{"list":"other","total":56,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"id":"2212.08073","title":"Constitutional AI: Harmlessness from AI Feedback","created":"2022-12-15","cited_by_count":3050},{"id":"2308.11432","title":"A Survey on Large Language Model based Autonomous Agents","created":"2023-08-22","cited_by_count":2242},{"id":"2503.09516","title":"Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning","created":"2025-03-12","cited_by_count":1444},{"id":"2309.07864","title":"The Rise and Potential of Large Language Model Based Agents: A Survey","created":"2023-09-14","cited_by_count":1439},{"id":"2212.03533","title":"Text Embeddings by Weakly-Supervised Contrastive Pre-training","created":"2022-12-07","cited_by_count":1253},{"id":"2112.09118","title":"Unsupervised Dense Information Retrieval with Contrastive Learning","created":"2021-12-16","cited_by_count":1216},{"id":"2402.01680","title":"Large Language Model based Multi-Agents: A Survey of Progress and Challenges","created":"2024-01-21","cited_by_count":769},{"id":"2304.05302","title":"RRHF: Rank Responses to Align Language Models with Human Feedback without tears","created":"2023-04-11","cited_by_count":463},{"id":"1708.04782","title":"StarCraft II: A New Challenge for Reinforcement Learning","created":"2017-08-16","cited_by_count":274},{"id":"2506.02153","title":"Small Language Models are the Future of Agentic AI","created":"2025-06-02","cited_by_count":270},{"id":"2309.15025","title":"Large Language Model Alignment: A Survey","created":"2023-09-26","cited_by_count":243},{"id":"2305.16867","title":"Playing repeated games with Large Language Models","created":"2023-05-26","cited_by_count":217},{"id":"2305.10142","title":"Improving Language Model Negotiation with Self-Play and In-Context Learning from AI Feedback","created":"2023-05-17","cited_by_count":207},{"id":"2303.13780","title":"Towards Making the Most of ChatGPT for Machine Translation","created":"2023-03-24","cited_by_count":138},{"id":"2211.14876","title":"Dense Text Retrieval based on Pretrained Language Models: A Survey","created":"2022-11-27","cited_by_count":136},{"id":"2401.01879","title":"Theoretical guarantees on the best-of-n alignment policy","created":"2024-01-03","cited_by_count":124},{"id":"2304.04339","title":"Is ChatGPT a Good Sentiment Analyzer? A Preliminary Study","created":"2023-04-10","cited_by_count":96},{"id":"2305.11171","title":"TrueTeacher: Learning Factual Consistency Evaluation with Large Language Models","created":"2023-05-18","cited_by_count":83},{"id":"2503.00223","title":"DeepRetrieval: Hacking Real Search Engines and Retrievers with Large Language Models via Reinforcement Learning","created":"2025-02-28","cited_by_count":66},{"id":"2310.17512","title":"CompeteAI: Understanding the Competition Dynamics in Large Language Model-based Agents","created":"2023-10-26","cited_by_count":65},{"id":"2304.04193","title":"Extractive Summarization via ChatGPT for Faithful Summary Generation","created":"2023-04-09","cited_by_count":59},{"id":"2310.00212","title":"Pairwise Proximal Policy Optimization: Harnessing Relative Feedback for LLM Alignment","created":"2023-09-30","cited_by_count":57},{"id":"2406.11827","title":"WPO: Enhancing RLHF with Weighted Preference Optimization","created":"2024-06-17","cited_by_count":54},{"id":"2504.16078","title":"LLMs are Greedy Agents: Effects of RL Fine-tuning on Decision-Making Abilities","created":"2025-04-22","cited_by_count":41},{"id":"2311.03220","title":"ALYMPICS: LLM Agents Meet Game Theory -- Exploring Strategic Decision-Making with AI Agents","created":"2023-11-06","cited_by_count":33},{"id":"2402.09552","title":"STEER: Assessing the Economic Rationality of Large Language Models","created":"2024-02-14","cited_by_count":27},{"id":"2302.06474","title":"Applying BERT and ChatGPT for Sentiment Analysis of Lyme Disease in Scientific Literature","created":"2023-02-07","cited_by_count":26},{"id":"2410.19744","title":"Towards Next-Generation LLM-based Recommender Systems: A Survey and Beyond","created":"2024-10-10","cited_by_count":26},{"id":"2507.10865","title":"Overview of the TREC 2022 deep learning track","created":"2025-07-10","cited_by_count":22},{"id":"2410.05254","title":"GLEE: A Unified Framework and Benchmark for Language-based Economic Environments","created":"2024-10-07","cited_by_count":20},{"id":"2401.01735","title":"Economics Arena for Large Language Models","created":"2024-01-03","cited_by_count":17},{"id":"2409.02795","title":"Towards a Unified View of Preference Learning for Large Language Models: A Survey","created":"2024-09-04","cited_by_count":17},{"id":"2501.09186","title":"Guiding Retrieval using LLM-based Listwise Rankers","created":"2025-01-15","cited_by_count":16},{"id":"2406.02081","title":"FightLadder: A Benchmark for Competitive Multi-Agent Reinforcement Learning","created":"2024-06-04","cited_by_count":13},{"id":"2401.17435","title":"Can LLMs Replace Economic Choice Prediction Labs? The Case of Language-based Persuasion Games","created":"2024-01-30","cited_by_count":12},{"id":"2406.00024","title":"Embedding-Aligned Language Models","created":"2024-05-24","cited_by_count":9},{"id":"1912.01901","title":"WIKIR: A Python toolkit for building a large-scale Wikipedia-based English Information Retrieval Dataset","created":"2019-12-04","cited_by_count":8},{"id":"2305.10361","title":"Human Choice Prediction in Language-based Persuasion Games: Simulation-based Off-Policy Evaluation","created":"2023-05-17","cited_by_count":8},{"id":"2502.13119","title":"STEER-ME: Assessing the Microeconomic Reasoning of Large Language Models","created":"2025-02-18","cited_by_count":7},{"id":"1806.05359","title":"Convergence of Learning Dynamics in Information Retrieval Games","created":"2018-06-14","cited_by_count":5},{"id":"2411.13187","title":"Engagement-Driven Content Generation with Large Language Models","created":"2024-11-20","cited_by_count":5},{"id":"2501.16355","title":"How Strategic Agents Respond: Comparing Analytical Models with LLM-Generated Responses in Strategic Classification","created":"2025-01-20","cited_by_count":5},{"id":"2305.16695","title":"The Search for Stability: Learning Dynamics of Strategic Publishers with Initial Documents","created":"2023-05-26","cited_by_count":4},{"id":"2405.11517","title":"On the Convergence of No-Regret Dynamics in Information Retrieval Games with Proportional Ranking Functions","created":"2024-05-19","cited_by_count":3},{"id":"2507.11042","title":"Aligned Query Expansion: Efficient Query Expansion for Information Retrieval through LLM Alignment","created":"2025-07-15","cited_by_count":3},{"id":"2412.15878","title":"On the Power of Strategic Corpus Enrichment in Content Creation Games","created":"2024-12-20","cited_by_count":1}],"next_cursor":null}