{"list":"other","total":58,"rows":[{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"id":"2507.06261","title":"Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities","created":"2025-07-07","cited_by_count":3796},{"id":"2307.15043","title":"Universal and Transferable Adversarial Attacks on Aligned Language Models","created":"2023-07-27","cited_by_count":3104},{"id":"2212.08073","title":"Constitutional AI: Harmlessness from AI Feedback","created":"2022-12-15","cited_by_count":3050},{"id":"2311.12022","title":"GPQA: A Graduate-Level Google-Proof Q&A Benchmark","created":"2023-11-20","cited_by_count":2879},{"id":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576},{"id":"2309.07864","title":"The Rise and Potential of Large Language Model Based Agents: A Survey","created":"2023-09-14","cited_by_count":1439},{"id":"2310.13548","title":"Towards Understanding Sycophancy in Language Models","created":"2023-10-20","cited_by_count":1040},{"id":"2004.09456","title":"StereoSet: Measuring stereotypical bias in pretrained language models","created":"2020-04-20","cited_by_count":924},{"id":"1712.05474","title":"AI2-THOR: An Interactive 3D Environment for Visual AI","created":"2017-12-14","cited_by_count":869},{"id":"2304.00685","title":"Vision-Language Models for Vision Tasks: A Survey","created":"2023-04-03","cited_by_count":839},{"id":"2212.09251","title":"Discovering Language Model Behaviors with Model-Written Evaluations","created":"2022-12-19","cited_by_count":836},{"id":"2512.02556","title":"DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models","created":"2025-12-02","cited_by_count":815},{"id":"2010.00133","title":"CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Models","created":"2020-09-30","cited_by_count":710},{"id":"2110.08193","title":"BBQ: A Hand-Built Bias Benchmark for Question Answering","created":"2021-10-15","cited_by_count":701},{"id":"2507.20534","title":"Kimi K2: Open Agentic Intelligence","created":"2025-07-28","cited_by_count":567},{"id":"2404.01318","title":"JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models","created":"2024-03-28","cited_by_count":536},{"id":"2403.03218","title":"The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning","created":"2024-03-05","cited_by_count":509},{"id":"2602.02276","title":"Kimi K2.5: Visual Agentic Intelligence","created":"2026-02-02","cited_by_count":501},{"id":"2310.06987","title":"Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation","created":"2023-10-10","cited_by_count":451},{"id":"2101.11718","title":"BOLD: Dataset and Metrics for Measuring Biases in Open-Ended Language Generation","created":"2021-01-27","cited_by_count":412},{"id":"2402.10260","title":"A StrongREJECT for Empty Jailbreaks","created":"2024-02-15","cited_by_count":385},{"id":"2412.14093","title":"Alignment faking in large language models","created":"2024-12-18","cited_by_count":360},{"id":"2412.14470","title":"Agent-SafetyBench: Evaluating the Safety of LLM Agents","created":"2024-12-19","cited_by_count":306},{"id":"2402.05044","title":"SALAD-Bench: A Hierarchical and Comprehensive Safety Benchmark for Large Language Models","created":"2024-02-07","cited_by_count":228},{"id":"2307.01881","title":"ProPILE: Probing Privacy Leakage in Large Language Models","created":"2023-07-04","cited_by_count":129},{"id":"2412.13178","title":"SafeAgentBench: A Benchmark for Safe Task Planning of Embodied LLM Agents","created":"2024-12-17","cited_by_count":116},{"id":"1711.09883","title":"AI Safety Gridworlds","created":"2017-11-27","cited_by_count":110},{"id":"2308.11339","title":"ProAgent: Building Proactive Cooperative Agents with Large Language Models","created":"2023-08-22","cited_by_count":98},{"id":"2404.08676","title":"ALERT: A Comprehensive Benchmark for Assessing Large Language Models' Safety through Red Teaming","created":"2024-04-06","cited_by_count":98},{"id":"2407.17436","title":"AIR-Bench 2024: A Safety Benchmark Based on