id":"2202.12109","title":"Prompt for Extraction? PAIE: Prompting Argument Interaction for Event Argument Extraction","created":"2022-02-24","cited_by_count":54},{"id":"2305.14288","title":"LLM-powered Data Augmentation for Enhanced Cross-lingual Performance","created":"2023-05-23","cited_by_count":51},{"id":"2305.13299","title":"Measuring Inductive Biases of In-Context Learning with Underspecified Demonstrations","created":"2023-05-22","cited_by_count":49},{"id":"2305.14450","title":"An Empirical Study on Information Extraction using Large Language Models","created":"2023-05-23","cited_by_count":46},{"id":"2205.10475","title":"DeepStruct: Pretraining of Language Models for Structure Prediction","created":"2022-05-21","cited_by_count":45},{"id":"1712.05191","title":"Relation Extraction : A Survey","created":"2017-12-14","cited_by_count":44},{"id":"2302.08675","title":"DREEAM: Guiding Attention with Evidence for Improving Document-Level Relation Extraction","created":"2023-02-17","cited_by_count":37},{"id":"2105.14485","title":"CLEVE: Contrastive Pre-training for Event Extraction","created":"2021-05-30","cited_by_count":36},{"id":"2306.10512","title":"Position: AI Evaluation Should Learn from How We Test Humans","created":"2023-06-18","cited_by_count":36},{"id":"2304.02182","title":"How to Design Translation Prompts for ChatGPT: An Empirical Study","created":"2023-04-05","cited_by_count":31},{"id":"2305.01555","title":"How to Unleash the Power of Large Language Models for Few-shot Relation Extraction?","created":"2023-05-02","cited_by_count":30},{"id":"2208.14565","title":"Optimizing Bi-Encoder for Named Entity Recognition via Contrastive Learning","created":"2022-08-30","cited_by_count":24},{"id":"2306.06331","title":"Investigating the Effectiveness of ChatGPT in Mathematical Reasoning and Problem Solving: Evidence from the Vietnamese National High School Graduation Examination","created":"2023-06-10","cited_by_count":13},{"id":"2309.14258","title":"OmniEvent: A Comprehensive, Fair, and Easy-to-Use Toolkit for Event Understanding","created":"2023-09-25","cited_by_count":11},{"id":"1905.07504","title":"Story Ending Prediction by Transferable BERT","created":"2019-05-17","cited_by_count":10},{"id":"2211.11754","title":"An Algorithm for Routing Vectors in Sequences","created":"2022-11-20","cited_by_count":7}],"next_cursor":null}