{"list":"other","total":69,"rows":[{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"id":"2312.10997","title":"Retrieval-Augmented Generation for Large Language Models: A Survey","created":"2023-12-18","cited_by_count":2212},{"id":"2202.03629","title":"Survey of Hallucination in Natural Language Generation","created":"2022-02-08","cited_by_count":2075},{"id":"2210.17323","title":"GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers","created":"2022-10-31","cited_by_count":1919},{"id":"2006.04779","title":"Conservative Q-Learning for Offline Reinforcement Learning","created":"2020-06-08","cited_by_count":1809},{"id":"1509.06461","title":"Deep Reinforcement Learning with Double Q-learning","created":"2015-09-22","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":"2211.10438","title":"SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models","created":"2022-11-18","cited_by_count":1386},{"id":"2306.00978","title":"AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration","created":"2023-06-01","cited_by_count":1298},{"id":"2312.06674","title":"Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations","created":"2023-12-07","cited_by_count":1207},{"id":"2311.12983","title":"GAIA: a benchmark for General AI Assistants","created":"2023-11-21","cited_by_count":1128},{"id":"2301.00774","title":"SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot","created":"2023-01-02","cited_by_count":1121},{"id":"2005.00661","title":"On Faithfulness and Factuality in Abstractive Summarization","created":"2020-05-02","cited_by_count":900},{"id":"2306.11695","title":"A Simple and Effective Pruning Approach for Large Language Models","created":"2023-06-20","cited_by_count":800},{"id":"2305.02301","title":"Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes","created":"2023-05-03","cited_by_count":737},{"id":"2305.11627","title":"LLM-Pruner: On the Structural Pruning of Large Language Models","created":"2023-05-19","cited_by_count":650},{"id":"2307.06435","title":"A Comprehensive Overview of Large Language Models","created":"2023-07-12","cited_by_count":648},{"id":"2304.05376","title":"ChemCrow: Augmenting large-language models with chemistry tools","created":"2023-04-11","cited_by_count":631},{"id":"2303.06865","title":"FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU","created":"2023-03-13","cited_by_count":575},{"id":"2206.01861","title":"ZeroQuant: Efficient and Affordable Post-Training Quantization for Large-Scale Transformers","created":"2022-06-04","cited_by_count":526},{"id":"1708.05866","title":"A Brief Survey of Deep Reinforcement Learning","created":"2017-08-19","cited_by_count":483},{"id":"2305.17888","title":"LLM-QAT: Data-Free Quantization Aware Training for Large Language Models","created":"2023-05-29","cited_by_count":324},{"id":"2309.02705","title":"Certifying LLM Safety against Adversarial Prompting","created":"2023-09-06","cited_by_count":266},{"id":"2407.01502","title":"AI Agents That Matter","created":"2024-07-01","cited_by_count":219},{"id":"2402.05930","title":"WebLINX: Real-World Website Navigation with Multi-Turn Dialogue","created":"2024-02-08","cited_by_count":180},{"id":"1810.05587","title":"A Survey and Critique of Multiagent Deep Reinforcement Learning","created":"2018-10-12","cited_by_count":177},{"id":"2312.11514","title":"LLM in a flash: Efficient Large Language Model Inference with Limited Memory","created":"2023-12-12","cited_by_count":177},{"id":"2401.03568","title":"Agent AI: Surveying the Horizons of Multimodal Interaction","created":"2024-01-07","cited_by_count":170},{"id":"2404.15155","title":"MDAgents: An Adaptive Collaboration of LLMs for Medical Decision-Making","created":"2024-04-22","cited_by_count":163},{"id":"2402.08567","title":"Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast","created":"2024-02-13","cited_by_count":153},{"id":"2311.07562","title":"GPT-4V in Wonderland: Large Multimodal Models for Zero-Shot Smartphone GUI Navigation","created":"2023-11-13","cited_by_count":137},{"id":"2402.18485","title":"A Multimodal Foundation Agent for Financial Trading: Tool-Augmented, Diversified, and Generalist","created":"2024-02-28","cited_by_count":137},{"id":"2407.19354","title":"The Emerged Security and Privacy of LLM Agent: A Survey with Case Studies","created":"2024-07-28","cited_by_count":131},{"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":"1812.11794","title":"Deep Reinforcement Learning for Multi-Agent Systems: A Review of Challenges, Solutions and Applications","created":"2018-12-31","cited_by_count":127},{"id":"2310.01557","title":"SmartPlay: A Benchmark for LLMs as Intelligent Agents","created":"2023-10-02","cited_by_count":125},{"id":"2412.05563","title":"A Survey on Uncertainty