{"total":82,"rows":[{"id":"2204.06745","title":"GPT-NeoX-20B: An Open-Source Autoregressive Language Model","created":"2022-04-14","cited_by_count":713,"area":null},{"id":"2206.05802","title":"Self-critiquing models for assisting human evaluators","created":"2022-06-12","cited_by_count":380,"area":null},{"id":"2109.13916","title":"Unsolved Problems in ML Safety","created":"2021-09-28","cited_by_count":292,"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":"2110.06674","title":"Truthful AI: Developing and governing AI that does not lie","created":"2021-10-13","cited_by_count":113,"area":null},{"id":"2206.13353","title":"Is Power-Seeking AI an Existential Risk?","created":"2022-06-16","cited_by_count":105,"area":null},{"id":"2102.03896","title":"Consequences of Misaligned AI","created":"2021-02-07","cited_by_count":80,"area":null},{"id":"2310.09144","title":"Goodhart's Law in Reinforcement Learning","created":"2023-10-13","cited_by_count":41,"area":null},{"id":"2209.13020","title":"Law Informs Code: A Legal Informatics Approach to Aligning Artificial Intelligence with Humans","created":"2022-09-14","cited_by_count":23,"area":null},{"id":"2202.09519","title":"The four-fifths rule is not disparate impact: a woeful tale of epistemic trespassing in algorithmic fairness","created":"2022-02-19","cited_by_count":21,"area":null},{"id":"2405.03207","title":"A Philosophical Introduction to Language Models - Part II: The Way Forward","created":"2024-05-06","cited_by_count":18,"area":null},{"id":"2211.07280","title":"A taxonomic system for failure cause analysis of open source AI incidents","created":"2022-11-14","cited_by_count":9,"area":null},{"id":"2410.09638","title":"On Goodhart's law, with an application to value alignment","created":"2024-10-12","cited_by_count":9,"area":null},{"id":"2603.12520","title":"When LLM Judge Scores Look Good but Best-of-N Decisions Fail","created":"2026-03-12","cited_by_count":9,"area":null},{"id":"2310.18244","title":"A Review of the Evidence for Existential Risk from AI via Misaligned Power-Seeking","created":"2023-10-27","cited_by_count":8,"area":null},{"id":"2508.14927","title":"AI Testing Should Account for Sophisticated Strategic Behaviour","created":"2025-08-19","cited_by_count":6,"area":null},{"id":"2607.14004","title":"Do Agent Optimizers Compound? A Continual-Learning Evaluation on Terminal-Bench 2.0","created":"2026-07-15","cited_by_count":6,"area":null},{"id":"2310.14455","title":"An International Consortium for Evaluations of Societal-Scale Risks from Advanced AI","created":"2023-10-22","cited_by_count":5,"area":null},{"id":"2405.04048","title":"Philosophy of Cognitive Science in the Age of Deep Learning","created":"2024-05-07","cited_by_count":5,"area":null},{"id":"2208.05320","title":"PEPPER: Empowering User-Centric Recommender Systems over Gossip Learning","created":"2022-08-09","cited_by_count":4,"area":null},{"id":"2305.19223","title":"Intent-aligned AI systems deplete human agency: the need for agency foundations research in AI safety","created":"2023-05-30","cited_by_count":4,"area":null},{"id":"2601.16909","title":"Preventing the Collapse of Peer Review Requires Verification-First AI","created":"2026-01-23","cited_by_count":3,"area":null},{"id":"2603.08371","title":"Leaderboard Incentives: Model Rankings under Strategic Post-Training","created":"2026-03-09","cited_by_count":3,"area":null},{"id":"2605.17829","title":"Interactive Evaluation Requires a Design Science","created":"2026-05-18","cited_by_count":3,"area":null},{"id":"2606.04075","title":"Large Language Models Hack Rewards, and Society","created":"2026-06-02","cited_by_count":3,"area":null},{"id":"2305.15299","title":"Science in the Era of ChatGPT, Large Language Models and Generative AI: Challenges for Research Ethics and How to Respond","created":"2023-05-24","cited_by_count":2,"area":null},{"id":"2503.07341","title":"The Economics of p(doom): Scenarios of Existential Risk and Economic Growth in the Age of Transformative AI","created":"2025-03-10","cited_by_count":2,"area":null},{"id":"2505.23445","title":"The Strong, Weak and Benign Goodhart's law. An independence-free and paradigm-agnostic formalisation","created":"2025-05-29","cited_by_count":2,"area":null},{"id":"2511.06148","title":"Large