{"list":"other","total":110,"rows":[{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"id":"2305.20050","title":"Let's Verify Step by Step","created":"2023-05-31","cited_by_count":3789},{"id":"2204.05862","title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","created":"2022-04-12","cited_by_count":3720},{"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":"2009.01325","title":"Learning to summarize from human feedback","created":"2020-09-02","cited_by_count":2588},{"id":"2312.10997","title":"Retrieval-Augmented Generation for Large Language Models: A Survey","created":"2023-12-18","cited_by_count":2212},{"id":"1909.08593","title":"Fine-Tuning Language Models from Human Preferences","created":"2019-09-18","cited_by_count":2150},{"id":"2307.02483","title":"Jailbroken: How Does LLM Safety Training Fail?","created":"2023-07-05","cited_by_count":1651},{"id":"2302.12173","title":"Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection","created":"2023-02-23","cited_by_count":1443},{"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":"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":"2112.00861","title":"A General Language Assistant as a Laboratory for Alignment","created":"2021-12-01","cited_by_count":1055},{"id":"2209.10652","title":"Toy Models of Superposition","created":"2022-09-21","cited_by_count":971},{"id":"2209.11895","title":"In-context Learning and Induction Heads","created":"2022-09-24","cited_by_count":964},{"id":"2209.07858","title":"Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned","created":"2022-08-23","cited_by_count":729},{"id":"2304.14997","title":"Towards Automated Circuit Discovery for Mechanistic Interpretability","created":"2023-04-28","cited_by_count":724},{"id":"2302.00083","title":"In-Context Retrieval-Augmented Language Models","created":"2023-01-31","cited_by_count":702},{"id":"2401.10020","title":"Self-Rewarding Language Models","created":"2024-01-18","cited_by_count":681},{"id":"2406.00515","title":"A Survey on Large Language Models for Code Generation","created":"2024-06-01","cited_by_count":658},{"id":"2308.10848","title":"AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors","created":"2023-08-21","cited_by_count":598},{"id":"2404.02151","title":"Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks","created":"2024-04-02","cited_by_count":486},{"id":"2310.03684","title":"SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks","created":"2023-10-05","cited_by_count":469},{"id":"2412.05579","title":"LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods","created":"2024-12-07","cited_by_count":465},{"id":"2001.09768","title":"Artificial Intelligence, Values and Alignment","created":"2020-01-13","cited_by_count":448},{"id":"2406.06592","title":"Improve Mathematical Reasoning in Language Models by Automated Process Supervision","created":"2024-06-05","cited_by_count":441},{"id":"2406.04692","title":"Mixture-of-Agents Enhances Large Language Model Capabilities","created":"2024-06-07","cited_by_count":438},{"id":"2305.15294","title":"Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergy","created":"2023-05-24","cited_by_count":346},{"id":"2406.04313","title":"Improving Alignment and Robustness with Circuit Breakers","created":"2024-06-06","cited_by_count":322},{"id":"1909.07528","title":"Emergent Tool Use From Multi-Agent Autocurricula","created":"2019-09-17","cited_by_count":313},{"id":"2304.08354","title":"Tool Learning with Foundation Models","created":"2023-04-17","cited_by_count":302},{"id":"2310.19852","title":"AI Alignment: A Comprehensive Survey","created":"2023-10-30","cited_by_count":263},{"id":"2507.11473","title":"Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety","created":"2025-07-15","cited_by_count":249},{"id":"2310.16427","title":"PromptAgent: Strategic Planning with Language Models Enables Expert-level Prompt Optimization","created":"2023-10-25","cited_by_count":233},{"id":"2306.12001","title":"An Overview of Catastrophic AI Risks","created":"2023-06-21","cited_by_count":222},{"id":"2305.14283","title":"Query Rewriting for Retrieval-Augmented Large Language Models","created":"2023-05-23","cited_by_count":213},{"id":"2501.16496","title":"Open Problems in