{"list":"other","total":78,"rows":[{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2212.08073","title":"Constitutional AI: Harmlessness from AI Feedback","created":"2022-12-15","cited_by_count":3050},{"id":"2206.04615","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","created":"2022-06-09","cited_by_count":1998},{"id":"2210.09261","title":"Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them","created":"2022-10-17","cited_by_count":1807},{"id":"2307.02483","title":"Jailbroken: How Does LLM Safety Training Fail?","created":"2023-07-05","cited_by_count":1651},{"id":"2310.01405","title":"Representation Engineering: A Top-Down Approach to AI Transparency","created":"2023-10-02","cited_by_count":1336},{"id":"2311.07911","title":"Instruction-Following Evaluation for Large Language Models","created":"2023-11-14","cited_by_count":1228},{"id":"2310.03693","title":"Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!","created":"2023-10-05","cited_by_count":1154},{"id":"2310.13548","title":"Towards Understanding Sycophancy in Language Models","created":"2023-10-20","cited_by_count":1040},{"id":"2202.03286","title":"Red Teaming Language Models with Language Models","created":"2022-02-07","cited_by_count":1026},{"id":"2308.10248","title":"Steering Language Models With Activation Engineering","created":"2023-08-20","cited_by_count":922},{"id":"2105.09938","title":"Measuring Coding Challenge Competence With APPS","created":"2021-05-20","cited_by_count":902},{"id":"2305.14233","title":"Enhancing Chat Language Models by Scaling High-quality Instructional Conversations","created":"2023-05-23","cited_by_count":839},{"id":"2008.02275","title":"Aligning AI With Shared Human Values","created":"2020-08-05","cited_by_count":723},{"id":"2406.15877","title":"BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions","created":"2024-06-22","cited_by_count":546},{"id":"2404.13208","title":"The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions","created":"2024-04-19","cited_by_count":493},{"id":"2404.02151","title":"Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks","created":"2024-04-02","cited_by_count":486},{"id":"2406.05946","title":"Safety Alignment Should Be Made More Than Just a Few Tokens Deep","created":"2024-06-10","cited_by_count":472},{"id":"2309.12288","title":"The Reversal Curse: LLMs trained on \"A is B\" fail to learn \"B is A\"","created":"2023-09-21","cited_by_count":407},{"id":"2503.11926","title":"Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation","created":"2025-03-14","cited_by_count":384},{"id":"2412.14093","title":"Alignment faking in large language models","created":"2024-12-18","cited_by_count":360},{"id":"2412.16339","title":"Deliberative Alignment: Reasoning Enables Safer Language Models","created":"2024-12-20","cited_by_count":308},{"id":"2412.04984","title":"Frontier Models are Capable of In-context Scheming","created":"2024-12-06","cited_by_count":287},{"id":"1906.01820","title":"Risks from Learned Optimization in Advanced Machine Learning Systems","created":"2019-06-05","cited_by_count":258},{"id":"2209.00626","title":"The Alignment Problem from a Deep Learning Perspective","created":"2022-08-30","cited_by_count":258},{"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":"2405.20947","title":"OR-Bench: An Over-Refusal Benchmark for Large Language Models","created":"2024-05-31","cited_by_count":244},{"id":"2312.06942","title":"AI Control: Improving Safety Despite Intentional Subversion","created":"2023-12-12","cited_by_count":229},{"id":"2306.09479","title":"Inverse Scaling: When Bigger Isn't Better","created":"2023-06-15","cited_by_count":207},{"id":"2509.02547","title":"The Landscape of Agentic Reinforcement Learning for LLMs: A Survey","created":"2025-09-02","cited_by_count":205},{"id":"2404.09932","title":"Foundational Challenges in Assuring Alignment and Safety of Large Language Models","created":"2024-04-15","cited_by_count":199},{"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":"2503.08679","title":"Chain-of-Thought Reasoning In The Wild Is Not Always Faithful","created":"2025-03-11","cited_by_count":170},{"id":"2406.07358","title":"AI Sandbagging: Language Models can Strategically Underperform on Evaluations","created":"2024-06-11","cited_by_count":145},{"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":"2511.18397","title":"Natural Emergent Misalignment from Reward Hacking in Production RL","created":"2025-11-23","cited_by_count":136},{"id":"2505.23836","title":"Large Language Models Often Know When They Are Being Evaluated","created":"2025-05-28","cited_by_count":128},{"id":"2503.00555","title":"Safety Tax: Safety Alignment Makes Your Large Reasoning Models Less Reasonable","created":"2025-03-01","cited_by_count":122},{"id":"2401.07927","title":"Are self-explanations from Large Language Models faithful?","created":"2024-01-15","cited_by_count":101},{"id":"2309.05858","title":"Uncovering mesa-optimization algorithms in Transformers","created":"2023-09-11","cited_by_count":100},{"id":"2311.08379","title":"Scheming