{"list":"other","total":61,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2205.11916","title":"Large Language Models are Zero-Shot Reasoners","created":"2022-05-24","cited_by_count":4374},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"2310.06825","title":"Mistral 7B","created":"2023-10-10","cited_by_count":3164},{"id":"1904.09751","title":"The Curious Case of Neural Text Degeneration","created":"2019-04-22","cited_by_count":2916},{"id":"1509.01626","title":"Character-level Convolutional Networks for Text Classification","created":"2015-09-04","cited_by_count":2330},{"id":"2202.12837","title":"Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?","created":"2022-02-25","cited_by_count":1434},{"id":"2101.06804","title":"What Makes Good In-Context Examples for GPT-$3$?","created":"2021-01-17","cited_by_count":1195},{"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":"1707.06209","title":"Crowdsourcing Multiple Choice Science Questions","created":"2017-07-19","cited_by_count":765},{"id":"2210.03493","title":"Automatic Chain of Thought Prompting in Large Language Models","created":"2022-10-07","cited_by_count":688},{"id":"2112.08633","title":"Learning To Retrieve Prompts for In-Context Learning","created":"2021-12-16","cited_by_count":648},{"id":"2110.15943","title":"MetaICL: Learning to Learn In Context","created":"2021-10-29","cited_by_count":454},{"id":"2308.14132","title":"Detecting Language Model Attacks with Perplexity","created":"2023-08-27","cited_by_count":431},{"id":"2303.03846","title":"Larger language models do in-context learning differently","created":"2023-03-07","cited_by_count":394},{"id":"2006.13554","title":"Normalized Loss Functions for Deep Learning with Noisy Labels","created":"2020-06-24","cited_by_count":257},{"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":"2212.04037","title":"Demystifying Prompts in Language Models via Perplexity Estimation","created":"2022-12-08","cited_by_count":216},{"id":"2212.10375","title":"Self-Adaptive In-Context Learning: An Information Compression Perspective for In-Context Example Selection and Ordering","created":"2022-12-20","cited_by_count":161},{"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":"2301.13670","title":"What Makes Good Examples for Visual In-Context Learning?","created":"2023-01-31","cited_by_count":150},{"id":"2301.11916","title":"Large Language Models Are Latent Variable Models: Explaining and Finding Good Demonstrations for In-Context Learning","created":"2023-01-27","cited_by_count":149},{"id":"2305.04320","title":"Unified Demonstration Retriever for In-Context Learning","created":"2023-05-07","cited_by_count":142},{"id":"2212.06800","title":"Diverse Demonstrations Improve In-context Compositional Generalization","created":"2022-12-13","cited_by_count":139},{"id":"2302.13539","title":"Finding Support Examples for In-Context Learning","created":"2023-02-27","cited_by_count":104},{"id":"1802.08979","title":"NL2Bash: A Corpus and Semantic Parser for Natural Language Interface to the Linux Operating System","created":"2018-02-25","cited_by_count":98},{"id":"2305.19148","title":"Mitigating Label Biases for In-context Learning","created":"2023-05-28","cited_by_count":89},{"id":"2109.06827","title":"Types of Out-of-Distribution Texts and How to Detect Them","created":"2021-09-14","cited_by_count":80},{"id":"2305.08298","title":"Symbol tuning improves in-context learning in language models","created":"2023-05-15","cited_by_count":75},{"id":"2310.09881","title":"In-Context Learning with Iterative Demonstration Selection","created":"2023-10-15","cited_by_count":74},{"id":"2305.14128","title":"Dr.ICL: Demonstration-Retrieved In-context Learning","created":"2023-05-23","cited_by_count":72},{"id":"2212.09865","title":"Z-ICL: Zero-Shot In-Context Learning with Pseudo-Demonstrations","created":"2022-12-19","cited_by_count":70},{"id":"2305.12907","title":"Meta-in-context learning in large language models","created":"2023-05-22","cited_by_count":59},{"id":"2305.14907","title":"Coverage-based Example Selection for In-Context Learning","created":"2023-05-24","cited_by_count":59},{"id":"2110.06283","title":"Detecting Corrupted Labels Without Training a Model to Predict","created":"2021-10-12","cited_by_count":58},{"id":"2401.12087","title":"Revisiting Demonstration Selection Strategies in In-Context Learning","created":"2024-01-22","cited_by_count":58},{"id":"2303.02913","title":"OpenICL: An Open-Source Framework for In-context Learning","created":"2023-03-06","cited_by_count":51},{"id":"2307.12375","title":"In-Context Learning Learns Label Relationships but Is Not Conventional Learning","created":"2023-07-23","cited_by_count":51},{"id":"2205.12253","title":"Evaluating the Impact of Model Scale for Compositional Generalization in Semantic Parsing","created":"2022-05-24","cited_by_count":50},{"id":"2305.09137","title":"Pre-Training to Learn in Context","created":"2023-05-16","cited_by_count":42},{"id":"2212.04055","title":"Mitigating Memorization of Noisy Labels by Clipping the Model Prediction","created":"2022-12-08","cited_by_count":40},{"id":"2310.20046","title":"Which Examples to Annotate for In-Context Learning? Towards Effective and Efficient Selection","created":"2023-10-30","cited_by_count":37},{"id":"2309.10954","title":"In-Context Learning for Text Classification with Many Labels","created":"2023-09-19","cited_by_count":35},{"id":"2305.12820","title":"MultiTabQA: Generating Tabular Answers for Multi-Table Question Answering","created":"2023-05-22","cited_by_count":32},{"id":"2307.10168","title":"LLMs as Workers in Human-Computational Algorithms? Replicating Crowdsourcing Pipelines with LLMs","created":"2023-07-19","cited_by_count":27},{"id":"2310.10873","title":"IDEAL: Influence-Driven Selective Annotations Empower In-Context Learners in Large Language Models","created":"2023-10-16","cited_by_count":27},{"id":"2204.09371","title":"Is BERT Robust to Label Noise? A Study on Learning with Noisy Labels in Text Classification","created":"2022-04-20","cited_by_count":21},{"id":"2212.07086","title":"NLIP: Noise-robust Language-Image Pre-training","created":"2022-12-14","cited_by_count":20},{"id":"2112.02960","title":"Two Wrongs Don't Make a Right: Combating Confirmation Bias in Learning with Label Noise","created":"2021-12-06","cited_by_count":18},{"id":"2209.00641","title":"Seq-UPS: Sequential Uncertainty-aware Pseudo-label Selection for Semi-Supervised Text Recognition","created":"2022-08-31","cited_by_count":14},{"id":"2312.16549","title":"How Robust are LLMs to In-Context Majority Label Bias?","created":"2023-12-27","cited_by_count":14},{"id":"2404.18191","title":"Exploring the Robustness of In-Context Learning with Noisy Labels","created":"2024-04-28","cited_by_count":14},{"id":"2211.11300","title":"Multi-Level Knowledge Distillation for Out-of-Distribution Detection in Text","created":"2022-11-21","cited_by_count":11},{"id":"2311.03798","title":"Noisy Pair Corrector for Dense Retrieval","created":"2023-11-07","cited_by_count":5},{"id":"2305.16337","title":"Handling Realistic Label Noise in BERT Text Classification","created":"2023-05-23","cited_by_count":4}],"next_cursor":null}