{"list":"other","total":97,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"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":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"1911.02116","title":"Unsupervised Cross-lingual Representation Learning at Scale","created":"2019-11-05","cited_by_count":3935},{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"id":"1310.4546","title":"Distributed Representations of Words and Phrases and their Compositionality","created":"2013-10-16","cited_by_count":3474},{"id":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344},{"id":"2101.03961","title":"Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity","created":"2021-01-11","cited_by_count":3073},{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"1906.08237","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","created":"2019-06-19","cited_by_count":2811},{"id":"1909.11942","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","created":"2019-09-26","cited_by_count":2790},{"id":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576},{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"id":"2101.00027","title":"The Pile: An 800GB Dataset of Diverse Text for Language Modeling","created":"2020-12-31","cited_by_count":2411},{"id":"2107.13586","title":"Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing","created":"2021-07-28","cited_by_count":2234},{"id":"2012.07805","title":"Extracting Training Data from Large Language Models","created":"2020-12-14","cited_by_count":2189},{"id":"2006.03654","title":"DeBERTa: Decoding-enhanced BERT with Disentangled Attention","created":"2020-06-05","cited_by_count":2181},{"id":"2308.12950","title":"Code Llama: Open Foundation Models for Code","created":"2023-08-24","cited_by_count":2139},{"id":"2211.05100","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","created":"2022-11-09","cited_by_count":1984},{"id":"2304.01373","title":"Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling","created":"2023-04-03","cited_by_count":1786},{"id":"2112.09332","title":"WebGPT: Browser-assisted question-answering with human feedback","created":"2021-12-17","cited_by_count":1745},{"id":"2311.05232","title":"A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions","created":"2023-11-09","cited_by_count":1601},{"id":"2110.08207","title":"Multitask Prompted Training Enables Zero-Shot Task Generalization","created":"2021-10-15","cited_by_count":1470},{"id":"2203.07814","title":"Competition-Level Code Generation with AlphaCode","created":"2022-02-08","cited_by_count":1462},{"id":"2009.13081","title":"What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams","created":"2020-09-28","cited_by_count":1356},{"id":"2207.04672","title":"No Language Left Behind: Scaling Human-Centered Machine Translation","created":"2022-07-11","cited_by_count":1312},{"id":"2201.08239","title":"LaMDA: Language Models for Dialog Applications","created":"2022-01-20","cited_by_count":1220},{"id":"2112.11446","title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","created":"2021-12-08","cited_by_count":1202},{"id":"2112.00861","title":"A General Language Assistant as a Laboratory for Alignment","created":"2021-12-01","cited_by_count":1055},{"id":"2303.17564","title":"BloombergGPT: A Large Language Model for Finance","created":"2023-03-30","cited_by_count":939},{"id":"2112.06905","title":"GLaM: Efficient Scaling of Language Models with Mixture-of-Experts","created":"2021-12-13","cited_by_count":897},{"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":"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":"2210.02414","title":"GLM-130B: An Open Bilingual Pre-trained Model","created":"2022-10-05","cited_by_count":843},{"id":"2211.09085","title":"Galactica: A Large Language Model for Science","created":"2022-11-16","cited_by_count":744},{"id":"2204.06745","title":"GPT-NeoX-20B: An Open-Source Autoregressive Language Model","created":"2022-04-14","cited_by_count":713},{"id":"2309.00770","title":"Bias and Fairness in Large Language Models: A Survey","created":"2023-09-02","cited_by_count":639},{"id":"2201.11990","title":"Using DeepSpeed and Megatron to Train Megatron-Turing NLG 530B, A Large-Scale Generative Language Model","created":"2022-01-28","cited_by_count":559},{"id":"2209.14375","title":"Improving alignment of dialogue agents via targeted human judgements","created":"2022-09-28","cited_by_count":531},{"id":"2204.05999","title":"InCoder: A Generative Model for Code Infilling and Synthesis","created":"2022-04-12","cited_by_count":498},{"id":"2104.08758","title":"Documenting Large Webtext Corpora: A Case Study on the Colossal Clean Crawled Corpus","created":"2021-04-18","cited_by_count":492},{"id":"2312.02003","title":"A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Ugly","created":"2023-12-04","cited_by_count":387},{"id":"2305.09617","title":"Towards Expert-Level Medical Question Answering with Large Language Models","created":"2023-05-16","cited_by_count":384},{"id":"2103.06333","title":"Unified Pre-training for Program Understanding and Generation","created":"2021-03-10","cited_by_count":366},{"id":"2207.01780","title":"CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning","created":"2022-07-05","cited_by_count":358},{"id":"1506.06726","title":"Skip-Thought Vectors","created":"2015-06-22","cited_by_count":322},{"id":"2106.07139","title":"Pre-Trained Models: Past, Present and Future","created":"2021-06-14","cited_by_count":319},{"id":"2303.17568","title":"CodeGeeX: A Pre-Trained Model for Code Generation with Multilingual Benchmarking on