{"list":"other","total":51,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"2303.11366","title":"Reflexion: Language Agents with Verbal Reinforcement Learning","created":"2023-03-20","cited_by_count":4276},{"id":"2108.07732","title":"Program Synthesis with Large Language Models","created":"2021-08-16","cited_by_count":3637},{"id":"2303.17651","title":"Self-Refine: Iterative Refinement with Self-Feedback","created":"2023-03-30","cited_by_count":3442},{"id":"2310.06825","title":"Mistral 7B","created":"2023-10-10","cited_by_count":3164},{"id":"2308.12950","title":"Code Llama: Open Foundation Models for Code","created":"2023-08-24","cited_by_count":2139},{"id":"2401.04088","title":"Mixtral of Experts","created":"2024-01-08","cited_by_count":1823},{"id":"2203.07814","title":"Competition-Level Code Generation with AlphaCode","created":"2022-02-08","cited_by_count":1462},{"id":"2401.14196","title":"DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence","created":"2024-01-25","cited_by_count":1181},{"id":"2305.10403","title":"PaLM 2 Technical Report","created":"2023-05-17","cited_by_count":1162},{"id":"2109.00859","title":"CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation","created":"2021-09-02","cited_by_count":906},{"id":"2203.13474","title":"CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis","created":"2022-03-25","cited_by_count":885},{"id":"2305.06161","title":"StarCoder: may the source be with you!","created":"2023-05-09","cited_by_count":799},{"id":"2307.05782","title":"Large Language Models","created":"2023-07-11","cited_by_count":780},{"id":"2104.08773","title":"Cross-Task Generalization via Natural Language Crowdsourcing Instructions","created":"2021-04-18","cited_by_count":699},{"id":"2310.04406","title":"Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models","created":"2023-10-06","cited_by_count":574},{"id":"2204.05999","title":"InCoder: A Generative Model for Code Infilling and Synthesis","created":"2022-04-12","cited_by_count":498},{"id":"2311.17911","title":"OPERA: Alleviating Hallucination in Multi-Modal Large Language Models via Over-Trust Penalty and Retrospection-Allocation","created":"2023-11-29","cited_by_count":478},{"id":"2404.19737","title":"Better & Faster Large Language Models via Multi-token Prediction","created":"2024-04-30","cited_by_count":360},{"id":"2303.17568","title":"CodeGeeX: A Pre-Trained Model for Code Generation with Multilingual Benchmarking on HumanEval-X","created":"2023-03-30","cited_by_count":300},{"id":"2105.12655","title":"CodeNet: A Large-Scale AI for Code Dataset for Learning a Diversity of Coding Tasks","created":"2021-05-25","cited_by_count":200},{"id":"2303.05510","title":"Planning with Large Language Models for Code Generation","created":"2023-03-09","cited_by_count":182},{"id":"2310.01714","title":"Large Language Models as Analogical Reasoners","created":"2023-10-03","cited_by_count":107},{"id":"2411.17558","title":"Natural Language Understanding and Inference with MLLM in Visual Question Answering: A Survey","created":"2024-11-26","cited_by_count":76},{"id":"2411.02937","title":"Benchmarking Multimodal Retrieval Augmented Generation with Dynamic VQA Dataset and Self-adaptive Planning Agent","created":"2024-11-05","cited_by_count":65},{"id":"2203.00991","title":"The Past Mistake is the Future Wisdom: Error-driven Contrastive Probability Optimization for Chinese Spell Checking","created":"2022-03-02","cited_by_count":56},{"id":"2307.09007","title":"On the (In)Effectiveness of Large Language Models for Chinese Text Correction","created":"2023-07-18","cited_by_count":54},{"id":"2402.03289","title":"Make Every Move Count: LLM-based High-Quality RTL Code Generation Using MCTS","created":"2024-02-05","cited_by_count":43},{"id":"2309.02772","title":"Hot or Cold? Adaptive Temperature Sampling for Code Generation with Large Language Models","created":"2023-09-06","cited_by_count":38},{"id":"2210.10320","title":"Learning from the Dictionary: Heterogeneous Knowledge Guided Fine-tuning for Chinese Spell Checking","created":"2022-10-19","cited_by_count":31},{"id":"2204.07789","title":"Contrastive Learning with Hard Negative Entities for Entity Set Expansion","created":"2022-04-16","cited_by_count":26},{"id":"2210.10442","title":"Linguistic Rules-Based Corpus Generation for Native Chinese Grammatical Error Correction","created":"2022-10-19","cited_by_count":25},{"id":"2409.19272","title":"Perception Compressor: A Training-Free Prompt Compression Framework in Long Context Scenarios","created":"2024-09-28","cited_by_count":23},{"id":"2502.11493","title":"DAST: Context-Aware Compression in LLMs via Dynamic Allocation of Soft Tokens","created":"2025-02-17","cited_by_count":22},{"id":"2207.08087","title":"Automatic Context Pattern Generation for Entity Set Expansion","created":"2022-07-17","cited_by_count":21},{"id":"2302.08774","title":"Vision, Deduction and Alignment: An Empirical Study on Multi-modal Knowledge Graph Alignment","created":"2023-02-17","cited_by_count":19},{"id":"2308.10529","title":"SeqGPT: An Out-of-the-box Large Language Model for Open Domain Sequence Understanding","created":"2023-08-21","cited_by_count":18},{"id":"2310.09119","title":"A Frustratingly Easy Plug-and-Play Detection-and-Reasoning Module for Chinese Spelling Check","created":"2023-10-13","cited_by_count":15},{"id":"2502.07184","title":"Refine Knowledge of Large Language Models via Adaptive Contrastive Learning","created":"2025-02-11","cited_by_count":15},{"id":"2207.09217","title":"Contextual Similarity is More Valuable than Character Similarity: An Empirical Study for Chinese Spell Checking","created":"2022-07-17","cited_by_count":14},{"id":"2402.08147","title":"VerMCTS: Synthesizing Multi-Step Programs using a Verifier, a Large Language Model, and Tree Search","created":"2024-02-13","cited_by_count":14},{"id":"2502.10454","title":"One Example Shown, Many Concepts Known! Counterexample-Driven Conceptual Reasoning in Mathematical LLMs","created":"2025-02-12","cited_by_count":14},{"id":"2306.17447","title":"Correct Like Humans: Progressive Learning Framework for Chinese Text Error Correction","created":"2023-06-30","cited_by_count":13},{"id":"2307.14878","title":"MESED: A Multi-modal Entity Set Expansion Dataset with Fine-grained Semantic Classes and Hard Negative Entities","created":"2023-07-27","cited_by_count":13},{"id":"2211.10997","title":"Embracing Ambiguity: Improving Similarity-oriented Tasks with Contextual Synonym Knowledge","created":"2022-11-20","cited_by_count":12},{"id":"2403.04247","title":"UltraWiki: Ultra-fine-grained Entity Set Expansion with Negative Seed Entities","created":"2024-03-07","cited_by_count":2}],"next_cursor":null}