AIs: Will AIs fake alignment during training in order to get power?","created":"2023-11-14","cited_by_count":97},{"id":"2507.05246","title":"When Chain of Thought is Necessary, Language Models Struggle to Evade Monitors","created":"2025-07-07","cited_by_count":88},{"id":"2506.19823","title":"Persona Features Control Emergent Misalignment","created":"2025-06-24","cited_by_count":86},{"id":"2509.15541","title":"Stress Testing Deliberative Alignment for Anti-Scheming Training","created":"2025-09-19","cited_by_count":86},{"id":"2401.13138","title":"Visibility into AI Agents","created":"2024-01-23","cited_by_count":79},{"id":"2510.07192","title":"Poisoning Attacks on LLMs Require a Near-constant Number of Poison Samples","created":"2025-10-08","cited_by_count":72},{"id":"2502.03407","title":"Detecting Strategic Deception Using Linear Probes","created":"2025-02-05","cited_by_count":68},{"id":"2410.13284","title":"Learning to Route LLMs with Confidence Tokens","created":"2024-10-17","cited_by_count":67},{"id":"2512.18311","title":"Monitoring Monitorability","created":"2025-12-20","cited_by_count":58},{"id":"2512.09742","title":"Weird Generalization and Inductive Backdoors: New Ways to Corrupt LLMs","created":"2025-12-10","cited_by_count":55},{"id":"2505.23575","title":"CoT Red-Handed: Stress Testing Chain-of-Thought Monitoring","created":"2025-05-29","cited_by_count":54},{"id":"2410.21514","title":"Sabotage Evaluations for Frontier Models","created":"2024-10-28","cited_by_count":52},{"id":"2508.09224","title":"From Hard Refusals to Safe-Completions: Toward Output-Centric Safety Training","created":"2025-08-12","cited_by_count":52},{"id":"2504.01849","title":"An Approach to Technical AGI Safety and Security","created":"2025-04-02","cited_by_count":45},{"id":"2504.10374","title":"Ctrl-Z: Controlling AI Agents via Resampling","created":"2025-04-14","cited_by_count":44},{"id":"2403.05518","title":"Bias-Augmented Consistency Training Reduces Biased Reasoning in Chain-of-Thought","created":"2024-03-08","cited_by_count":39},{"id":"2512.04123","title":"Measuring Agents in Production","created":"2025-12-02","cited_by_count":37},{"id":"2512.00193","title":"A Rosetta Stone for AI Benchmarks","created":"2025-11-28","cited_by_count":36},{"id":"2411.03336","title":"Towards evaluations-based safety cases for AI scheming","created":"2024-10-29","cited_by_count":33},{"id":"2601.10160","title":"Alignment Pretraining: AI Discourse Causes Self-Fulfilling (Mis)alignment","created":"2026-01-15","cited_by_count":33},{"id":"2411.17693","title":"Adaptive Deployment of Untrusted LLMs Reduces Distributed Threats","created":"2024-11-26","cited_by_count":31},{"id":"2505.18807","title":"Mitigating Deceptive Alignment via Self-Monitoring","created":"2025-05-24","cited_by_count":29},{"id":"2504.18530","title":"Scaling Laws For Scalable Oversight","created":"2025-04-25","cited_by_count":23},{"id":"2510.19851","title":"Can Reasoning Models Obfuscate Reasoning? Stress-Testing Chain-of-Thought Monitorability","created":"2025-10-21","cited_by_count":22},{"id":"2512.08093","title":"Training LLMs for Honesty via Confessions","created":"2025-12-08","cited_by_count":22},{"id":"2504.11844","title":"Evaluating the Goal-Directedness of Large Language Models","created":"2025-04-16","cited_by_count":16},{"id":"2510.27062","title":"Consistency Training Helps Stop Sycophancy and Jailbreaks","created":"2025-10-31","cited_by_count":16},{"id":"2502.11843","title":"Can LLM Agents Maintain a Persona in Discourse?","created":"2025-02-17","cited_by_count":15},{"id":"2509.18058","title":"Strategic Dishonesty Can Undermine AI Safety Evaluations of Frontier LLMs","created":"2025-09-22","cited_by_count":15},{"id":"2511.06626","title":"Spilling the Beans: Teaching LLMs to Self-Report Their Hidden Objectives","created":"2025-11-10","cited_by_count":15},{"id":"2511.09904","title":"CTRL-ALT-DECEIT: Sabotage Evaluations for Automated AI R&D","created":"2025-11-13","cited_by_count":15},{"id":"2512.07810","title":"Auditing Games for Sandbagging","created":"2025-12-08","cited_by_count":14},{"id":"2512.19027","title":"Recontextualization Mitigates Specification Gaming without Modifying the Specification","created":"2025-12-22","cited_by_count":14},{"id":"2509.13316","title":"Do Activation Verbalization Methods Convey Privileged Information?","created":"2025-09-16","cited_by_count":10},{"id":"2601.23045","title":"The Hot Mess of AI: How Does Misalignment Scale With Model Intelligence and Task Complexity?","created":"2026-01-30","cited_by_count":10},{"id":"2506.06414","title":"Benchmarking Misuse Mitigation Against Covert Adversaries","created":"2025-06-06","cited_by_count":8},{"id":"2512.22154","title":"Practical challenges of control monitoring in frontier AI deployments","created":"2025-12-15","cited_by_count":8},{"id":"2502.16366","title":"A Generative Approach to LLM Harmfulness Mitigation with Red Flag Tokens","created":"2025-02-22","cited_by_count":1}],"next_cursor":null}