Mechanistic Interpretability","created":"2025-01-27","cited_by_count":179},{"id":"2405.11403","title":"MapCoder: Multi-Agent Code Generation for Competitive Problem Solving","created":"2024-05-18","cited_by_count":177},{"id":"2012.08630","title":"Open Problems in Cooperative AI","created":"2020-12-15","cited_by_count":168},{"id":"2404.11584","title":"The Landscape of Emerging AI Agent Architectures for Reasoning, Planning, and Tool Calling: A Survey","created":"2024-04-17","cited_by_count":168},{"id":"2502.14143","title":"Multi-Agent Risks from Advanced AI","created":"2025-02-19","cited_by_count":163},{"id":"2210.02441","title":"Ask Me Anything: A simple strategy for prompting language models","created":"2022-10-05","cited_by_count":155},{"id":"2502.12025","title":"SafeChain: Safety of Language Models with Long Chain-of-Thought Reasoning Capabilities","created":"2025-02-17","cited_by_count":136},{"id":"2403.13793","title":"Evaluating Frontier Models for Dangerous Capabilities","created":"2024-03-20","cited_by_count":128},{"id":"2502.14847","title":"Red-Teaming LLM Multi-Agent Systems via Communication Attacks","created":"2025-02-20","cited_by_count":122},{"id":"1710.03748","title":"Emergent Complexity via Multi-Agent Competition","created":"2017-10-10","cited_by_count":120},{"id":"2406.12814","title":"Dissecting Adversarial Robustness of Multimodal LM Agents","created":"2024-06-18","cited_by_count":120},{"id":"2407.02646","title":"A Practical Review of Mechanistic Interpretability for Transformer-Based Language Models","created":"2024-07-02","cited_by_count":118},{"id":"2402.07510","title":"Secret Collusion among AI Agents: Multi-Agent Deception via Steganography","created":"2024-02-12","cited_by_count":113},{"id":"2404.16244","title":"The Ethics of Advanced AI Assistants","created":"2024-04-24","cited_by_count":107},{"id":"2206.13353","title":"Is Power-Seeking AI an Existential Risk?","created":"2022-06-16","cited_by_count":105},{"id":"2407.04622","title":"On scalable oversight with weak LLMs judging strong LLMs","created":"2024-07-05","cited_by_count":99},{"id":"2504.00587","title":"AgentNet: Decentralized Evolutionary Coordination for LLM-based Multi-Agent Systems","created":"2025-04-01","cited_by_count":90},{"id":"2404.02183","title":"Self-Organized Agents: A LLM Multi-Agent Framework toward Ultra Large-Scale Code Generation and Optimization","created":"2024-04-02","cited_by_count":84},{"id":"2401.13138","title":"Visibility into AI Agents","created":"2024-01-23","cited_by_count":79},{"id":"2206.04737","title":"Outsider Oversight: Designing a Third Party Audit Ecosystem for AI Governance","created":"2022-06-09","cited_by_count":67},{"id":"2406.05498","title":"SelfDefend: LLMs Can Defend Themselves against Jailbreaking in a Practical Manner","created":"2024-06-08","cited_by_count":63},{"id":"2403.02475","title":"Enhancing LLM Safety via Constrained Direct Preference Optimization","created":"2024-03-04","cited_by_count":49},{"id":"2303.09387","title":"Characterizing Manipulation from AI Systems","created":"2023-03-16","cited_by_count":43},{"id":"2501.10114","title":"Infrastructure for AI Agents","created":"2025-01-17","cited_by_count":41},{"id":"2404.10636","title":"What are human values, and how do we align AI to them?","created":"2024-03-27","cited_by_count":32},{"id":"2405.10313","title":"How Far Are We From AGI: Are LLMs All We Need?","created":"2024-05-16","cited_by_count":31},{"id":"2504.21848","title":"Characterizing AI Agents for Alignment and Governance","created":"2025-04-30","cited_by_count":30},{"id":"2509.04876","title":"OSC: Cognitive Orchestration through Dynamic Knowledge Alignment in Multi-Agent LLM Collaboration","created":"2025-09-05","cited_by_count":30},{"id":"2309.01933","title":"Provably safe systems: the only path to controllable AGI","created":"2023-09-05","cited_by_count":29},{"id":"1805.01109","title":"AGI Safety Literature Review","created":"2018-05-03","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":"2505.19301","title":"A Novel Zero-Trust Identity Framework for Agentic AI: Decentralized Authentication and Fine-Grained Access Control","created":"2025-05-25","cited_by_count":28},{"id":"2411.17713","title":"Llama Guard 3-1B-INT4: