{"total":31,"rows":[{"id":"2504.07952","title":"Dynamic Cheatsheet: Test-Time Learning with Adaptive Memory","created":"2025-04-10","cited_by_count":163,"area":null},{"id":"2602.15785","title":"This human study did not involve human subjects: Validating LLM simulations as behavioral evidence","created":"2026-02-17","cited_by_count":29,"area":null},{"id":"2507.12691","title":"Benchmarking Deception Probes via Black-to-White Performance Boosts","created":"2025-07-16","cited_by_count":19,"area":null},{"id":"2509.26072","title":"The Silent Judge: Unacknowledged Shortcut Bias in LLM-as-a-Judge","created":"2025-09-30","cited_by_count":15,"area":null},{"id":"2511.22662","title":"Difficulties with Evaluating a Deception Detector for AIs","created":"2025-11-27","cited_by_count":13,"area":null},{"id":"2512.18792","title":"The Dead Salmons of AI Interpretability","created":"2025-12-21","cited_by_count":12,"area":null},{"id":"2507.09788","title":"TinyTroupe: An LLM-powered Multiagent Persona Simulation Toolkit","created":"2025-07-13","cited_by_count":7,"area":null},{"id":"2511.03235","title":"From Five Dimensions to Many: Large Language Models as Precise and Interpretable Psychological Profilers","created":"2025-11-05","cited_by_count":5,"area":null},{"id":"2506.21584","title":"Empirical Evidence for Alignment Faking in a Small LLM and Prompt-Based Mitigation Techniques","created":"2025-06-17","cited_by_count":4,"area":null},{"id":"2605.29601","title":"Training Deliberative Monitors for Black-Box Scheming Detection","created":"2026-05-28","cited_by_count":4,"area":null},{"id":"2508.02584","title":"MArgE: Meshing Argumentative Evidence from Multiple Large Language Models for Justifiable Claim Verification","created":"2025-08-04","cited_by_count":3,"area":null},{"id":"2601.14553","title":"Self-Blinding and Counterfactual Self-Simulation Mitigate Biases and Sycophancy in Large Language Models","created":"2026-01-21","cited_by_count":3,"area":null},{"id":"2605.25052","title":"Faithfulness Metrics Don't Measure Faithfulness: A Meta-Evaluation with Ground Truth","created":"2026-05-24","cited_by_count":3,"area":null},{"id":"2602.04003","title":"When AI Persuades: Adversarial Explanation Attacks on Human Trust in AI-Assisted Decision Making","created":"2026-02-03","cited_by_count":2,"area":null},{"id":"2605.21491","title":"Teaching Language Models to Forecast Research Success Through Comparative Idea Evaluation","created":"2026-04-06","cited_by_count":2,"area":null},{"id":"2510.13393","title":"Learnable Game-theoretic Policy Optimization for Data-centric Self-explanation Rationalization","created":"2025-10-15","cited_by_count":1,"area":null},{"id":"2512.08645","title":"Chain-of-Image Generation: Toward Monitorable and Controllable Image Generation","created":"2025-12-09","cited_by_count":1,"area":null},{"id":"2602.13241","title":"Empowering 9-1-1 Calltaking Training with Generative AI: Experiences and Lessons Learned","created":"2026-01-30","cited_by_count":1,"area":null},{"id":"2606.26071","title":"Model Forensics: Investigating Whether Concerning Behavior Reflects Misalignment","created":"2026-06-24","cited_by_count":1,"area":null},{"id":"2608.02621","title":"Knowing the Form, Not the Function: Automatically Auditing Answer--Authority Decoupling in Legal Benchmarks","created":"2026-07-03","cited_by_count":1,"area":null},{"id":"2609.02852","title":"The Implications of Linguistic Illegibility for LLM Security","created":"2026-09-02","cited_by_count":1,"area":null},{"id":"2609.07731","title":"The Profit Alignment Problem: How Profit Mandates Induce Alignment Failures in LLMs","created":"2026-09-07","cited_by_count":1,"area":null},{"id":"2508.06017","title":"Position: Intelligent Coding Systems Should Write Programs with Justifications","created":"2025-08-08","cited_by_count":0,"area":null},{"id":"2511.01363","title":"Automatic Minds: Cognitive Parallels Between Hypnotic States and Large Language Model Processing","created":"2025-11-03","cited_by_count":0,"area":null},{"id":"2601.15115","title":"Training-Free and Interpretable Hateful Video Detection via Multi-stage Adversarial Reasoning","created":"2026-01-21","cited_by_count":0,"area":null},{"id":"2603.01254","title":"LLM Self-Explanations Fail Semantic Invariance","created":"2026-03-01","cited_by_count":0,"area":null},{"id":"2603.13351","title":"Prompt Complexity Dilutes Structured Reasoning: A Follow-Up Study on the Car Wash Problem","created":"2026-03-07","cited_by_count":0,"area":null},{"id":"2606.11445","title":"Forecasting Future Behavior as a Learning Task","created":"2026-06-09","cited_by_count":0,"area":null},{"id":"2606.21121","title":"Answer Engineering: Local Trajectory Editing for Protocol-Constrained Decision Making in Large Language Models","created":"2026-06-19","cited_by_count":0,"area":null},{"id":"2607.17621","title":"Mechanistic Attention Guidance for Agent Memory Refinement","created":"2026-07-20","cited_by_count":0,"area":null},{"id":"2607.25648","title":"Why Public Service AI Governance Frameworks Risk Failing in the Age of General-Purpose AI: Lessons from Policing","created":"2026-07-28","cited_by_count":0,"area":null}],"next_cursor":null}