{"list":"other","total":53,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"1706.06083","title":"Towards Deep Learning Models Resistant to Adversarial Attacks","created":"2017-06-19","cited_by_count":6415},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"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":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"2307.15043","title":"Universal and Transferable Adversarial Attacks on Aligned Language Models","created":"2023-07-27","cited_by_count":3104},{"id":"2109.07958","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","created":"2021-09-08","cited_by_count":2975},{"id":"1704.05426","title":"A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference","created":"2017-04-18","cited_by_count":2682},{"id":"2211.05100","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","created":"2022-11-09","cited_by_count":1984},{"id":"2110.08207","title":"Multitask Prompted Training Enables Zero-Shot Task Generalization","created":"2021-10-15","cited_by_count":1470},{"id":"2309.07864","title":"The Rise and Potential of Large Language Model Based Agents: A Survey","created":"2023-09-14","cited_by_count":1439},{"id":"2102.09690","title":"Calibrate Before Use: Improving Few-Shot Performance of Language Models","created":"2021-02-19","cited_by_count":1392},{"id":"1902.02918","title":"Certified Adversarial Robustness via Randomized Smoothing","created":"2019-02-08","cited_by_count":1340},{"id":"2012.15723","title":"Making Pre-trained Language Models Better Few-shot Learners","created":"2020-12-31","cited_by_count":1256},{"id":"2112.11446","title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","created":"2021-12-08","cited_by_count":1202},{"id":"1708.06733","title":"BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain","created":"2017-08-22","cited_by_count":1106},{"id":"1905.02175","title":"Adversarial Examples Are Not Bugs, They Are Features","created":"2019-05-06","cited_by_count":953},{"id":"2111.02080","title":"An Explanation of In-context Learning as Implicit Bayesian Inference","created":"2021-11-03","cited_by_count":938},{"id":"2109.00859","title":"CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation","created":"2021-09-02","cited_by_count":906},{"id":"2203.13474","title":"CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis","created":"2022-03-25","cited_by_count":885},{"id":"2212.07677","title":"Transformers learn in-context by gradient descent","created":"2022-12-15","cited_by_count":732},{"id":"2003.08271","title":"Pre-trained Models for Natural Language Processing: A Survey","created":"2020-03-18","cited_by_count":505},{"id":"1812.05271","title":"TextBugger: Generating Adversarial Text Against Real-world Applications","created":"2018-12-13","cited_by_count":381},{"id":"1801.04354","title":"Black-box Generation of Adversarial Text Sequences to Evade Deep Learning Classifiers","created":"2018-01-13","cited_by_count":345},{"id":"2310.14152","title":"Orthogonal Subspace Learning for Language Model Continual Learning","created":"2023-10-22","cited_by_count":312},{"id":"1909.11764","title":"FreeLB: Enhanced Adversarial Training for Natural Language Understanding","created":"2019-09-25","cited_by_count":264},{"id":"2104.08315","title":"Surface Form Competition: Why the Highest Probability Answer Isn't Always Right","created":"2021-04-16","cited_by_count":263},{"id":"1911.03437","title":"SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized Optimization","created":"2019-11-08","cited_by_count":254},{"id":"2303.10420","title":"A Comprehensive Capability Analysis of GPT-3 and GPT-3.5 Series Models","created":"2023-03-18","cited_by_count":246},{"id":"2111.02840","title":"Adversarial GLUE: A Multi-Task Benchmark for Robustness Evaluation of Language Models","created":"2021-11-04","cited_by_count":232},{"id":"2210.02875","title":"Binding Language Models in Symbolic Languages","created":"2022-10-06","cited_by_count":228},{"id":"2306.04528","title":"PromptRobust: Towards Evaluating the Robustness of Large Language Models on Adversarial Prompts","created":"2023-06-07","cited_by_count":226},{"id":"2301.07067","title":"Transformers as Algorithms: Generalization and Stability in In-context Learning","created":"2023-01-17","cited_by_count":222},{"id":"2302.12095","title":"On the Robustness of ChatGPT: An Adversarial and Out-of-distribution Perspective","created":"2023-02-22","cited_by_count":211},{"id":"2212.10559","title":"Why Can GPT Learn In-Context? Language Models Implicitly Perform Gradient Descent as Meta-Optimizers","created":"2022-12-20","cited_by_count":204},{"id":"2210.12353","title":"Leveraging Large Language Models for Multiple Choice Question Answering","created":"2022-10-22","cited_by_count":203},{"id":"1506.01066","title":"Visualizing and Understanding Neural Models in NLP","created":"2015-06-02","cited_by_count":200},{"id":"2304.08085","title":"InstructUIE: Multi-task Instruction Tuning for Unified Information Extraction","created":"2023-04-17","cited_by_count":170},{"id":"2108.04106","title":"Noisy Channel Language Model Prompting for Few-Shot Text Classification","created":"2021-08-09","cited_by_count":165},{"id":"2210.07128","title":"Language Models of Code are Few-Shot Commonsense Learners","created":"2022-10-13","cited_by_count":160},{"id":"2108.04840","title":"Post-hoc Interpretability for Neural NLP: A Survey","created":"2021-08-10","cited_by_count":156},{"id":"2210.02441","title":"Ask Me Anything: A simple strategy for prompting language models","created":"2022-10-05","cited_by_count":155},{"id":"2305.05711","title":"CodeIE: Large Code Generation Models are Better Few-Shot Information Extractors","created":"2023-05-09","cited_by_count":68},{"id":"2303.00293","title":"How Robust is GPT-3.5 to Predecessors? A Comprehensive Study on Language Understanding Tasks","created":"2023-03-01","cited_by_count":58},{"id":"2004.05887","title":"Frequency-Guided Word Substitutions for Detecting Textual Adversarial Examples","created":"2020-04-13","cited_by_count":54},{"id":"1805.10265","title":"Training verified learners with learned verifiers","created":"2018-05-25","cited_by_count":50},{"id":"2009.07964","title":"Tasty Burgers, Soggy Fries: Probing Aspect Robustness in Aspect-Based Sentiment Analysis","created":"2020-09-16","cited_by_count":23},{"id":"2204.04391","title":"MINER: Improving Out-of-Vocabulary Named Entity Recognition from an Information Theoretic Perspective","created":"2022-04-09","cited_by_count":17},{"id":"2305.11790","title":"Prompting with Pseudo-Code Instructions","created":"2023-05-19","cited_by_count":14},{"id":"2304.13250","title":"Exploring the Curious Case of Code Prompts","created":"2023-04-26","cited_by_count":6}],"next_cursor":null}