{"list":"other","total":57,"rows":[{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"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":"2503.14476","title":"DAPO: An Open-Source LLM Reinforcement Learning System at Scale","created":"2025-03-18","cited_by_count":2810},{"id":"2308.12950","title":"Code Llama: Open Foundation Models for Code","created":"2023-08-24","cited_by_count":2139},{"id":"2409.19256","title":"HybridFlow: A Flexible and Efficient RLHF Framework","created":"2024-09-28","cited_by_count":2057},{"id":"2402.04249","title":"HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal","created":"2024-02-06","cited_by_count":1429},{"id":"2305.01210","title":"Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation","created":"2023-05-02","cited_by_count":1391},{"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":"2310.04451","title":"AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models","created":"2023-10-03","cited_by_count":785},{"id":"2306.08568","title":"WizardCoder: Empowering Code Large Language Models with Evol-Instruct","created":"2023-06-14","cited_by_count":733},{"id":"2107.06499","title":"Deduplicating Training Data Makes Language Models Better","created":"2021-07-14","cited_by_count":714},{"id":"2501.17161","title":"SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training","created":"2025-01-28","cited_by_count":672},{"id":"2406.15877","title":"BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions","created":"2024-06-22","cited_by_count":546},{"id":"2404.01318","title":"JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models","created":"2024-03-28","cited_by_count":536},{"id":"2308.01263","title":"XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models","created":"2023-08-02","cited_by_count":505},{"id":"2502.01456","title":"Process Reinforcement through Implicit Rewards","created":"2025-02-03","cited_by_count":504},{"id":"2402.19173","title":"StarCoder 2 and The Stack v2: The Next Generation","created":"2024-02-29","cited_by_count":502},{"id":"2406.18495","title":"WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs","created":"2024-06-26","cited_by_count":496},{"id":"2308.03825","title":"\"Do Anything Now\": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models","created":"2023-08-07","cited_by_count":489},{"id":"2404.02151","title":"Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks","created":"2024-04-02","cited_by_count":486},{"id":"2309.11998","title":"LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation Dataset","created":"2023-09-21","cited_by_count":461},{"id":"2503.01307","title":"Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRs","created":"2025-03-03","cited_by_count":377},{"id":"2207.01780","title":"CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning","created":"2022-07-05","cited_by_count":358},{"id":"1909.03496","title":"Devign: Effective Vulnerability Identification by Learning Comprehensive Program Semantics via Graph Neural Networks","created":"2019-09-08","cited_by_count":272},{"id":"2312.02120","title":"Magicoder: Empowering Code Generation with OSS-Instruct","created":"2023-12-04","cited_by_count":256},{"id":"2404.03027","title":"JailBreakV: A Benchmark for Assessing the Robustness of MultiModal Large Language Models against Jailbreak Attacks","created":"2024-04-03","cited_by_count":230},{"id":"2406.18510","title":"WildTeaming at Scale: From In-the-Wild Jailbreaks to (Adversarially) Safer Language Models","created":"2024-06-26","cited_by_count":223},{"id":"2402.11753","title":"ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs","created":"2024-02-19","cited_by_count":216},{"id":"2308.07124","title":"OctoPack: Instruction Tuning Code Large Language Models","created":"2023-08-14","cited_by_count":189},{"id":"2501.18837","title":"Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming","created":"2025-01-31","cited_by_count":181},{"id":"2302.05319","title":"Large Language Models for Code: Security Hardening and Adversarial Testing","created":"2023-02-10","cited_by_count":155},{"id":"2403.18624","title":"Vulnerability Detection with Code Language Models: How Far Are We?","created":"2024-03-27","cited_by_count":139},{"id":"2411.04905","title":"OpenCoder: The Open Cookbook for Top-Tier Code Large Language Models","created":"2024-11-07","cited_by_count":130},{"id":"2505.07608","title":"MiMo: Unlocking the Reasoning Potential of Language Model -- From Pretraining to Posttraining","created":"2025-05-12","cited_by_count":121},{"id":"2304.00409","title":"DiverseVul: A New Vulnerable Source Code Dataset for Deep Learning Based Vulnerability Detection","created":"2023-04-01","cited_by_count":102},{"id":"2411.07781","title":"RedCode: Risky Code Execution and Generation Benchmark for Code Agents","created":"2024-11-12","cited_by_count":90},{"id":"2402.09497","title":"Instruction Tuning for Secure Code Generation","created":"2024-02-14","cited_by_count":68},{"id":"2410.24198","title":"SelfCodeAlign: Self-Alignment for Code Generation","created":"2024-10-31","cited_by_count":62},{"id":"2501.08200","title":"CWEval: Outcome-driven Evaluation on Functionality and Security of LLM Code Generation","created":"2025-01-14","cited_by_count":59},{"id":"2408.01605","title":"CYBERSECEVAL 3: Advancing the Evaluation of Cybersecurity Risks and Capabilities in Large Language Models","created":"2024-08-02","cited_by_count":58},{"id":"2302.04012","title":"CodeLMSec Benchmark: Systematically Evaluating and Finding Security Vulnerabilities in Black-Box Code Language Models","created":"2023-02-08","cited_by_count":55},{"id":"2402.07688","title":"CyberMetric: A Benchmark Dataset based on Retrieval-Augmented Generation for Evaluating LLMs in Cybersecurity Knowledge","created":"2024-02-12","cited_by_count":55},{"id":"2502.19820","title":"Foot-In-The-Door: A Multi-turn Jailbreak for LLMs","created":"2025-02-27","cited_by_count":54},{"id":"2401.03315","title":"Malla: Demystifying Real-world Large Language Model Integrated Malicious Services","created":"2024-01-06","cited_by_count":33},{"id":"2409.15154","title":"RMCBench: Benchmarking Large Language Models' Resistance to Malicious Code","created":"2024-09-23","cited_by_count":28},{"id":"2503.16431","title":"OpenAI's Approach to External Red Teaming for AI Models and Systems","created":"2025-01-24","cited_by_count":28},{"id":"2411.12882","title":"ProSec: Fortifying Code LLMs with Proactive Security Alignment","created":"2024-11-19","cited_by_count":25},{"id":"2408.04811","title":"h4rm3l: A language for Composable Jailbreak Attack Synthesis","created":"2024-08-09","cited_by_count":24},{"id":"2409.12699","title":"PromSec: Prompt Optimization for Secure Generation of Functional Source Code with Large Language Models (LLMs)","created":"2024-09-19","cited_by_count":19},{"id":"2409.06446","title":"HexaCoder: Secure Code Generation via Oracle-Guided Synthetic Training Data","created":"2024-09-10","cited_by_count":16},{"id":"2410.01488","title":"SecCoder: Towards Generalizable and Robust Secure Code Generation","created":"2024-10-02","cited_by_count":14},{"id":"2501.01335","title":"CySecBench: Generative AI-based CyberSecurity-focused Prompt Dataset for Benchmarking Large Language Models","created":"2025-01-02","cited_by_count":10},{"id":"2506.07313","title":"SCGAgent: Recreating the Benefits of Reasoning Models for Secure Code Generation with Agentic Workflows","created":"2025-06-08","cited_by_count":4}],"next_cursor":null}