{"list":"other","total":83,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"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":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"id":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"id":"2205.11916","title":"Large Language Models are Zero-Shot Reasoners","created":"2022-05-24","cited_by_count":4374},{"id":"2305.20050","title":"Let's Verify Step by Step","created":"2023-05-31","cited_by_count":3789},{"id":"2305.10601","title":"Tree of Thoughts: Deliberate Problem Solving with Large Language Models","created":"2023-05-17","cited_by_count":3211},{"id":"2308.12950","title":"Code Llama: Open Foundation Models for Code","created":"2023-08-24","cited_by_count":2139},{"id":"2408.03314","title":"Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters","created":"2024-08-06","cited_by_count":1986},{"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":"2205.10625","title":"Least-to-Most Prompting Enables Complex Reasoning in Large Language Models","created":"2022-05-21","cited_by_count":1407},{"id":"2211.12588","title":"Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks","created":"2022-11-22","cited_by_count":1076},{"id":"2312.08935","title":"Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations","created":"2023-12-14","cited_by_count":928},{"id":"2211.14275","title":"Solving math word problems with process- and outcome-based feedback","created":"2022-11-25","cited_by_count":901},{"id":"2308.09687","title":"Graph of Thoughts: Solving Elaborate Problems with Large Language Models","created":"2023-08-18","cited_by_count":886},{"id":"2308.10144","title":"ExpeL: LLM Agents Are Experiential Learners","created":"2023-08-20","cited_by_count":876},{"id":"2305.14992","title":"Reasoning with Language Model is Planning with World Model","created":"2023-05-24","cited_by_count":861},{"id":"2308.07201","title":"ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate","created":"2023-08-14","cited_by_count":742},{"id":"2309.12284","title":"MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models","created":"2023-09-21","cited_by_count":735},{"id":"2306.08302","title":"Unifying Large Language Models and Knowledge Graphs: A Roadmap","created":"2023-06-14","cited_by_count":668},{"id":"2002.00388","title":"A Survey on Knowledge Graphs: Representation, Acquisition and Applications","created":"2020-02-02","cited_by_count":643},{"id":"2212.10403","title":"Towards Reasoning in Large Language Models: A Survey","created":"2022-12-20","cited_by_count":596},{"id":"2410.05229","title":"GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models","created":"2024-10-07","cited_by_count":550},{"id":"2411.16594","title":"From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judge","created":"2024-11-25","cited_by_count":494},{"id":"2408.15240","title":"Generative Verifiers: Reward Modeling as Next-Token Prediction","created":"2024-08-27","cited_by_count":480},{"id":"2405.06211","title":"A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models","created":"2024-05-10","cited_by_count":452},{"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":"2205.09712","title":"Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoning","created":"2022-05-19","cited_by_count":334},{"id":"2306.03314","title":"Multi-Agent Collaboration: Harnessing the Power of Intelligent LLM Agents","created":"2023-06-05","cited_by_count":333},{"id":"2401.11817","title":"Hallucination is Inevitable: An Innate Limitation of Large Language Models","created":"2024-01-22","cited_by_count":332},{"id":"2408.08921","title":"Graph Retrieval-Augmented Generation: A Survey","created":"2024-08-15","cited_by_count":324},{"id":"2309.17179","title":"Alphazero-like Tree-Search can Guide Large Language Model Decoding and Training","created":"2023-09-29","cited_by_count":295},{"id":"2412.06559","title":"ProcessBench: Identifying Process Errors in Mathematical Reasoning","created":"2024-12-09","cited_by_count":292},{"id":"2402.00157","title":"Large Language Models for Mathematical Reasoning: Progresses and Challenges","created":"2024-01-31","cited_by_count":284},{"id":"2501.12570","title":"O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning","created":"2025-01-22","cited_by_count":279},{"id":"2306.13304","title":"ToolQA: A Dataset for LLM Question Answering with External Tools","created":"2023-06-23","cited_by_count":274},{"id":"2303.00001","title":"Reward Design with Language Models","created":"2023-02-27","cited_by_count":261},{"id":"2309.15025","title":"Large Language Model Alignment: A Survey","created":"2023-09-26","cited_by_count":243},{"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":"2402.10200","title":"Chain-of-Thought Reasoning Without Prompting","created":"2024-02-15","cited_by_count":210},{"id":"2309.15402","title":"Navigate through Enigmatic Labyrinth A Survey of Chain of Thought Reasoning: Advances, Frontiers and Future","created":"2023-09-27","cited_by_count":184},{"id":"2207.05987","title":"DocPrompting: