{"total":27,"rows":[{"id":"2403.08319","title":"Knowledge Conflicts for LLMs: A Survey","created":"2024-03-13","cited_by_count":283,"area":null},{"id":"2406.19384","title":"The Remarkable Robustness of LLMs: Stages of Inference?","created":"2024-06-27","cited_by_count":146,"area":null},{"id":"2401.14446","title":"Black-Box Access is Insufficient for Rigorous AI Audits","created":"2024-01-25","cited_by_count":126,"area":null},{"id":"2311.02462","title":"Levels of AGI for Operationalizing Progress on the Path to AGI","created":"2023-11-04","cited_by_count":96,"area":null},{"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,"area":null},{"id":"2406.16254","title":"Confidence Regulation Neurons in Language Models","created":"2024-06-24","cited_by_count":57,"area":null},{"id":"2310.20501","title":"Neural Retrievers are Biased Towards LLM-Generated Content","created":"2023-10-31","cited_by_count":38,"area":null},{"id":"2408.11865","title":"How Susceptible are LLMs to Influence in Prompts?","created":"2024-08-17","cited_by_count":33,"area":null},{"id":"2402.08323","title":"Mapping the Ethics of Generative AI: A Comprehensive Scoping Review","created":"2024-02-13","cited_by_count":19,"area":null},{"id":"2406.01860","title":"Eliciting the Priors of Large Language Models using Iterated In-Context Learning","created":"2024-06-04","cited_by_count":19,"area":null},{"id":"2404.12699","title":"SOPHON: Non-Fine-Tunable Learning to Restrain Task Transferability For Pre-trained Models","created":"2024-04-19","cited_by_count":17,"area":null},{"id":"2405.16546","title":"Cocktail: A Comprehensive Information Retrieval Benchmark with LLM-Generated Documents Integration","created":"2024-05-26","cited_by_count":17,"area":null},{"id":"2501.11739","title":"Episodic memory in AI agents poses risks that should be studied and mitigated","created":"2025-01-20","cited_by_count":11,"area":null},{"id":"2402.07776","title":"TELLER: A Trustworthy Framework for Explainable, Generalizable and Controllable Fake News Detection","created":"2024-02-12","cited_by_count":10,"area":null},{"id":"2404.02675","title":"Responsible Reporting for Frontier AI Development","created":"2024-04-03","cited_by_count":10,"area":null},{"id":"2411.16035","title":"Predicting Emergent Capabilities by Finetuning","created":"2024-11-25","cited_by_count":10,"area":null},{"id":"2403.14791","title":"Particip-AI: A Democratic Surveying Framework for Anticipating Future AI Use Cases, Harms and Benefits","created":"2024-03-21","cited_by_count":9,"area":null},{"id":"2404.05388","title":"An AI System Evaluation Framework for Advancing AI Safety: Terminology, Taxonomy, Lifecycle Mapping","created":"2024-04-08","cited_by_count":8,"area":null},{"id":"2412.08897","title":"Neural Interactive Proofs","created":"2024-12-12","cited_by_count":7,"area":null},{"id":"2512.00371","title":"Evaluating LLMs in Open-Source Games","created":"2025-11-29","cited_by_count":5,"area":null},{"id":"2503.05856","title":"This Is Your Doge, If It Please You: Exploring Deception and Robustness in Mixture of LLMs","created":"2025-03-07","cited_by_count":4,"area":null},{"id":"2403.06537","title":"On the Consideration of AI Openness: Can Good Intent Be Abused?","created":"2024-03-11","cited_by_count":2,"area":null},{"id":"2407.00805","title":"Towards Shutdownable Agents via Stochastic Choice","created":"2024-06-30","cited_by_count":2,"area":null},{"id":"2602.22519","title":"A Mathematical Theory of Agency and Intelligence","created":"2026-02-26","cited_by_count":1,"area":null},{"id":"2504.19990","title":"Mitigating Societal Cognitive Overload in the Age of AI: Challenges and Directions","created":"2025-04-28","cited_by_count":0,"area":null},{"id":"2511.07699","title":"Misaligned by Design: Incentive Failures in Machine Learning","created":"2025-11-10","cited_by_count":0,"area":null},{"id":"2604.05826","title":"Reciprocal Trust and Distrust in Artificial Intelligence Systems: The Hard Problem of Regulation","created":"2026-04-07","cited_by_count":0,"area":null}],"next_cursor":null}