{"list":"other","total":69,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"1905.07830","title":"HellaSwag: Can a Machine Really Finish Your Sentence?","created":"2019-05-19","cited_by_count":4100},{"id":"1809.09600","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","created":"2018-09-25","cited_by_count":3754},{"id":"1508.07909","title":"Neural Machine Translation of Rare Words with Subword Units","created":"2015-08-31","cited_by_count":2918},{"id":"1911.11641","title":"PIQA: Reasoning about Physical Commonsense in Natural Language","created":"2019-11-26","cited_by_count":2883},{"id":"2303.16634","title":"G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment","created":"2023-03-29","cited_by_count":2276},{"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":"2404.14219","title":"Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone","created":"2024-04-22","cited_by_count":1917},{"id":"2401.04088","title":"Mixtral of Experts","created":"2024-01-08","cited_by_count":1823},{"id":"2210.09261","title":"Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them","created":"2022-10-17","cited_by_count":1807},{"id":"2311.07911","title":"Instruction-Following Evaluation for Large Language Models","created":"2023-11-14","cited_by_count":1228},{"id":"1510.03055","title":"A Diversity-Promoting Objective Function for Neural Conversation Models","created":"2015-10-11","cited_by_count":1077},{"id":"2403.08295","title":"Gemma: Open Models Based on Gemini Research and Technology","created":"2024-03-13","cited_by_count":916},{"id":"2302.04023","title":"A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity","created":"2023-02-08","cited_by_count":894},{"id":"2309.03409","title":"Large Language Models as Optimizers","created":"2023-09-07","cited_by_count":864},{"id":"1602.06023","title":"Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond","created":"2016-02-19","cited_by_count":812},{"id":"2304.06364","title":"AGIEval: A Human-Centric Benchmark for Evaluating Foundation Models","created":"2023-04-13","cited_by_count":716},{"id":"2305.08322","title":"C-Eval: A Multi-Level Multi-Discipline Chinese Evaluation Suite for Foundation Models","created":"2023-05-15","cited_by_count":708},{"id":"2309.01219","title":"Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models","created":"2023-09-03","cited_by_count":698},{"id":"2302.06476","title":"Is ChatGPT a General-Purpose Natural Language Processing Task Solver?","created":"2023-02-08","cited_by_count":488},{"id":"2405.07987","title":"The Platonic Representation Hypothesis","created":"2024-05-13","cited_by_count":382},{"id":"2209.12356","title":"News Summarization and Evaluation in the Era of GPT-3","created":"2022-09-26","cited_by_count":327},{"id":"2210.07197","title":"Towards a Unified Multi-Dimensional Evaluator for Text Generation","created":"2022-10-13","cited_by_count":264},{"id":"2301.07069","title":"Prompting Large Language Model for Machine Translation: A Case Study","created":"2023-01-17","cited_by_count":250},{"id":"2112.08542","title":"QAFactEval: Improved QA-Based Factual Consistency Evaluation for Summarization","created":"2021-12-16","cited_by_count":236},{"id":"2309.08532","title":"EvoPrompt: Connecting LLMs with Evolutionary Algorithms Yields Powerful Prompt Optimizers","created":"2023-09-15","cited_by_count":193},{"id":"2306.07174","title":"Augmenting Language Models with Long-Term Memory","created":"2023-06-12","cited_by_count":189},{"id":"2305.12474","title":"Evaluating the Performance of Large Language Models on GAOKAO Benchmark","created":"2023-05-21","cited_by_count":186},{"id":"1911.03118","title":"Not Enough Data? Deep Learning to the Rescue!","created":"2019-11-08","cited_by_count":175},{"id":"2306.15448","title":"Understanding Social Reasoning in Language Models with Language Models","created":"2023-06-21","cited_by_count":172},{"id":"2302.03494","title":"A Categorical Archive of ChatGPT