{"list":"other","total":53,"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":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"1809.09600","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","created":"2018-09-25","cited_by_count":3754},{"id":"2305.14314","title":"QLoRA: Efficient Finetuning of Quantized LLMs","created":"2023-05-23","cited_by_count":3418},{"id":"2109.07958","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","created":"2021-09-08","cited_by_count":2975},{"id":"1911.11641","title":"PIQA: Reasoning about Physical Commonsense in Natural Language","created":"2019-11-26","cited_by_count":2883},{"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":"2210.17323","title":"GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers","created":"2022-10-31","cited_by_count":1919},{"id":"1811.00937","title":"CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge","created":"2018-11-02","cited_by_count":1822},{"id":"2207.04672","title":"No Language Left Behind: Scaling Human-Centered Machine Translation","created":"2022-07-11","cited_by_count":1312},{"id":"2011.01060","title":"Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps","created":"2020-11-02","cited_by_count":1282},{"id":"2112.11446","title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","created":"2021-12-08","cited_by_count":1202},{"id":"2208.07339","title":"LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale","created":"2022-08-15","cited_by_count":906},{"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":"2304.07327","title":"OpenAssistant Conversations -- Democratizing Large Language Model Alignment","created":"2023-04-14","cited_by_count":721},{"id":"2309.14525","title":"Aligning Large Multimodal Models with Factually Augmented RLHF","created":"2023-09-25","cited_by_count":712},{"id":"2104.04473","title":"Efficient Large-Scale Language Model Training on GPU Clusters Using Megatron-LM","created":"2021-04-09","cited_by_count":632},{"id":"2104.10350","title":"Carbon Emissions and Large Neural Network Training","created":"2021-04-21","cited_by_count":567},{"id":"1911.12237","title":"SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarization","created":"2019-11-27","cited_by_count":535},{"id":"1908.09203","title":"Release Strategies and the Social Impacts of Language Models","created":"2019-08-24","cited_by_count":513},{"id":"2111.01243","title":"Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Survey","created":"2021-11-01","cited_by_count":463},{"id":"2304.13712","title":"Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyond","created":"2023-04-26","cited_by_count":411},{"id":"2202.13169","title":"A Systematic Evaluation of Large Language Models of Code","created":"2022-02-26","cited_by_count":363},{"id":"2305.00050","title":"Causal Reasoning and Large Language Models: Opening a New Frontier for Causality","created":"2023-04-28","cited_by_count":353},{"id":"1904.01557","title":"Analysing Mathematical Reasoning Abilities of Neural Models","created":"2019-04-02","cited_by_count":335},{"id":"1502.05698","title":"Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks","created":"2015-02-19","cited_by_count":314},{"id":"1908.05739","title":"Abductive Commonsense Reasoning","created":"2019-08-15","cited_by_count":301},{"id":"2212.09720","title":"The case for 4-bit precision: k-bit Inference Scaling Laws","created":"2022-12-19","cited_by_count":251},{"id":"2302.08582","title":"Pretraining Language Models with Human Preferences","created":"2023-02-16","cited_by_count":247},{"id":"2308.07702","title":"Better Zero-Shot Reasoning with Role-Play Prompting","created":"2023-08-15","cited_by_count":223},{"id":"2202.07785","title":"Predictability and Surprise in Large Generative Models","created":"2022-02-15","cited_by_count":210},{"id":"2306.09479","title":"Inverse Scaling: When Bigger Isn't Better","created":"2023-06-15","cited_by_count":207},{"id":"2310.07521","title":"Survey on Factuality in Large Language Models: Knowledge, Retrieval and Domain-Specificity","created":"2023-10-11","cited_by_count":206},{"id":"1908.06177","title":"CLUTRR: A Diagnostic Benchmark for Inductive Reasoning from Text","created":"2019-08-16","cited_by_count":162},{"id":"2104.08661","title":"Explaining Answers with Entailment Trees","created":"2021-04-17","cited_by_count":152},{"id":"2309.01809","title":"Are Emergent Abilities in Large Language Models just In-Context Learning?","created":"2023-09-04","cited_by_count":109},{"id":"2310.01714","title":"Large Language Models as Analogical Reasoners","created":"2023-10-03","cited_by_count":107},{"id":"2206.09557","title":"LUT-GEMM: Quantized Matrix Multiplication based on LUTs for Efficient Inference in Large-Scale Generative Language Models","created":"2022-06-20","cited_by_count":105},{"id":"2305.14152","title":"Memory-Efficient Fine-Tuning of Compressed Large Language Models via sub-4-bit Integer Quantization","created":"2023-05-23","cited_by_count":100},{"id":"2104.05832","title":"SpartQA: : A Textual Question Answering Benchmark for Spatial Reasoning","created":"2021-04-12","cited_by_count":77},{"id":"2204.08292","title":"StepGame: A New Benchmark for Robust Multi-Hop Spatial Reasoning in Texts","created":"2022-04-18","cited_by_count":68},{"id":"2205.15960","title":"NusaX: Multilingual Parallel Sentiment Dataset for 10 Indonesian Local Languages","created":"2022-05-31","cited_by_count":68},{"id":"2103.09535","title":"Towards Few-Shot Fact-Checking via Perplexity","created":"2021-03-17","cited_by_count":63},{"id":"2007.06477","title":"Learning Reasoning Strategies in End-to-End Differentiable Proving","created":"2020-07-13","cited_by_count":60},{"id":"2106.04571","title":"TIMEDIAL: Temporal Commonsense Reasoning in Dialog","created":"2021-06-08","cited_by_count":55},{"id":"2205.05849","title":"e-CARE: a New Dataset for Exploring Explainable Causal Reasoning","created":"2022-05-12","cited_by_count":47},{"id":"2112.02732","title":"JointLK: Joint Reasoning with Language Models and Knowledge Graphs for Commonsense Question Answering","created":"2021-12-06","cited_by_count":40},{"id":"1511.06488","title":"Resiliency of Deep Neural Networks under Quantization","created":"2015-11-20","cited_by_count":35},{"id":"2203.10261","title":"FaiRR: Faithful and Robust Deductive Reasoning over Natural Language","created":"2022-03-19","cited_by_count":29},{"id":"1804.00619","title":"Modeling Semantic Plausibility by Injecting World Knowledge","created":"2018-04-02","cited_by_count":24}],"next_cursor":null}