{"list":"other","total":60,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"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":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"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":"2212.08073","title":"Constitutional AI: Harmlessness from AI Feedback","created":"2022-12-15","cited_by_count":3050},{"id":"2311.12022","title":"GPQA: A Graduate-Level Google-Proof Q&A Benchmark","created":"2023-11-20","cited_by_count":2879},{"id":"2101.00027","title":"The Pile: An 800GB Dataset of Diverse Text for Language Modeling","created":"2020-12-31","cited_by_count":2411},{"id":"2211.05100","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","created":"2022-11-09","cited_by_count":1984},{"id":"2006.05525","title":"Knowledge Distillation: A Survey","created":"2020-06-09","cited_by_count":1603},{"id":"2305.13245","title":"GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints","created":"2023-05-22","cited_by_count":1346},{"id":"1904.03323","title":"Publicly Available Clinical BERT Embeddings","created":"2019-04-06","cited_by_count":1002},{"id":"1903.00161","title":"DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs","created":"2019-03-01","cited_by_count":903},{"id":"2204.06745","title":"GPT-NeoX-20B: An Open-Source Autoregressive Language Model","created":"2022-04-14","cited_by_count":713},{"id":"2403.14608","title":"Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey","created":"2024-03-21","cited_by_count":656},{"id":"2402.00838","title":"OLMo: Accelerating the Science of Language Models","created":"2024-02-01","cited_by_count":613},{"id":"2311.16867","title":"The Falcon Series of Open Language Models","created":"2023-11-28","cited_by_count":535},{"id":"2402.06196","title":"Large Language Models: A Survey","created":"2024-02-09","cited_by_count":525},{"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":"2401.00595","title":"State of What Art? A Call for Multi-Prompt LLM Evaluation","created":"2023-12-31","cited_by_count":310},{"id":"2409.02060","title":"OLMoE: Open Mixture-of-Experts Language Models","created":"2024-09-03","cited_by_count":301},{"id":"2402.07827","title":"Aya Model: An Instruction Finetuned Open-Access Multilingual Language Model","created":"2024-02-12","cited_by_count":295},{"id":"2401.00396","title":"RAGTruth: A Hallucination Corpus for Developing Trustworthy Retrieval-Augmented Language Models","created":"2023-12-31","cited_by_count":283},{"id":"2305.15717","title":"The False Promise of Imitating Proprietary LLMs","created":"2023-05-25","cited_by_count":263},{"id":"2309.11235","title":"OpenChat: Advancing Open-source Language Models with Mixed-Quality Data","created":"2023-09-20","cited_by_count":252},{"id":"2308.00951","title":"From Sparse to Soft Mixtures of Experts","created":"2023-08-02","cited_by_count":248},{"id":"2402.03927","title":"Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMs","created":"2024-02-06","cited_by_count":229},{"id":"2312.03863","title":"Efficient Large Language Models: A Survey","created":"2023-12-06","cited_by_count":186},{"id":"2302.08500","title":"Auditing large language models: a three-layered approach","created":"2023-02-16","cited_by_count":137},{"id":"2409.11402","title":"NVLM: Open Frontier-Class Multimodal LLMs","created":"2024-09-17","cited_by_count":125},{"id":"2306.01941","title":"AI Transparency in the Age of LLMs: A Human-Centered Research Roadmap","created":"2023-06-02","cited_by_count":123},{"id":"2402.01761","title":"Rethinking Interpretability in the Era of Large Language Models","created":"2024-01-30","cited_by_count":111},{"id":"2312.06550","title":"LLM360: Towards Fully Transparent Open-Source LLMs","created":"2023-12-11","cited_by_count":104},{"id":"2406.02622","title":"Safeguarding Large Language Models: A Survey","created":"2024-06-03","cited_by_count":78},{"id":"2408.13296","title":"The Ultimate Guide to Fine-Tuning LLMs from Basics to Breakthroughs: An Exhaustive Review of Technologies, Research, Best Practices, Applied Research Challenges and Opportunities","created":"2024-08-23","cited_by_count":64},{"id":"2410.13639","title":"A Comparative Study on Reasoning Patterns of OpenAI's o1 Model","created":"2024-10-17","cited_by_count":63},{"id":"2307.05532","title":"Opening up ChatGPT: Tracking openness, transparency, and accountability in instruction-tuned text generators","created":"2023-07-08","cited_by_count":56},{"id":"2105.03036","title":"SpeechMoE: Scaling to Large Acoustic Models with Dynamic Routing Mixture of Experts","created":"2021-05-07","cited_by_count":48},{"id":"2403.14473","title":"The Ethics of ChatGPT in Medicine and Healthcare: A Systematic Review on Large Language Models (LLMs)","created":"2024-03-21","cited_by_count":45},{"id":"2402.06094","title":"Rethinking Data Selection for Supervised Fine-Tuning","created":"2024-02-08","cited_by_count":35},{"id":"2308.10092","title":"Open, Closed, or Small Language Models for Text Classification?","created":"2023-08-19","cited_by_count":34},{"id":"2311.09227","title":"Open-Sourcing Highly Capable Foundation Models: An evaluation of risks, benefits, and alternative methods for pursuing open-source objectives","created":"2023-09-29","cited_by_count":31},{"id":"2403.10776","title":"From Melting Pots to Misrepresentations: Exploring Harms in Generative AI","created":"2024-03-16","cited_by_count":13},{"id":"2310.07611","title":"Democratizing LLMs: An Exploration of Cost-Performance Trade-offs in Self-Refined Open-Source Models","created":"2023-10-11","cited_by_count":11},{"id":"2402.15100","title":"Studying LLM Performance on Closed- and Open-source Data","created":"2024-02-23","cited_by_count":11},{"id":"2405.02803","title":"Is Flash Attention Stable?","created":"2024-05-05","cited_by_count":10},{"id":"2309.16134","title":"Let's Chat to Find the APIs: Connecting Human, LLM and Knowledge Graph through AI Chain","created":"2023-09-28","cited_by_count":7},{"id":"2409.16559","title":"Demystifying Issues, Causes and Solutions in LLM Open-Source Projects","created":"2024-09-25","cited_by_count":3},{"id":"1903.05277","title":"Activity-Based Analysis of Open Source Software Contributors: Roles and Dynamics","created":"2019-03-13","cited_by_count":2},{"id":"2410.01810","title":"Propaganda is all you need","created":"2024-09-13","cited_by_count":1}],"next_cursor":null}