HumanEval-X","created":"2023-03-30","cited_by_count":300},{"id":"2205.05131","title":"UL2: Unifying Language Learning Paradigms","created":"2022-05-10","cited_by_count":295},{"id":"2107.02137","title":"ERNIE 3.0: Large-scale Knowledge Enhanced Pre-training for Language Understanding and Generation","created":"2021-07-05","cited_by_count":260},{"id":"2212.12017","title":"OPT-IML: Scaling Language Model Instruction Meta Learning through the Lens of Generalization","created":"2022-12-22","cited_by_count":236},{"id":"2311.10723","title":"Large Language Models in Finance: A Survey","created":"2023-09-28","cited_by_count":226},{"id":"2105.04054","title":"Societal Biases in Language Generation: Progress and Challenges","created":"2021-05-10","cited_by_count":202},{"id":"2212.03551","title":"Talking About Large Language Models","created":"2022-12-07","cited_by_count":175},{"id":"1602.02410","title":"Exploring the Limits of Language Modeling","created":"2016-02-07","cited_by_count":173},{"id":"2307.15343","title":"Med-HALT: Medical Domain Hallucination Test for Large Language Models","created":"2023-07-28","cited_by_count":157},{"id":"2204.05832","title":"What Language Model Architecture and Pretraining Objective Work Best for Zero-Shot Generalization?","created":"2022-04-12","cited_by_count":150},{"id":"2305.02309","title":"CodeGen2: Lessons for Training LLMs on Programming and Natural Languages","created":"2023-05-03","cited_by_count":125},{"id":"2310.19341","title":"Skywork: A More Open Bilingual Foundation Model","created":"2023-10-30","cited_by_count":112},{"id":"2203.09095","title":"Automating Code Review Activities by Large-Scale Pre-training","created":"2022-03-17","cited_by_count":98},{"id":"2110.08527","title":"An Empirical Survey of the Effectiveness of Debiasing Techniques for Pre-trained Language Models","created":"2021-10-16","cited_by_count":97},{"id":"2008.06460","title":"Hate Speech Detection and Racial Bias Mitigation in Social Media based on BERT model","created":"2020-08-14","cited_by_count":87},{"id":"2109.04650","title":"What Changes Can Large-scale Language Models Bring? Intensive Study on HyperCLOVA: Billions-scale Korean Generative Pretrained Transformers","created":"2021-09-10","cited_by_count":76},{"id":"1707.00061","title":"Racial Disparity in Natural Language Processing: A Case Study of Social Media African-American English","created":"2017-06-30","cited_by_count":71},{"id":"2212.14402","title":"GPT Takes the Bar Exam","created":"2022-12-29","cited_by_count":65},{"id":"1907.07237","title":"FAHT: An Adaptive Fairness-aware Decision Tree Classifier","created":"2019-07-16","cited_by_count":63},{"id":"2208.01448","title":"AlexaTM 20B: Few-Shot Learning Using a Large-Scale Multilingual Seq2Seq Model","created":"2022-08-02","cited_by_count":57},{"id":"2210.11399","title":"Transcending Scaling Laws with 0.1% Extra Compute","created":"2022-10-20","cited_by_count":57},{"id":"2306.05550","title":"Bias Against 93 Stigmatized Groups in Masked Language Models and Downstream Sentiment Classification Tasks","created":"2023-06-08","cited_by_count":51},{"id":"2305.13272","title":"CLASS: A Design Framework for building Intelligent Tutoring Systems based on Learning Science principles","created":"2023-05-22","cited_by_count":48},{"id":"2212.08109","title":"An Empirical Study of Deep Learning Models for Vulnerability Detection","created":"2022-12-15","cited_by_count":46},{"id":"2108.07403","title":"FARF: A Fair and Adaptive Random Forests Classifier","created":"2021-08-17","cited_by_count":37},{"id":"1904.09408","title":"Language Models with Transformers","created":"2019-04-20","cited_by_count":36},{"id":"2304.13714","title":"Evaluation of GPT-3.5 and GPT-4 for supporting real-world information needs in healthcare delivery","created":"2023-04-26","cited_by_count":30},{"id":"2310.05595","title":"Decoding the Threat Landscape : ChatGPT, FraudGPT, and WormGPT in Social Engineering Attacks","created":"2023-10-09","cited_by_count":23},{"id":"2203.16024","title":"Longitudinal Fairness with Censorship","created":"2022-03-30","cited_by_count":22},{"id":"2203.10965","title":"PTM4Tag: Sharpening Tag Recommendation of Stack Overflow Posts with Pre-trained Models","created":"2022-03-21","cited_by_count":16},{"id":"2309.08859","title":"Rethinking Learning Rate Tuning in the Era of Large Language Models","created":"2023-09-16","cited_by_count":16},{"id":"2301.12364","title":"Fair Decision-making Under Uncertainty","created":"2023-01-29","cited_by_count":15},{"id":"2302.08017","title":"Preventing Discriminatory Decision-making in Evolving Data Streams","created":"2023-02-16","cited_by_count":12},{"id":"2302.08015","title":"Individual Fairness under Uncertainty","created":"2023-02-16","cited_by_count":11},{"id":"2308.05935","title":"LittleMu: Deploying an Online Virtual Teaching Assistant via Heterogeneous Sources Integration and Chain of Teach Prompts","created":"2023-08-11","cited_by_count":9},{"id":"2309.08112","title":"Empowering Private Tutoring by Chaining Large Language Models","created":"2023-09-15","cited_by_count":9},{"id":"2303.06853","title":"Representation Learning for Stack Overflow Posts: How Far are We?","created":"2023-03-13","cited_by_count":6},{"id":"2005.13665","title":"Deep Learning for Portfolio Optimization","created":"2020-05-27","cited_by_count":4},{"id":"2209.10868","title":"Answer Summarization for Technical Queries: Benchmark and New Approach","created":"2022-09-22","cited_by_count":4},{"id":"2301.03489","title":"Unveiling and Mitigating Bias in Ride-Hailing Pricing for Equitable Policy Making","created":"2023-01-09","cited_by_count":3}],"next_cursor":null}