{"list":"other","total":59,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"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":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"1603.02754","title":"XGBoost: A Scalable Tree Boosting System","created":"2016-03-09","cited_by_count":5166},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"2211.05100","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","created":"2022-11-09","cited_by_count":1984},{"id":"2306.00978","title":"AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration","created":"2023-06-01","cited_by_count":1298},{"id":"2206.10789","title":"Scaling Autoregressive Models for Content-Rich Text-to-Image Generation","created":"2022-06-22","cited_by_count":1295},{"id":"2104.00298","title":"EfficientNetV2: Smaller Models and Faster Training","created":"2021-04-01","cited_by_count":1135},{"id":"2209.11895","title":"In-context Learning and Induction Heads","created":"2022-09-24","cited_by_count":964},{"id":"2005.00661","title":"On Faithfulness and Factuality in Abstractive Summarization","created":"2020-05-02","cited_by_count":900},{"id":"2205.05638","title":"Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning","created":"2022-05-11","cited_by_count":896},{"id":"2103.07191","title":"Are NLP Models really able to Solve Simple Math Word Problems?","created":"2021-03-12","cited_by_count":878},{"id":"2103.13630","title":"A Survey of Quantization Methods for Efficient Neural Network Inference","created":"2021-03-25","cited_by_count":815},{"id":"2303.16199","title":"LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention","created":"2023-03-28","cited_by_count":781},{"id":"2109.00122","title":"FinQA: A Dataset of Numerical Reasoning over Financial Data","created":"2021-09-01","cited_by_count":562},{"id":"2403.02310","title":"Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve","created":"2024-03-04","cited_by_count":526},{"id":"2402.06196","title":"Large Language Models: A Survey","created":"2024-02-09","cited_by_count":525},{"id":"2106.08295","title":"A White Paper on Neural Network Quantization","created":"2021-06-15","cited_by_count":472},{"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":"2401.11817","title":"Hallucination is Inevitable: An Innate Limitation of Large Language Models","created":"2024-01-22","cited_by_count":332},{"id":"2106.04489","title":"Parameter-efficient Multi-task Fine-tuning for Transformers via Shared Hypernetworks","created":"2021-06-08","cited_by_count":284},{"id":"2311.11944","title":"FinanceBench: A New Benchmark for Financial Question Answering","created":"2023-11-20","cited_by_count":270},{"id":"2311.10723","title":"Large Language Models in Finance: A Survey","created":"2023-09-28","cited_by_count":226},{"id":"2210.03849","title":"ConvFinQA: Exploring the Chain of Numerical Reasoning in Conversational Finance Question Answering","created":"2022-10-07","cited_by_count":196},{"id":"2403.03883","title":"SaulLM-7B: A pioneering Large Language Model for Law","created":"2024-03-06","cited_by_count":142},{"id":"2304.07619","title":"Can ChatGPT Forecast Stock Price Movements? Return Predictability and Large Language Models","created":"2023-04-15","cited_by_count":129},{"id":"2401.00908","title":"DocLLM: A layout-aware generative language model for multimodal document understanding","created":"2023-12-31","cited_by_count":116},{"id":"2401.11641","title":"Revolutionizing Finance with LLMs: An Overview of Applications and Insights","created":"2024-01-22","cited_by_count":90},{"id":"2203.04291","title":"Learning from Few Examples: A Summary of Approaches to Few-Shot Learning","created":"2022-03-07","cited_by_count":86},{"id":"2107.09051","title":"AI in Finance: Challenges, Techniques and Opportunities","created":"2021-07-20","cited_by_count":81},{"id":"2401.14351","title":"ServerlessLLM: Low-Latency Serverless Inference for Large Language Models","created":"2024-01-25","cited_by_count":80},{"id":"2402.02315","title":"A Survey of Large Language Models in Finance (FinLLMs)","created":"2024-02-04","cited_by_count":79},{"id":"2307.03941","title":"Right to be Forgotten in the Era of Large Language Models: Implications, Challenges, and Solutions","created":"2023-07-08","cited_by_count":60},{"id":"2305.05862","title":"Are ChatGPT and GPT-4 General-Purpose Solvers for Financial Text Analytics? A Study on Several Typical Tasks","created":"2023-05-10","cited_by_count":59},{"id":"1305.2982","title":"Estimating or Propagating Gradients Through Stochastic Neurons","created":"2013-05-14","cited_by_count":55},{"id":"2408.04693","title":"Understanding the Performance and Estimating the Cost of LLM Fine-Tuning","created":"2024-08-08","cited_by_count":48},{"id":"2309.09558","title":"Summarization is (Almost) Dead","created":"2023-09-18","cited_by_count":44},{"id":"2401.03737","title":"Can Large Language Models Beat Wall Street? Unveiling the Potential of AI in Stock Selection","created":"2024-01-08","cited_by_count":29},{"id":"2404.10779","title":"Fine Tuning LLM for Enterprise: Practical Guidelines and Recommendations","created":"2024-03-23","cited_by_count":28},{"id":"2401.00081","title":"Synthetic Data Applications in Finance","created":"2023-12-29","cited_by_count":22},{"id":"2311.09008","title":"End-to-end Task-oriented Dialogue: A Survey of Tasks, Methods, and Future Directions","created":"2023-11-15","cited_by_count":17},{"id":"2404.05101","title":"StockGPT: A GenAI Model for Stock Prediction and Trading","created":"2024-04-07","cited_by_count":11},{"id":"2407.12797","title":"CEBench: A Benchmarking Toolkit for the Cost-Effectiveness of LLM Pipelines","created":"2024-06-20","cited_by_count":11},{"id":"2403.15756","title":"Leveraging Large Language Models for Preliminary Security Risk Analysis: A Mission-Critical Case Study","created":"2024-03-23","cited_by_count":10},{"id":"2406.14319","title":"LiveMind: Low-latency Large Language Models with Simultaneous Inference","created":"2024-06-20","cited_by_count":10},{"id":"2402.09728","title":"AbuseGPT: Abuse of Generative AI ChatBots to Create Smishing Campaigns","created":"2024-02-15","cited_by_count":9},{"id":"2408.02006","title":"LLaSA: Large Language and E-Commerce Shopping Assistant","created":"2024-08-04","cited_by_count":8},{"id":"2401.06164","title":"Multimodal Gen-AI for Fundamental Investment Research","created":"2023-12-24","cited_by_count":7},{"id":"1808.09940","title":"Adversarial Deep Reinforcement Learning in Portfolio Management","created":"2018-08-29","cited_by_count":6},{"id":"2308.16538","title":"The AI Revolution: Opportunities and Challenges for the Finance Sector","created":"2023-08-31","cited_by_count":6},{"id":"2212.13312","title":"Users really do respond to smishing","created":"2022-12-26","cited_by_count":4},{"id":"2404.03523","title":"Integrating Generative AI into Financial Market Prediction for Improved Decision Making","created":"2024-04-04","cited_by_count":4},{"id":"2310.17826","title":"OmniFill: Domain-Agnostic Form Filling Suggestions Using Multi-Faceted Context","created":"2023-10-27","cited_by_count":2}],"next_cursor":null}