Failures","created":"2023-02-06","cited_by_count":168},{"id":"2304.11082","title":"Fundamental Limitations of Alignment in Large Language Models","created":"2023-04-19","cited_by_count":155},{"id":"2302.13007","title":"AugGPT: Leveraging ChatGPT for Text Data Augmentation","created":"2023-02-25","cited_by_count":130},{"id":"2401.12794","title":"Benchmarking LLMs via Uncertainty Quantification","created":"2024-01-23","cited_by_count":126},{"id":"2304.06588","title":"ChatGPT-4 Outperforms Experts and Crowd Workers in Annotating Political Twitter Messages with Zero-Shot Learning","created":"2023-04-13","cited_by_count":100},{"id":"2305.16289","title":"Diversify Your Vision Datasets with Automatic Diffusion-Based Augmentation","created":"2023-05-25","cited_by_count":100},{"id":"2211.13972","title":"Picking on the Same Person: Does Algorithmic Monoculture lead to Outcome Homogenization?","created":"2022-11-25","cited_by_count":91},{"id":"2403.20279","title":"LUQ: Long-text Uncertainty Quantification for LLMs","created":"2024-03-29","cited_by_count":81},{"id":"2202.13047","title":"AugESC: Dialogue Augmentation with Large Language Models for Emotional Support Conversation","created":"2022-02-26","cited_by_count":79},{"id":"2110.07356","title":"Medically Aware GPT-3 as a Data Generator for Medical Dialogue Summarization","created":"2021-09-09","cited_by_count":76},{"id":"2303.07992","title":"Can ChatGPT Replace Traditional KBQA Models? An In-depth Analysis of the Question Answering Performance of the GPT LLM Family","created":"2023-03-14","cited_by_count":71},{"id":"2304.10513","title":"Why Does ChatGPT Fall Short in Providing Truthful Answers?","created":"2023-04-20","cited_by_count":54},{"id":"2310.15851","title":"Self-Guard: Empower the LLM to Safeguard Itself","created":"2023-10-24","cited_by_count":54},{"id":"2309.07062","title":"Large Language Models for Compiler Optimization","created":"2023-09-11","cited_by_count":52},{"id":"2204.01959","title":"Data Augmentation for Intent Classification with Off-the-shelf Large Language Models","created":"2022-04-05","cited_by_count":49},{"id":"2210.04185","title":"Controllable Dialogue Simulation with In-Context Learning","created":"2022-10-09","cited_by_count":42},{"id":"2306.08952","title":"Towards Benchmarking and Improving the Temporal Reasoning Capability of Large Language Models","created":"2023-06-15","cited_by_count":37},{"id":"2211.03044","title":"Tuning Language Models as Training Data Generators for Augmentation-Enhanced Few-Shot Learning","created":"2022-11-06","cited_by_count":36},{"id":"2310.11761","title":"A Comprehensive Evaluation of Large Language Models on Legal Judgment Prediction","created":"2023-10-18","cited_by_count":28},{"id":"2302.05096","title":"Selective In-Context Data Augmentation for Intent Detection using Pointwise V-Information","created":"2023-02-10","cited_by_count":24},{"id":"2101.11429","title":"TSQA: Tabular Scenario Based Question Answering","created":"2021-01-14","cited_by_count":21},{"id":"2407.03658","title":"GPT-4 vs. Human Translators: A Comprehensive Evaluation of Translation Quality Across Languages, Domains, and Expertise Levels","created":"2024-07-04","cited_by_count":21},{"id":"2310.08394","title":"Towards Better Evaluation of Instruction-Following: A Case-Study in Summarization","created":"2023-10-12","cited_by_count":18},{"id":"2211.09783","title":"UniSumm and SummZoo: Unified Model and Diverse Benchmark for Few-Shot Summarization","created":"2022-11-17","cited_by_count":15},{"id":"2402.13463","title":"RefuteBench: Evaluating Refuting Instruction-Following for Large Language Models","created":"2024-02-21","cited_by_count":11},{"id":"1804.00540","title":"A Systematic Review of Automated Grammar Checking in English Language","created":"2018-03-29","cited_by_count":3},{"id":"2310.19462","title":"Constituency Parsing using LLMs","created":"2023-10-30","cited_by_count":2}],"next_cursor":null}