{"list":"other","total":106,"rows":[{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344},{"id":"2310.11511","title":"Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection","created":"2023-10-17","cited_by_count":1839},{"id":"2308.14508","title":"LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding","created":"2023-08-28","cited_by_count":1417},{"id":"2002.08155","title":"CodeBERT: A Pre-Trained Model for Programming and Natural Languages","created":"2020-02-19","cited_by_count":1310},{"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":"2407.16741","title":"OpenHands: An Open Platform for AI Software Developers as Generalist Agents","created":"2024-07-23","cited_by_count":1002},{"id":"2301.12652","title":"REPLUG: Retrieval-Augmented Black-Box Language Models","created":"2023-01-30","cited_by_count":792},{"id":"2302.00083","title":"In-Context Retrieval-Augmented Language Models","created":"2023-01-31","cited_by_count":702},{"id":"2309.00614","title":"Baseline Defenses for Adversarial Attacks Against Aligned Language Models","created":"2023-09-01","cited_by_count":651},{"id":"2009.08366","title":"GraphCodeBERT: Pre-training Code Representations with Data Flow","created":"2020-09-17","cited_by_count":609},{"id":"2305.06983","title":"Active Retrieval Augmented Generation","created":"2023-05-11","cited_by_count":516},{"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":"2501.05366","title":"Search-o1: Agentic Search-Enhanced Large Reasoning Models","created":"2025-01-09","cited_by_count":433},{"id":"2406.02069","title":"PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling","created":"2024-06-04","cited_by_count":432},{"id":"2308.14132","title":"Detecting Language Model Attacks with Perplexity","created":"2023-08-27","cited_by_count":431},{"id":"2308.10620","title":"Large Language Models for Software Engineering: A Systematic Literature Review","created":"2023-08-21","cited_by_count":399},{"id":"2303.12570","title":"RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generation","created":"2023-03-22","cited_by_count":367},{"id":"2311.04934","title":"Prompt Cache: Modular Attention Reuse for Low-Latency Inference","created":"2023-11-07","cited_by_count":268},{"id":"2304.07590","title":"Self-collaboration Code Generation via ChatGPT","created":"2023-04-15","cited_by_count":258},{"id":"2010.15980","title":"AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Prompts","created":"2020-10-29","cited_by_count":249},{"id":"2407.11550","title":"Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference","created":"2024-07-16","cited_by_count":235},{"id":"2310.03003","title":"From Words to Watts: Benchmarking the Energy Costs of Large Language Model Inference","created":"2023-10-04","cited_by_count":170},{"id":"2302.05319","title":"Large Language Models for Code: Security Hardening and Adversarial Testing","created":"2023-02-10","cited_by_count":155},{"id":"2403.03163","title":"Design2Code: Benchmarking Multimodal Code Generation for Automated Front-End Engineering","created":"2024-03-05","cited_by_count":152},{"id":"2212.09420","title":"Large Language Models Meet NL2Code: A Survey","created":"2022-12-19","cited_by_count":138},{"id":"2403.17927","title":"MAGIS: LLM-Based Multi-Agent Framework for GitHub Issue Resolution","created":"2024-03-26","cited_by_count":134},{"id":"2405.06823","title":"PLeak: Prompt Leaking Attacks against Large Language Model Applications","created":"2024-05-10","cited_by_count":127},{"id":"2501.01257","title":"CodeElo: Benchmarking Competition-level Code Generation of LLMs with Human-comparable Elo Ratings","created":"2025-01-02","cited_by_count":115},{"id":"2306.14893","title":"LongCoder: A Long-Range Pre-trained Language Model for Code Completion","created":"2023-06-26","cited_by_count":112},{"id":"2006.03463","title":"Sponge Examples: Energy-Latency Attacks on Neural Networks","created":"2020-06-05","cited_by_count":111},{"id":"2502.14382","title":"S*: Test Time Scaling for Code Generation","created":"2025-02-20","cited_by_count":98},{"id":"2409.20550","title":"LLM Hallucinations in Practical Code Generation: Phenomena, Mechanism, and Mitigation","created":"2024-09-30","cited_by_count":93},{"id":"2212.10481","title":"Execution-Based Evaluation for Open-Domain Code Generation","created":"2022-12-20","cited_by_count":91},{"id":"2406.14497","title":"CodeRAG-Bench: Can Retrieval Augment Code Generation?","created":"2024-06-20","cited_by_count":91},{"id":"2501.05040","title":"SWE-Fixer: Training Open-Source LLMs for Effective and Efficient GitHub Issue Resolution","created":"2025-01-09","cited_by_count":90},{"id":"2405.14918","title":"AnalogCoder: Analog Circuit Design via Training-Free Code Generation","created":"2024-05-23","cited_by_count":84},{"id":"1510.00726","title":"A