Generating Code by Retrieving the Docs","created":"2022-07-13","cited_by_count":153},{"id":"2308.11730","title":"Knowledge Graph Prompting for Multi-Document Question Answering","created":"2023-08-22","cited_by_count":152},{"id":"2410.12832","title":"Generative Reward Models","created":"2024-10-02","cited_by_count":148},{"id":"2407.11511","title":"Multi-Step Reasoning with Large Language Models, a Survey","created":"2024-07-16","cited_by_count":143},{"id":"2401.05856","title":"Seven Failure Points When Engineering a Retrieval Augmented Generation System","created":"2024-01-11","cited_by_count":139},{"id":"2305.13269","title":"Chain-of-Knowledge: Grounding Large Language Models via Dynamic Knowledge Adapting over Heterogeneous Sources","created":"2023-05-22","cited_by_count":122},{"id":"2404.00282","title":"Survey on Large Language Model-Enhanced Reinforcement Learning: Concept, Taxonomy, and Methods","created":"2024-03-30","cited_by_count":116},{"id":"2404.01230","title":"LLM as a Mastermind: A Survey of Strategic Reasoning with Large Language Models","created":"2024-04-01","cited_by_count":99},{"id":"2410.09671","title":"OpenR: An Open Source Framework for Advanced Reasoning with Large Language Models","created":"2024-10-12","cited_by_count":94},{"id":"2311.07914","title":"Can Knowledge Graphs Reduce Hallucinations in LLMs? : A Survey","created":"2023-11-14","cited_by_count":92},{"id":"2407.16216","title":"Reinforcement Learning for LLM Post-Training: A Survey","created":"2024-07-23","cited_by_count":92},{"id":"2410.02884","title":"LLaMA-Berry: Pairwise Optimization for O1-like Olympiad-Level Mathematical Reasoning","created":"2024-10-03","cited_by_count":91},{"id":"2311.09724","title":"OVM, Outcome-supervised Value Models for Planning in Mathematical Reasoning","created":"2023-11-16","cited_by_count":85},{"id":"2405.16506","title":"GRAG: Graph Retrieval-Augmented Generation","created":"2024-05-26","cited_by_count":78},{"id":"2409.05746","title":"LLMs Will Always Hallucinate, and We Need to Live With This","created":"2024-09-09","cited_by_count":78},{"id":"2412.00154","title":"o1-Coder: an o1 Replication for Coding","created":"2024-11-29","cited_by_count":78},{"id":"2306.01337","title":"MathChat: Converse to Tackle Challenging Math Problems with LLM Agents","created":"2023-06-02","cited_by_count":68},{"id":"2410.13639","title":"A Comparative Study on Reasoning Patterns of OpenAI's o1 Model","created":"2024-10-17","cited_by_count":63},{"id":"2303.14725","title":"Natural Language Reasoning, A Survey","created":"2023-03-26","cited_by_count":61},{"id":"2405.12035","title":"KG-RAG: Bridging the Gap Between Knowledge and Creativity","created":"2024-05-20","cited_by_count":56},{"id":"2303.08769","title":"Prompting Large Language Models With the Socratic Method","created":"2023-02-17","cited_by_count":43},{"id":"2302.08242","title":"Tuning computer vision models with task rewards","created":"2023-02-16","cited_by_count":37},{"id":"2312.06185","title":"KnowGPT: Knowledge Graph based Prompting for Large Language Models","created":"2023-12-11","cited_by_count":31},{"id":"2406.13862","title":"Knowledge Graph-Enhanced Large Language Models via Path Selection","created":"2024-06-19","cited_by_count":28},{"id":"2411.19477","title":"Provable Scaling Laws for the Test-Time Compute of Large Language Models","created":"2024-11-29","cited_by_count":26},{"id":"2109.12872","title":"Meta-Aggregator: Learning to Aggregate for 1-bit Graph Neural Networks","created":"2021-09-27","cited_by_count":25},{"id":"2304.14593","title":"Deep Graph Reprogramming","created":"2023-04-28","cited_by_count":22},{"id":"2404.00344","title":"Can LLMs Master Math? Investigating Large Language Models on Math Stack Exchange","created":"2024-03-30","cited_by_count":22},{"id":"2401.09042","title":"LLMs for Relational Reasoning: How Far are We?","created":"2024-01-17","cited_by_count":21},{"id":"2407.06564","title":"Combining Knowledge Graphs and Large Language Models","created":"2024-07-09","cited_by_count":16},{"id":"2309.13078","title":"LPML: LLM-Prompting Markup Language for Mathematical Reasoning","created":"2023-09-21","cited_by_count":15},{"id":"2407.10670","title":"Enhancing Retrieval and Managing Retrieval: A Four-Module Synergy for Improved Quality and Efficiency in RAG Systems","created":"2024-07-15","cited_by_count":15},{"id":"2408.08535","title":"CommunityKG-RAG: Leveraging Community Structures in Knowledge Graphs for Advanced Retrieval-Augmented Generation in Fact-Checking","created":"2024-08-16","cited_by_count":11},{"id":"2402.17786","title":"Stepwise Self-Consistent Mathematical Reasoning with Large Language Models","created":"2024-02-24","cited_by_count":8},{"id":"2406.14629","title":"Can LLMs Learn by Teaching for Better Reasoning? A Preliminary Study","created":"2024-06-20","cited_by_count":5},{"id":"2205.03772","title":"Math-KG: Construction and Applications of Mathematical Knowledge Graph","created":"2022-05-08","cited_by_count":4}],"next_cursor":null}