Risk Categories from Regulations and Policies","created":"2024-07-11","cited_by_count":74},{"id":"2503.03750","title":"The MASK Benchmark: Disentangling Honesty From Accuracy in AI Systems","created":"2025-03-05","cited_by_count":72},{"id":"2510.20270","title":"ImpossibleBench: Measuring LLMs' Propensity of Exploiting Test Cases","created":"2025-10-23","cited_by_count":65},{"id":"2410.06172","title":"Multimodal Situational Safety","created":"2024-10-08","cited_by_count":58},{"id":"2402.04247","title":"Risks of AI Scientists: Prioritizing Safeguarding Over Autonomy","created":"2024-02-06","cited_by_count":49},{"id":"2506.16402","title":"IS-Bench: Evaluating Interactive Safety of VLM-Driven Embodied Agents in Daily Household Tasks","created":"2025-06-19","cited_by_count":41},{"id":"2304.05510","title":"chatClimate: Grounding Conversational AI in Climate Science","created":"2023-04-11","cited_by_count":32},{"id":"2504.14650","title":"A Framework for Benchmarking and Aligning Task-Planning Safety in LLM-Based Embodied Agents","created":"2025-04-20","cited_by_count":30},{"id":"2505.18807","title":"Mitigating Deceptive Alignment via Self-Monitoring","created":"2025-05-24","cited_by_count":29},{"id":"2104.05107","title":"Towards a Collective Agenda on AI for Earth Science Data Analysis","created":"2021-04-11","cited_by_count":27},{"id":"2408.04449","title":"EARBench: Towards Evaluating Physical Risk Awareness for Task Planning of Foundation Model-based Embodied AI Agents","created":"2024-08-08","cited_by_count":27},{"id":"2410.14182","title":"LabSafety Bench: Benchmarking LLMs on Safety Issues in Scientific Labs","created":"2024-10-18","cited_by_count":25},{"id":"2506.14922","title":"FORTRESS: Frontier Risk Evaluation for National Security and Public Safety","created":"2025-06-17","cited_by_count":24},{"id":"2310.02932","title":"Assessing Large Language Models on Climate Information","created":"2023-10-04","cited_by_count":23},{"id":"2404.16251","title":"Prompt Leakage effect and defense strategies for multi-turn LLM interactions","created":"2024-04-24","cited_by_count":23},{"id":"2504.18565","title":"RepliBench: Evaluating the Autonomous Replication Capabilities of Language Model Agents","created":"2025-04-21","cited_by_count":15},{"id":"2404.01295","title":"Towards Safety and Helpfulness Balanced Responses via Controllable Large Language Models","created":"2024-04-01","cited_by_count":14},{"id":"2504.04893","title":"SCAM: A Real-World Typographic Robustness Evaluation for Multimodal Foundation Models","created":"2025-04-07","cited_by_count":13},{"id":"2504.15699","title":"Advancing Embodied Agent Security: From Safety Benchmarks to Input Moderation","created":"2025-04-22","cited_by_count":13},{"id":"2505.21605","title":"SoSBench: Benchmarking Safety Alignment on Six Scientific Domains","created":"2025-05-27","cited_by_count":12},{"id":"2509.08494","title":"HumanAgencyBench: Scalable Evaluation of Human Agency Support in AI Assistants","created":"2025-09-10","cited_by_count":11},{"id":"2508.05855","title":"Safety of Embodied Navigation: A Survey","created":"2025-08-07","cited_by_count":10},{"id":"2411.18289","title":"Don't Let Your Robot be Harmful: Responsible Robotic Manipulation via Safety-as-Policy","created":"2024-11-27","cited_by_count":9},{"id":"2507.16534","title":"Frontier AI Risk Management Framework in Practice: A Risk Analysis Technical Report","created":"2025-07-22","cited_by_count":8},{"id":"2602.04064","title":"The CitizenQuery Benchmark: A Novel Dataset and Evaluation Pipeline for Measuring LLM Performance in Citizen Query Tasks","created":"2026-02-03","cited_by_count":5},{"id":"2504.17404","title":"Super Co-alignment of Human and AI for Sustainable Symbiotic Society","created":"2025-04-24","cited_by_count":2},{"id":"2509.25643","title":"SOCK: A Benchmark for Measuring Self-Replication in Large Language Models","created":"2025-09-30","cited_by_count":2}],"next_cursor":null}