{"total":32,"rows":[{"id":"2109.13916","title":"Unsolved Problems in ML Safety","created":"2021-09-28","cited_by_count":292,"area":null},{"id":"2109.10862","title":"Recursively Summarizing Books with Human Feedback","created":"2021-09-22","cited_by_count":290,"area":null},{"id":"2209.00626","title":"The Alignment Problem from a Deep Learning Perspective","created":"2022-08-30","cited_by_count":258,"area":null},{"id":"2105.14111","title":"Goal Misgeneralization in Deep Reinforcement Learning","created":"2021-05-28","cited_by_count":123,"area":null},{"id":"2206.13353","title":"Is Power-Seeking AI an Existential Risk?","created":"2022-06-16","cited_by_count":105,"area":null},{"id":"2310.11589","title":"Eliciting Human Preferences with Language Models","created":"2023-10-17","cited_by_count":92,"area":null},{"id":"2304.00612","title":"Eight Things to Know about Large Language Models","created":"2023-04-02","cited_by_count":73,"area":null},{"id":"2407.21792","title":"Safetywashing: Do AI Safety Benchmarks Actually Measure Safety Progress?","created":"2024-07-31","cited_by_count":61,"area":null},{"id":"2204.11966","title":"Estimating and Penalizing Induced Preference Shifts in Recommender Systems","created":"2022-04-25","cited_by_count":29,"area":null},{"id":"2205.13026","title":"Preference Dynamics Under Personalized Recommendations","created":"2022-05-25","cited_by_count":25,"area":null},{"id":"2109.04083","title":"User Tampering in Reinforcement Learning Recommender Systems","created":"2021-09-09","cited_by_count":23,"area":null},{"id":"2204.10018","title":"Path-Specific Objectives for Safer Agent Incentives","created":"2022-04-21","cited_by_count":20,"area":null},{"id":"2306.13945","title":"Large Sequence Models for Sequential Decision-Making: A Survey","created":"2023-06-24","cited_by_count":19,"area":null},{"id":"2404.12366","title":"Accounting for AI and Users Shaping One Another: The Role of Mathematical Models","created":"2024-04-18","cited_by_count":11,"area":null},{"id":"2310.15047","title":"Implicit meta-learning may lead language models to trust more reliable sources","created":"2023-10-23","cited_by_count":10,"area":null},{"id":"2305.17601","title":"Incentivizing honest performative predictions with proper scoring rules","created":"2023-05-28","cited_by_count":9,"area":null},{"id":"2308.02435","title":"Designing Fiduciary Artificial Intelligence","created":"2023-07-27","cited_by_count":8,"area":null},{"id":"2310.06167","title":"Predictable Artificial Intelligence","created":"2023-10-09","cited_by_count":8,"area":null},{"id":"2111.12146","title":"Sharing to learn and learning to share; Fitting together Meta-Learning, Multi-Task Learning, and Transfer Learning: A meta review","created":"2021-11-23","cited_by_count":6,"area":null},{"id":"2508.14231","title":"Incident Analysis for AI Agents","created":"2025-08-19","cited_by_count":5,"area":null},{"id":"2510.21332","title":"Weak-to-Strong Generalization under Distribution Shifts","created":"2025-10-24","cited_by_count":4,"area":null},{"id":"2307.10987","title":"Characterising Decision Theories with Mechanised Causal Graphs","created":"2023-07-20","cited_by_count":3,"area":null},{"id":"2501.01665","title":"FairSense: Long-Term Fairness Analysis of ML-Enabled Systems","created":"2025-01-03","cited_by_count":3,"area":null},{"id":"2109.05278","title":"Existence conditions for hidden feedback loops in online recommender systems","created":"2021-09-11","cited_by_count":1,"area":null},{"id":"2209.11801","title":"Solutions to preference manipulation in recommender systems require knowledge of meta-preferences","created":"2022-09-14","cited_by_count":1,"area":null},{"id":"2412.20732","title":"Joint Scoring Rules: Zero-Sum Competition Avoids Performative Prediction","created":"2024-12-30","cited_by_count":1,"area":null},{"id":"2605.13307","title":"PRISM-X: Experiments on Personalised Fine-Tuning with Human and Simulated Users","created":"2026-05-13","cited_by_count":1,"area":null},{"id":"2606.26418","title":"Unbiased Canonical Set-Valued Oracles Via Lattice Theory","created":"2026-06-24","cited_by_count":1,"area":null},{"id":"2203.10629","title":"Explicit User Manipulation in Reinforcement Learning Based Recommender Systems","created":"2022-03-20","cited_by_count":0,"area":null},{"id":"2305.14537","title":"Disincentivizing Polarization in Social Networks","created":"2023-05-23","cited_by_count":0,"area":null},{"id":"2503.03401","title":"Evolutionary Prediction Games","created":"2025-03-05","cited_by_count":0,"area":null},{"id":"2608.14795","title":"Individual Disempowerment through an Advice Channel: Control Loss when Influence is Endogenous","created":"2026-08-14","cited_by_count":0,"area":null}],"next_cursor":null}