{"list":"other","total":56,"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":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"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":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"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":"2302.04761","title":"Toolformer: Language Models Can Teach Themselves to Use Tools","created":"2023-02-09","cited_by_count":4182},{"id":"2307.03172","title":"Lost in the Middle: How Language Models Use Long Contexts","created":"2023-07-06","cited_by_count":3455},{"id":"2305.10601","title":"Tree of Thoughts: Deliberate Problem Solving with Large Language Models","created":"2023-05-17","cited_by_count":3211},{"id":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576},{"id":"1806.03822","title":"Know What You Don't Know: Unanswerable Questions for SQuAD","created":"2018-06-11","cited_by_count":1554},{"id":"2002.10957","title":"MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers","created":"2020-02-25","cited_by_count":1463},{"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":"2112.04426","title":"Improving language models by retrieving from trillions of tokens","created":"2021-12-08","cited_by_count":1293},{"id":"2101.06804","title":"What Makes Good In-Context Examples for GPT-$3$?","created":"2021-01-17","cited_by_count":1195},{"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":"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":"2111.02080","title":"An Explanation of In-context Learning as Implicit Bayesian Inference","created":"2021-11-03","cited_by_count":938},{"id":"2112.00114","title":"Show Your Work: Scratchpads for Intermediate Computation with Language Models","created":"2021-11-30","cited_by_count":886},{"id":"2112.08633","title":"Learning To Retrieve Prompts for In-Context Learning","created":"2021-12-16","cited_by_count":648},{"id":"2210.15097","title":"Contrastive Decoding: Open-ended Text Generation as Optimization","created":"2022-10-27","cited_by_count":609},{"id":"2112.07899","title":"Large Dual Encoders Are Generalizable Retrievers","created":"2021-12-15","cited_by_count":456},{"id":"2302.07842","title":"Augmented Language Models: a Survey","created":"2023-02-15","cited_by_count":403},{"id":"2105.11447","title":"True Few-Shot Learning with Language Models","created":"2021-05-24","cited_by_count":344},{"id":"2305.11747","title":"HaluEval: A Large-Scale Hallucination Evaluation Benchmark for Large Language Models","created":"2023-05-19","cited_by_count":341},{"id":"2309.11495","title":"Chain-of-Verification Reduces Hallucination in Large Language Models","created":"2023-09-20","cited_by_count":324},{"id":"2306.05087","title":"PandaLM: An Automatic Evaluation Benchmark for LLM Instruction Tuning Optimization","created":"2023-06-08","cited_by_count":316},{"id":"2210.08726","title":"RARR: Researching and Revising What Language Models Say, Using Language Models","created":"2022-10-17","cited_by_count":287},{"id":"2210.09150","title":"Prompting GPT-3 To Be Reliable","created":"2022-10-17","cited_by_count":260},{"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":"2212.02437","title":"In-context Examples Selection for Machine Translation","created":"2022-12-05","cited_by_count":172},{"id":"2004.05483","title":"Unsupervised Commonsense Question Answering with Self-Talk","created":"2020-04-11","cited_by_count":161},{"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":"2210.02441","title":"Ask Me Anything: A simple strategy for prompting language models","created":"2022-10-05","cited_by_count":155},{"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":"2305.08377","title":"Text Classification via Large Language Models","created":"2023-05-15","cited_by_count":106},{"id":"2208.07204","title":"USB: A Unified Semi-supervised Learning Benchmark for Classification","created":"2022-08-12","cited_by_count":95},{"id":"2306.09296","title":"KoLA: Carefully Benchmarking World Knowledge of Large Language Models","created":"2023-06-15","cited_by_count":85},{"id":"2309.09117","title":"Contrastive Decoding Improves Reasoning in Large Language Models","created":"2023-09-17","cited_by_count":74},{"id":"2211.08073","title":"GLUE-X: Evaluating Natural Language Understanding Models from an Out-of-distribution Generalization Perspective","created":"2022-11-15","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":"2306.11270","title":"Evaluating the Zero-shot Robustness of Instruction-tuned Language Models","created":"2023-06-20","cited_by_count":66},{"id":"2305.09993","title":"Reprompting: Automated Chain-of-Thought Prompt Inference Through Gibbs Sampling","created":"2023-05-17","cited_by_count":47},{"id":"2305.08848","title":"Small Models are Valuable Plug-ins for Large Language Models","created":"2023-05-15","cited_by_count":42},{"id":"2305.09137","title":"Pre-Training to Learn in Context","created":"2023-05-16","cited_by_count":42},{"id":"2306.15091","title":"Understanding In-Context Learning via Supportive Pretraining Data","created":"2023-06-26","cited_by_count":41},{"id":"2010.12512","title":"Generating Plausible Counterfactual Explanations for Deep Transformers in Financial Text Classification","created":"2020-10-23","cited_by_count":40},{"id":"2106.15231","title":"Exploring the Efficacy of Automatically Generated Counterfactuals for Sentiment Analysis","created":"2021-06-29","cited_by_count":30},{"id":"2203.12918","title":"A Rationale-Centric Framework for Human-in-the-loop Machine Learning","created":"2022-03-24","cited_by_count":27},{"id":"2210.07448","title":"Evaluating Out-of-Distribution Performance on Document Image Classifiers","created":"2022-10-14","cited_by_count":16},{"id":"2311.15614","title":"FreeAL: Towards Human-Free Active Learning in the Era of Large Language Models","created":"2023-11-27","cited_by_count":14},{"id":"2307.01453","title":"Diverse Retrieval-Augmented In-Context Learning for Dialogue State Tracking","created":"2023-07-04","cited_by_count":10},{"id":"2208.08280","title":"Exploiting Unlabeled Data for Target-Oriented Opinion Words Extraction","created":"2022-08-17","cited_by_count":2}],"next_cursor":null}