Primer on Neural Network Models for Natural Language Processing","created":"2015-10-02","cited_by_count":76},{"id":"2401.11170","title":"Inducing High Energy-Latency of Large Vision-Language Models with Verbose Images","created":"2024-01-20","cited_by_count":69},{"id":"2402.12065","title":"WKVQuant: Quantizing Weight and Key/Value Cache for Large Language Models Gains More","created":"2024-02-19","cited_by_count":69},{"id":"2308.11396","title":"Towards an Understanding of Large Language Models in Software Engineering Tasks","created":"2023-08-22","cited_by_count":68},{"id":"2502.05206","title":"Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety","created":"2025-02-02","cited_by_count":67},{"id":"2311.10372","title":"A Survey of Large Language Models for Code: Evolution, Benchmarking, and Future Trends","created":"2023-11-17","cited_by_count":66},{"id":"2212.10007","title":"CoCoMIC: Code Completion By Jointly Modeling In-file and Cross-file Context","created":"2022-12-20","cited_by_count":65},{"id":"2507.23361","title":"SWE-Exp: Experience-Driven Software Issue Resolution","created":"2025-07-31","cited_by_count":65},{"id":"2010.02432","title":"A Panda? No, It's a Sloth: Slowdown Attacks on Adaptive Multi-Exit Neural Network Inference","created":"2020-10-06","cited_by_count":61},{"id":"2103.04264","title":"T-Miner: A Generative Approach to Defend Against Trojan Attacks on DNN-based Text Classification","created":"2021-03-07","cited_by_count":60},{"id":"2409.09030","title":"Agents in Software Engineering: Survey, Landscape, and Vision","created":"2024-09-13","cited_by_count":60},{"id":"2308.10819","title":"Evaluating the Instruction-Following Robustness of Large Language Models to Prompt Injection","created":"2023-08-17","cited_by_count":59},{"id":"2406.01422","title":"Alibaba LingmaAgent: Improving Automated Issue Resolution via Comprehensive Repository Exploration","created":"2024-06-03","cited_by_count":58},{"id":"2310.04951","title":"CodeTransOcean: A Comprehensive Multilingual Benchmark for Code Translation","created":"2023-10-08","cited_by_count":57},{"id":"2206.00052","title":"CodeAttack: Code-Based Adversarial Attacks for Pre-trained Programming Language Models","created":"2022-05-31","cited_by_count":53},{"id":"2507.23348","title":"SWE-Debate: Competitive Multi-Agent Debate for Software Issue Resolution","created":"2025-07-31","cited_by_count":53},{"id":"2203.15859","title":"NICGSlowDown: Evaluating the Efficiency Robustness of Neural Image Caption Generation Models","created":"2022-03-29","cited_by_count":50},{"id":"2107.07112","title":"On the Evaluation of Neural Code Summarization","created":"2021-07-15","cited_by_count":48},{"id":"2407.19487","title":"RLCoder: Reinforcement Learning for Repository-Level Code Completion","created":"2024-07-28","cited_by_count":44},{"id":"2108.12987","title":"CAST: Enhancing Code Summarization with Hierarchical Splitting and Reconstruction of Abstract Syntax Trees","created":"2021-08-30","cited_by_count":32},{"id":"2402.14323","title":"REPOFUSE: Repository-Level Code Completion with Fused Dual Context","created":"2024-02-22","cited_by_count":32},{"id":"2103.09499","title":"Code Completion by Modeling Flattened Abstract Syntax Trees as Graphs","created":"2021-03-17","cited_by_count":30},{"id":"2406.06918","title":"HumanEvo: An Evolution-aware Benchmark for More Realistic Evaluation of Repository-level Code Generation","created":"2024-06-11","cited_by_count":28},{"id":"2409.15154","title":"RMCBench: Benchmarking Large Language Models' Resistance to Malicious Code","created":"2024-09-23","cited_by_count":28},{"id":"2203.02700","title":"RACE: Retrieval-Augmented Commit Message Generation","created":"2022-03-05","cited_by_count":27},{"id":"2505.04606","title":"OmniGIRL: A Multilingual and Multimodal Benchmark for GitHub Issue Resolution","created":"2025-05-07","cited_by_count":24},{"id":"2107.01933","title":"CoCoSum: Contextual Code Summarization with Multi-Relational Graph Neural Network","created":"2021-07-05","cited_by_count":22},{"id":"2204.03293","title":"CoCoSoDa: Effective Contrastive Learning for Code Search","created":"2022-04-07","cited_by_count":22},{"id":"2503.20589","title":"What to Retrieve for Effective Retrieval-Augmented Code Generation? An Empirical Study and Beyond","created":"2025-03-26","cited_by_count":22},{"id":"2407.20042","title":"When to Stop? Towards Efficient Code Generation in LLMs with Excess Token Prevention","created":"2024-07-29","cited_by_count":21},{"id":"2408.13204","title":"DOMAINEVAL: An Auto-Constructed Benchmark for Multi-Domain Code Generation","created":"2024-08-23","cited_by_count":21},{"id":"2502.18297","title":"DeepCircuitX: A Comprehensive Repository-Level Dataset for RTL Code Understanding, Generation, and PPA