Quantification of Large Language Models: Taxonomy, Open Research Challenges, and Future Directions","created":"2024-12-07","cited_by_count":121},{"id":"2405.15589","title":"Efficient Adversarial Training in LLMs with Continuous Attacks","created":"2024-05-24","cited_by_count":113},{"id":"2408.02479","title":"From LLMs to LLM-based Agents for Software Engineering: A Survey of Current, Challenges and Future","created":"2024-08-05","cited_by_count":86},{"id":"2502.18036","title":"Harnessing Multiple Large Language Models: A Survey on LLM Ensemble","created":"2025-02-25","cited_by_count":86},{"id":"2502.11211","title":"A Survey of LLM-based Agents in Medicine: How far are we from Baymax?","created":"2025-02-16","cited_by_count":85},{"id":"2406.02622","title":"Safeguarding Large Language Models: A Survey","created":"2024-06-03","cited_by_count":78},{"id":"2406.16937","title":"A Complete Survey on LLM-based AI Chatbots","created":"2024-06-17","cited_by_count":71},{"id":"2402.01822","title":"Building Guardrails for Large Language Models","created":"2024-02-02","cited_by_count":65},{"id":"2401.03868","title":"FlightLLM: Efficient Large Language Model Inference with a Complete Mapping Flow on FPGAs","created":"2024-01-08","cited_by_count":64},{"id":"2409.18807","title":"LLM With Tools: A Survey","created":"2024-09-24","cited_by_count":61},{"id":"2408.06361","title":"Large Language Model Agent in Financial Trading: A Survey","created":"2024-07-26","cited_by_count":60},{"id":"2503.11733","title":"LLM Agents for Education: Advances and Applications","created":"2025-03-14","cited_by_count":59},{"id":"2308.02019","title":"Baby Llama: knowledge distillation from an ensemble of teachers trained on a small dataset with no performance penalty","created":"2023-08-03","cited_by_count":57},{"id":"2308.00016","title":"Alpha-GPT: Human-AI Interactive Alpha Mining for Quantitative Investment","created":"2023-07-31","cited_by_count":56},{"id":"2410.12855","title":"JAILJUDGE: A Comprehensive Jailbreak Judge Benchmark with Multi-Agent Enhanced Explanation Evaluation Framework","created":"2024-10-11","cited_by_count":47},{"id":"2310.07018","title":"NEWTON: Are Large Language Models Capable of Physical Reasoning?","created":"2023-10-10","cited_by_count":45},{"id":"2009.08605","title":"Hardware Accelerator for Multi-Head Attention and Position-Wise Feed-Forward in the Transformer","created":"2020-09-18","cited_by_count":43},{"id":"2404.07963","title":"EduAgent: Generative Student Agents in Learning","created":"2024-03-23","cited_by_count":42},{"id":"2210.15042","title":"Privately Fine-Tuning Large Language Models with Differential Privacy","created":"2022-10-26","cited_by_count":39},{"id":"2405.02213","title":"Automatic Programming: Large Language Models and Beyond","created":"2024-05-03","cited_by_count":36},{"id":"2502.17516","title":"A Survey on Mechanistic Interpretability for Multi-Modal Foundation Models","created":"2025-02-22","cited_by_count":34},{"id":"2405.14487","title":"A Comprehensive Overview of Large Language Models (LLMs) for Cyber Defences: Opportunities and Directions","created":"2024-05-23","cited_by_count":33},{"id":"2406.10811","title":"LLMFactor: Extracting Profitable Factors through Prompts for Explainable Stock Movement Prediction","created":"2024-06-16","cited_by_count":33},{"id":"2402.03755","title":"QuantAgent: Seeking Holy Grail in Trading by Self-Improving Large Language Model","created":"2024-02-06","cited_by_count":30},{"id":"2403.13313","title":"Polaris: A Safety-focused LLM Constellation Architecture for Healthcare","created":"2024-03-20","cited_by_count":28},{"id":"2410.04078","title":"TeachTune: Reviewing Pedagogical Agents Against Diverse Student Profiles with Simulated Students","created":"2024-10-05","cited_by_count":25},{"id":"2410.21418","title":"Large Language Models for Manufacturing","created":"2024-10-28","cited_by_count":24},{"id":"2503.18132","title":"MathAgent: Leveraging a Mixture-of-Math-Agent Framework for Real-World Multimodal Mathematical Error Detection","created":"2025-03-23","cited_by_count":24},{"id":"2405.15690","title":"A Case Study of LLM for Automated Vulnerability Repair: Assessing Impact of Reasoning and Patch Validation Feedback","created":"2024-05-24","cited_by_count":22},{"id":"2411.06535","title":"Probabilistic Consensus through Ensemble Validation: A Framework for LLM Reliability","created":"2024-11-10","cited_by_count":9},{"id":"2404.07960","title":"Content Knowledge Identification with Multi-Agent Large Language Models (LLMs)","created":"2024-03-22","cited_by_count":6},{"id":"2502.01702","title":"Al-Khwarizmi: Discovering Physical Laws with Foundation Models","created":"2025-02-03","cited_by_count":5}],"next_cursor":null}