Compact and Efficient Safeguard for Human-AI Conversations","created":"2024-11-18","cited_by_count":26},{"id":"2505.14667","title":"SAFEPATH: Preventing Harmful Reasoning in Chain-of-Thought via Early Alignment","created":"2025-05-20","cited_by_count":24},{"id":"2504.18530","title":"Scaling Laws For Scalable Oversight","created":"2025-04-25","cited_by_count":23},{"id":"1901.00064","title":"Impossibility and Uncertainty Theorems in AI Value Alignment (or why your AGI should not have a utility function)","created":"2018-12-31","cited_by_count":22},{"id":"2509.10147","title":"Virtual Agent Economies","created":"2025-09-12","cited_by_count":21},{"id":"2502.07663","title":"Human Decision-making is Susceptible to AI-driven Manipulation","created":"2025-02-11","cited_by_count":19},{"id":"2404.04289","title":"Designing for Human-Agent Alignment: Understanding what humans want from their agents","created":"2024-04-04","cited_by_count":18},{"id":"2509.01063","title":"An Economy of AI Agents","created":"2025-09-01","cited_by_count":18},{"id":"2502.10581","title":"Do We Need to Verify Step by Step? Rethinking Process Supervision from a Theoretical Perspective","created":"2025-02-14","cited_by_count":17},{"id":"2504.10915","title":"LOKA Protocol: A Decentralized Framework for Trustworthy and Ethical AI Agent Ecosystems","created":"2025-04-15","cited_by_count":16},{"id":"1607.00913","title":"Superintelligence cannot be contained: Lessons from Computability Theory","created":"2016-07-04","cited_by_count":13},{"id":"2503.13754","title":"From Autonomous Agents to Integrated Systems, A New Paradigm: Orchestrated Distributed Intelligence","created":"2025-03-17","cited_by_count":12},{"id":"2508.13732","title":"Self-Organizing Agent Network for LLM-based Workflow Automation","created":"2025-08-19","cited_by_count":12},{"id":"2507.14660","title":"When Autonomy Goes Rogue: Preparing for Risks of Multi-Agent Collusion in Social Systems","created":"2025-07-19","cited_by_count":11},{"id":"2408.16074","title":"Verification methods for international AI agreements","created":"2024-08-28","cited_by_count":10},{"id":"2502.15212","title":"Measuring AI agent autonomy: Towards a scalable approach with code inspection","created":"2025-02-21","cited_by_count":10},{"id":"2505.08120","title":"Putting It All into Context: Simplifying Agents with LCLMs","created":"2025-05-12","cited_by_count":9},{"id":"2502.00580","title":"Defense Against the Dark Prompts: Mitigating Best-of-N Jailbreaking with Prompt Evaluation","created":"2025-02-01","cited_by_count":8},{"id":"1707.08476","title":"Guidelines for Artificial Intelligence Containment","created":"2017-07-24","cited_by_count":7},{"id":"2506.11083","title":"RedDebate: Safer Responses Through Multi-Agent Red Teaming Debates","created":"2025-06-04","cited_by_count":7},{"id":"1906.08667","title":"A network approach to cartel detection in public auction markets","created":"2019-06-20","cited_by_count":5},{"id":"2310.14455","title":"An International Consortium for Evaluations of Societal-Scale Risks from Advanced AI","created":"2023-10-22","cited_by_count":5},{"id":"2501.17755","title":"AI Governance through Markets","created":"2025-01-29","cited_by_count":5},{"id":"2502.00012","title":"Lessons from complexity theory for AI governance","created":"2025-01-07","cited_by_count":5},{"id":"2508.14231","title":"Incident Analysis for AI Agents","created":"2025-08-19","cited_by_count":5},{"id":"2508.21323","title":"LLM-driven Provenance Forensics for Threat Investigation and Detection","created":"2025-08-29","cited_by_count":5},{"id":"2307.08171","title":"Credit Assignment: Challenges and Opportunities in Developing Human-like AI Agents","created":"2023-07-16","cited_by_count":4},{"id":"2408.07933","title":"Adapting cybersecurity frameworks to manage frontier AI risks: A defense-in-depth approach","created":"2024-08-15","cited_by_count":4},{"id":"2501.17112","title":"Decoding Human Preferences in Alignment: An Improved Approach to Inverse Constitutional AI","created":"2025-01-28","cited_by_count":4},{"id":"2502.04675","title":"Scalable Oversight for Superhuman AI via Recursive Self-Critiquing","created":"2025-02-07","cited_by_count":4}],"next_cursor":"100"}