Analysis","created":"2025-02-25","cited_by_count":21},{"id":"2107.05373","title":"On the Evaluation of Commit Message Generation Models: An Experimental Study","created":"2021-07-12","cited_by_count":20},{"id":"2210.05370","title":"DeepPerform: An Efficient Approach for Performance Testing of Resource-Constrained Neural Networks","created":"2022-10-10","cited_by_count":17},{"id":"2410.09812","title":"Unraveling the Potential of Large Language Models in Code Translation: How Far Are We?","created":"2024-10-13","cited_by_count":17},{"id":"2210.03696","title":"LLMEffiChecker: Understanding and Testing Efficiency Degradation of Large Language Models","created":"2022-10-07","cited_by_count":16},{"id":"2408.11296","title":"RePair: Automated Program Repair with Process-based Feedback","created":"2024-08-21","cited_by_count":16},{"id":"2407.00456","title":"Beyond Functional Correctness: Investigating Coding Style Inconsistencies in Large Language Models","created":"2024-06-29","cited_by_count":15},{"id":"2305.03655","title":"White-Box Multi-Objective Adversarial Attack on Dialogue Generation","created":"2023-05-05","cited_by_count":14},{"id":"2310.08069","title":"Rethinking Negative Pairs in Code Search","created":"2023-10-12","cited_by_count":14},{"id":"2409.06679","title":"E2LLM: Encoder Elongated Large Language Models for Long-Context Understanding and Reasoning","created":"2024-09-10","cited_by_count":13},{"id":"2412.18573","title":"Top General Performance = Top Domain Performance? DomainCodeBench: A Multi-domain Code Generation Benchmark","created":"2024-12-24","cited_by_count":13},{"id":"2507.19942","title":"Prometheus: Towards Long-Horizon Codebase Navigation for Repository-Level Problem Solving","created":"2025-07-26","cited_by_count":13},{"id":"2310.01446","title":"Adaptive-Solver Framework for Dynamic Strategy Selection in Large Language Model Reasoning","created":"2023-10-01","cited_by_count":12},{"id":"2401.14727","title":"SparseCoder: Identifier-Aware Sparse Transformer for File-Level Code Summarization","created":"2024-01-26","cited_by_count":11},{"id":"2406.11589","title":"CoSQA+: Pioneering the Multi-Choice Code Search Benchmark with Test-Driven Agents","created":"2024-06-17","cited_by_count":11},{"id":"2408.05542","title":"You Augment Me: Exploring ChatGPT-based Data Augmentation for Semantic Code Search","created":"2024-08-10","cited_by_count":11},{"id":"2502.05610","title":"Towards Sustainable NLP: Insights from Benchmarking Inference Energy in Large Language Models","created":"2025-02-08","cited_by_count":11},{"id":"2203.15287","title":"Accelerating Code Search with Deep Hashing and Code Classification","created":"2022-03-29","cited_by_count":10},{"id":"2401.05926","title":"Using Large Language Models for Commit Message Generation: A Preliminary Study","created":"2024-01-11","cited_by_count":10},{"id":"2401.08376","title":"KADEL: Knowledge-Aware Denoising Learning for Commit Message Generation","created":"2024-01-16","cited_by_count":10},{"id":"2404.14824","title":"Automated Commit Message Generation with Large Language Models: An Empirical Study and Beyond","created":"2024-04-23","cited_by_count":10},{"id":"2504.08734","title":"Towards an Understanding of Context Utilization in Code Intelligence","created":"2025-04-11","cited_by_count":10},{"id":"2208.11271","title":"Tackling Long Code Search with Splitting, Encoding, and Aggregating","created":"2022-08-24","cited_by_count":9},{"id":"2308.10759","title":"EALink: An Efficient and Accurate Pre-trained Framework for Issue-Commit Link Recovery","created":"2023-08-21","cited_by_count":9},{"id":"2208.11274","title":"Revisiting Code Search in a Two-Stage Paradigm","created":"2022-08-24","cited_by_count":8},{"id":"2308.13416","title":"SoTaNa: The Open-Source Software Development Assistant","created":"2023-08-25","cited_by_count":8},{"id":"2407.13271","title":"Identifying Smart Contract Security Issues in Code Snippets from Stack Overflow","created":"2024-07-18","cited_by_count":8},{"id":"2105.09630","title":"Enriching Query Semantics for Code Search with Reinforcement Learning","created":"2021-05-20","cited_by_count":7},{"id":"2408.06037","title":"Hyperion: Unveiling DApp Inconsistencies using LLM and Dataflow-Guided Symbolic Execution","created":"2024-08-12","cited_by_count":7},{"id":"2410.22240","title":"Are Decoder-Only Large Language Models the Silver Bullet for Code Search?","created":"2024-10-29","cited_by_count":7},{"id":"2409.03274","title":"Recent Advances in Attack and Defense Approaches of Large Language Models","created":"2024-09-05","cited_by_count":6},{"id":"2504.19444","title":"Large Language Models are Qualified Benchmark Builders: Rebuilding Pre-Training Datasets for Advancing Code Intelligence Tasks","created":"2025-04-28","cited_by_count":6}],"next_cursor":"100"}