{"list":"other","total":51,"rows":[{"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":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"id":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"id":"2302.04761","title":"Toolformer: Language Models Can Teach Themselves to Use Tools","created":"2023-02-09","cited_by_count":4182},{"id":"2004.04906","title":"Dense Passage Retrieval for Open-Domain Question Answering","created":"2020-04-10","cited_by_count":3824},{"id":"2305.10601","title":"Tree of Thoughts: Deliberate Problem Solving with Large Language Models","created":"2023-05-17","cited_by_count":3211},{"id":"2503.14476","title":"DAPO: An Open-Source LLM Reinforcement Learning System at Scale","created":"2025-03-18","cited_by_count":2810},{"id":"1506.02438","title":"High-Dimensional Continuous Control Using Generalized Advantage Estimation","created":"2015-06-08","cited_by_count":2026},{"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":"2203.14465","title":"STaR: Bootstrapping Reasoning With Reasoning","created":"2022-03-28","cited_by_count":940},{"id":"2212.10509","title":"Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions","created":"2022-12-20","cited_by_count":923},{"id":"2305.14992","title":"Reasoning with Language Model is Planning with World Model","created":"2023-05-24","cited_by_count":861},{"id":"2309.01219","title":"Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models","created":"2023-09-03","cited_by_count":698},{"id":"2304.11277","title":"PyTorch FSDP: Experiences on Scaling Fully Sharded Data Parallel","created":"2023-04-21","cited_by_count":660},{"id":"2305.06983","title":"Active Retrieval Augmented Generation","created":"2023-05-11","cited_by_count":516},{"id":"2501.05366","title":"Search-o1: Agentic Search-Enhanced Large Reasoning Models","created":"2025-01-09","cited_by_count":433},{"id":"2308.01825","title":"Scaling Relationship on Learning Mathematical Reasoning with Large Language Models","created":"2023-08-03","cited_by_count":427},{"id":"2305.09645","title":"StructGPT: A General Framework for Large Language Model to Reason over Structured Data","created":"2023-05-16","cited_by_count":343},{"id":"2310.01061","title":"Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning","created":"2023-10-02","cited_by_count":328},{"id":"2402.07630","title":"G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering","created":"2024-02-12","cited_by_count":223},{"id":"1904.09537","title":"PullNet: Open Domain Question Answering with Iterative Retrieval on Knowledge Bases and Text","created":"2019-04-21","cited_by_count":184},{"id":"2011.07743","title":"Beyond I.I.D.: Three Levels of Generalization for Question Answering on Knowledge Bases","created":"2020-11-16","cited_by_count":171},{"id":"1809.00782","title":"Open Domain Question Answering Using Early Fusion of Knowledge Bases and Text","created":"2018-09-04","cited_by_count":168},{"id":"2211.14876","title":"Dense Text Retrieval based on Pretrained Language Models: A Survey","created":"2022-11-27","cited_by_count":136},{"id":"2101.03737","title":"Improving Multi-hop Knowledge Base Question Answering by Learning Intermediate Supervision Signals","created":"2021-01-11","cited_by_count":101},{"id":"2202.13296","title":"Subgraph Retrieval Enhanced Model for Multi-hop Knowledge Base Question Answering","created":"2022-02-27","cited_by_count":93},{"id":"2402.11163","title":"KG-Agent: An Efficient Autonomous Agent Framework for Complex Reasoning over Knowledge Graph","created":"2024-02-17","cited_by_count":93},{"id":"2109.08678","title":"RnG-KBQA: Generation Augmented Iterative Ranking for Knowledge Base Question Answering","created":"2021-09-17","cited_by_count":86},{"id":"2210.00063","title":"DecAF: Joint Decoding of Answers and Logical Forms for Question Answering over Knowledge Bases","created":"2022-09-30","cited_by_count":84},{"id":"2410.20724","title":"Simple Is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generation","created":"2024-10-28","cited_by_count":80},{"id":"2410.23875","title":"Plan-on-Graph: Self-Correcting Adaptive Planning of Large Language Model on Knowledge Graphs","created":"2024-10-31","cited_by_count":78},{"id":"2305.01750","title":"Few-shot In-context Learning for Knowledge Base Question Answering","created":"2023-05-02","cited_by_count":74},{"id":"2503.21322","title":"HyperGraphRAG: Retrieval-Augmented Generation via Hypergraph-Structured Knowledge Representation","created":"2025-03-27","cited_by_count":68},{"id":"2407.10805","title":"Think-on-Graph 2.0: Deep and Faithful Large Language Model Reasoning with Knowledge-guided Retrieval Augmented Generation","created":"2024-07-15","cited_by_count":64},{"id":"2210.12925","title":"TIARA: Multi-grained Retrieval for Robust Question Answering over Large Knowledge Bases","created":"2022-10-24","cited_by_count":59},{"id":"2212.09736","title":"Don't Generate, Discriminate: A Proposal for Grounding Language Models to Real-World Environments","created":"2022-12-19","cited_by_count":57},{"id":"2507.21892","title":"Graph-R1: Towards Agentic GraphRAG Framework via End-to-end Reinforcement Learning","created":"2025-07-29","cited_by_count":52},{"id":"2204.08109","title":"ArcaneQA: Dynamic Program Induction and Contextualized Encoding for Knowledge Base Question Answering","created":"2022-04-17","cited_by_count":48},{"id":"2003.13956","title":"SPARQA: Skeleton-based Semantic Parsing for Complex Questions over Knowledge Bases","created":"2020-03-31","cited_by_count":47},{"id":"2310.08975","title":"ChatKBQA: A Generate-then-Retrieve Framework for Knowledge Base Question Answering with Fine-tuned Large Language Models","created":"2023-10-13","cited_by_count":44},{"id":"2403.11886","title":"QueryAgent: A Reliable and Efficient Reasoning Framework with Environmental Feedback-based Self-Correction","created":"2024-03-18","cited_by_count":27},{"id":"2402.15131","title":"Interactive-KBQA: Multi-Turn Interactions for Knowledge Base Question Answering with Large Language Models","created":"2024-02-23","cited_by_count":25},{"id":"2501.18922","title":"KBQA-o1: Agentic Knowledge Base Question Answering with Monte Carlo Tree Search","created":"2025-01-31","cited_by_count":22},{"id":"2306.14722","title":"FC-KBQA: A Fine-to-Coarse Composition Framework for Knowledge Base Question Answering","created":"2023-06-26","cited_by_count":21},{"id":"2410.18415","title":"Decoding on Graphs: Faithful and Sound Reasoning on Knowledge Graphs through Generation of Well-Formed Chains","created":"2024-10-24","cited_by_count":20},{"id":"2409.19753","title":"CoTKR: Chain-of-Thought Enhanced Knowledge Rewriting for Complex Knowledge Graph Question Answering","created":"2024-09-29","cited_by_count":17},{"id":"2309.04695","title":"Code-Style In-Context Learning for Knowledge-Based Question Answering","created":"2023-09-09","cited_by_count":13}],"next_cursor":null}