Language Models Develop Novel Social Biases Through Adaptive Exploration","created":"2025-11-08","cited_by_count":2,"area":null},{"id":"2602.05656","title":"Alignment Verifiability in Large Language Models: Normative Indistinguishability under Behavioral Evaluation","created":"2026-02-05","cited_by_count":2,"area":null},{"id":"2603.24126","title":"Likelihood Hacking in Probabilistic Program Synthesis","created":"2026-03-25","cited_by_count":2,"area":null},{"id":"2605.06390","title":"Automated alignment is harder than you think","created":"2026-05-07","cited_by_count":2,"area":null},{"id":"2605.07671","title":"The Endogeneity of Miscalibration: Impossibility and Escape in Scored Reporting","created":"2026-05-08","cited_by_count":2,"area":null},{"id":"2608.13566","title":"Don't Claim Benchmark-Oriented Optimization Improves General Coding Capability -- Diverse Evaluation Is Required","created":"2026-06-26","cited_by_count":2,"area":null},{"id":"2210.07126","title":"Challenges in Explanation Quality Evaluation","created":"2022-10-13","cited_by_count":1,"area":null},{"id":"2603.15017","title":"Consequentialist Objectives and Catastrophe","created":"2026-03-16","cited_by_count":1,"area":null},{"id":"2605.26200","title":"Workflow Closure Is Not Scientific Closure in Auto-Research Systems","created":"2026-05-25","cited_by_count":1,"area":null},{"id":"2606.11417","title":"Signed Compression Progress on a Sealed Audit is Goodhart-Resistant","created":"2026-06-09","cited_by_count":1,"area":null},{"id":"2606.23597","title":"Against Proxy Optimization","created":"2026-06-22","cited_by_count":1,"area":null},{"id":"2607.02134","title":"Coding-agents can replicate scientific machine learning papers","created":"2026-07-02","cited_by_count":1,"area":null},{"id":"2607.08946","title":"Training, Reading, and Editing Legible Transformers","created":"2026-07-09","cited_by_count":1,"area":null},{"id":"2608.04896","title":"When Shared Rollouts Fail in Defensive Driving Evaluation: A NAVSIM Score Basis Audit","created":"2026-08-05","cited_by_count":1,"area":null},{"id":"2608.09819","title":"Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA","created":"2026-08-10","cited_by_count":1,"area":null},{"id":"2609.32390","title":"Reward Hacking and Agent Containment Failure: A Monte Carlo Study Based on the 2026 Hugging Face Incident","created":"2026-09-26","cited_by_count":1,"area":null},{"id":"2302.07872","title":"Data-Centric Governance","created":"2023-02-14","cited_by_count":0,"area":null},{"id":"2308.05120","title":"Dynamic Model Agnostic Reliability Evaluation of Machine-Learning Methods Integrated in Instrumentation & Control Systems","created":"2023-08-08","cited_by_count":0,"area":null},{"id":"2403.05540","title":"Extinction Risks from AI: Invisible to Science?","created":"2024-02-02","cited_by_count":0,"area":null},{"id":"2407.06098","title":"Epistemological Bias As a Means for the Automated Detection of Injustices in Text","created":"2024-07-08","cited_by_count":0,"area":null},{"id":"2509.02391","title":"Gaming and Cooperation in Federated Learning: What Can Happen and How to Monitor It","created":"2025-09-02","cited_by_count":0,"area":null},{"id":"2510.02840","title":"Take Goodhart Seriously: Principled Limit on General-Purpose AI Optimization","created":"2025-10-03","cited_by_count":0,"area":null},{"id":"2604.07709","title":"IatroBench: A Pre-Registered Benchmark of Clinical Omission in Language Models","created":"2026-04-09","cited_by_count":0,"area":null},{"id":"2604.16516","title":"Operationalizing Fairness in Text-to-Image Models: A Survey of Bias, Fairness Audits and Mitigation Strategies","created":"2026-04-15","cited_by_count":0,"area":null},{"id":"2605.10956","title":"Acceleration of horizontal numerical advection for atmospheric modeling through surrogate modeling with temporal coarse-graining","created":"2026-04-30","cited_by_count":0,"area":null},{"id":"2605.11496","title":"The Evaluation Differential: When Frontier AI Models Recognise They Are Being Tested","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2605.14407","title":"Metis AI: The Overlooked Middle Zone Between AI-Native and World-Movers","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2605.22612","title":"Healthcare LLM Benchmarks Are Only as Good as Their Explicit Assumptions","created":"2026-05-21","cited_by_count":0,"area":null},{"id":"2605.30680","title":"Healthcare Mechanisms from Policy-as-Code Search under Strategic Provider Response","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2605.30916","title":"Welfare, Improvability, and Variance: A Principal-Agent Approach to Optimal Benchmark Item Aggregation","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2606.12442","title":"Reframing AI Loss of Control: What Control Is, How to Have It, How to Lose It","created":"2026-05-19","cited_by_count":0,"area":null},{"id":"2606.16319","title":"Architectural Wisdom: A Framework for Governing Optimization in AI Systems","created":"2026-06-15","cited_by_count":0,"area":null},{"id":"2606.16914","title":"Greed Is Learned: Visible Incentives as Reward-Hacking Triggers","created":"2026-06-15","cited_by_count":0,"area":null},{"id":"2606.18539","title":"TS-Fault: Benchmarking Time Series Forecasters Against Structural Faults","created":"2026-06-16","cited_by_count":0,"area":null},{"id":"2606.28863","title":"Defeat Devices in AI Systems","created":"2026-06-27","cited_by_count":0,"area":null},{"id":"2606.30219","title":"EvalSafetyGap: A Hybrid Survey and Conceptual Framework for LLM Evaluation-Safety Failures","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2607.22682","title":"A Vocabulary for Multi-Agent Automated Research Systems","created":"2026-07-13","cited_by_count":0,"area":null},{"id":"2608.01432","title":"A New Theory of Value for Post-AGI Economics","created":"2026-08-02","cited_by_count":0,"area":null},{"id":"2608.08722","title":"Gaming Without an Attacker: Benchmark Fingerprinting in LLM-Driven Search Under Selection Pressure","created":"2026-08-09","cited_by_count":0,"area":null},{"id":"2608.10209","title":"Evaluation-Conditioned Training: Teaching Models to Generalize to Stronger Oversight Regimes","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2608.13577","title":"AI Evaluation Should Work With Humans","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2608.30466","title":"CHASE: How Content Ecosystems Are Reshaped When Ranking Is the Only Target","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.00064","title":"Attention Sensitivity Is Not Enough: Dissociating Attention-Level and Behavioural In-Context Learning under Fine-Tuning","created":"2026-08-30","cited_by_count":0,"area":null},{"id":"2609.01345","title":"Cheap Verifiers, Large Blind Spots: Measuring the Reliability Cost of Cost-Saving Cascades","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.07559","title":"Scoring Without the Engine: Validating a Deterministic, Manipulation-Resistant Content Score for Generative Engines, End to End","created":"2026-09-07","cited_by_count":0,"area":null},{"id":"2609.09250","title":"No Free Checker: A Survey of Verifiers for Robot Policies","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.13168","title":"A Cross Community Agenda for Speech AI","created":"2026-07-22","cited_by_count":0,"area":null},{"id":"2609.33180","title":"Which Self-Improvements Should We Trust? Reliable Self-Improvement When Agents Reuse Their Benchmarks","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2610.00164","title":"Metric-Construction Coupling Inflates Measured Synthetic Dialect Recovery","created":"2026-09-14","cited_by_count":0,"area":null},{"id":"2610.02608","title":"Time Series Forecasting Benchmarks Need Scenario-Grounded Stress Testing","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.04429","title":"Asking Earns Nothing: Scoring the Decision to Act in BFCL Multi-Turn","created":"2026-10-03","cited_by_count":0,"area":null},{"id":"2610.08878","title":"How Could AI Eliminate Humanity? A Failure-Mode Analysis of Civilizational Risk","created":"2026-10-06","cited_by_count":0,"area":null},{"id":"2610.09296","title":"The AI Evaluation Ecosystem","created":"2026-10-07","cited_by_count":0,"area":null},{"id":"2610.14063","title":"Auditing LLM Program Search for Bermudan Stopping with Primal--Dual Certificates","created":"2026-10-07","cited_by_count":0,"area":null}],"next_cursor":null}