{"total":99,"rows":[{"id":"2508.02087","title":"When Truth Is Overridden: Uncovering the Internal Origins of Sycophancy in Large Language Models","created":"2025-08-04","cited_by_count":50,"area":null},{"id":"2511.08579","title":"Training Language Models to Explain Their Own Computations","created":"2025-11-11","cited_by_count":30,"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":"2511.01805","title":"Accumulating Context Changes the Beliefs of Language Models","created":"2025-11-03","cited_by_count":28,"area":null},{"id":"2505.17120","title":"Self-Interpretability: LLMs Can Describe Complex Internal Processes that Drive Their Decisions","created":"2025-05-21","cited_by_count":25,"area":null},{"id":"2512.08093","title":"Training LLMs for Honesty via Confessions","created":"2025-12-08","cited_by_count":22,"area":null},{"id":"2605.19943","title":"Probabilistic Tiny Recursive Model","created":"2026-05-19","cited_by_count":19,"area":null},{"id":"2505.14633","title":"Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas","created":"2025-05-20","cited_by_count":18,"area":null},{"id":"2507.19218","title":"Technological folie \\`a deux: Feedback Loops Between AI Chatbots and Mental Illness","created":"2025-07-25","cited_by_count":15,"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":"2605.12673","title":"Do Androids Dream of Breaking the Game? Systematically Auditing AI Agent Benchmarks with BenchJack","created":"2026-05-12","cited_by_count":14,"area":null},{"id":"2509.21361","title":"Context Is What You Need: The Maximum Effective Context Window for Real World Limits of LLMs","created":"2025-09-21","cited_by_count":12,"area":null},{"id":"2509.21882","title":"Position: The Hidden Costs and Measurement Gaps of Reinforcement Learning with Verifiable Rewards","created":"2025-09-26","cited_by_count":12,"area":null},{"id":"2512.15712","title":"Predictive Concept Decoders: Training Scalable End-to-End Interpretability Assistants","created":"2025-12-17","cited_by_count":12,"area":null},{"id":"2506.20702","title":"The Singapore Consensus on Global AI Safety Research Priorities","created":"2025-06-25","cited_by_count":10,"area":null},{"id":"2507.15886","title":"Combining Cost-Constrained Runtime Monitors for AI Safety","created":"2025-07-19","cited_by_count":10,"area":null},{"id":"2601.10242","title":"Loop as a Bridge: Can Looped Transformers Truly Link Representation Space and Natural Language Outputs?","created":"2026-01-15","cited_by_count":8,"area":null},{"id":"2510.03999","title":"LH-Deception: Simulating and Understanding LLM Deceptive Behaviors in Long-Horizon Interactions","created":"2025-10-05","cited_by_count":7,"area":null},{"id":"2603.10011","title":"Gemma Needs Help: Investigating and Mitigating Emotional Instability in LLMs","created":"2026-02-17","cited_by_count":7,"area":null},{"id":"2508.16599","title":"Humans Perceive Wrong Narratives from AI Reasoning Texts","created":"2025-08-09","cited_by_count":6,"area":null},{"id":"2601.13717","title":"Simulated Ignorance Fails: A Systematic Study of LLM Behaviors on Forecasting Problems Before Model Knowledge Cutoff","created":"2026-01-20","cited_by_count":6,"area":null},{"id":"2505.21537","title":"OpenReview Should be Protected and Leveraged as a Community Asset for Research in the Era of Large Language Models","created":"2025-05-24","cited_by_count":5,"area":null},{"id":"2505.24040","title":"MedPAIR: Measuring Physicians and AI Relevance Alignment in Medical Question Answering","created":"2025-05-29","cited_by_count":5,"area":null},{"id":"2510.09671","title":"Table Question Answering in the Era of Large Language Models: A Comprehensive Survey of Tasks, Methods, and Evaluation","created":"2025-10-08","cited_by_count":5,"area":null},{"id":"2511.11500","title":"Honesty over Accuracy: Trustworthy Language Models through Reinforced Hesitation","created":"2025-11-14","cited_by_count":5,"area":null},{"id":"2601.19768","title":"GAVEL: Towards Rule-Based Safety Through Activation Monitoring","created":"2026-01-27","cited_by_count":5,"area":null},{"id":"2605.01048","title":"Compared to What? Baselines and Metrics for Counterfactual Prompting","created":"2026-05-01","cited_by_count":5,"area":null},{"id":"2608.23642","title":"AI Agents Push Humans Out of the Loop","created":"2026-08-24","cited_by_count":5,"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":"2606.32038","title":"Introspective Coupling: Self-Explanation Training Tracks Behavioral Change Despite Fixed Supervision","created":"2026-06-30","cited_by_count":4,"area":null},{"id":"2506.16975","title":"Latent Concept Disentanglement in Transformer-based Language Models","created":"2025-06-20","cited_by_count":3,"area":null},{"id":"2510.02339","title":"Evaluating Uncertainty Quantification Methods in Argumentative Large Language Models","created":"2025-09-26","cited_by_count":3,"area":null},{"id":"2512.00742","title":"On the Regulatory Potential of User Interfaces for AI Agent Governance","created":"2025-11-30","cited_by_count":3,"area":null},{"id":"2512.02299","title":"HealthContradict: Evaluating Biomedical Knowledge Conflicts in Language Models","created":"2025-12-02","cited_by_count":3,"area":null},{"id":"2602.05532","title":"Split Personality Training: Revealing Latent Knowledge Through Alternate Personalities","created":"2026-02-05","cited_by_count":3,"area":null},{"id":"2602.10324","title":"Discovering Differences in Strategic Behavior Between Humans and LLMs","created":"2026-02-10","cited_by_count":3,"area":null},{"id":"2603.14643","title":"Argumentation for Explainable and Globally Contestable Decision Support with LLMs","created":"2026-03-15","cited_by_count":3,"area":null},{"id":"2604.27865","title":"KellyBench: A Benchmark for Long-Horizon Sequential Decision Making","created":"2026-04-30","cited_by_count":3,"area":null},{"id":"2605.00226","title":"Why Do LLMs Struggle in Strategic Play? Broken Links Between Observations, Beliefs, and Actions","created":"2026-04-30","cited_by_count":3,"area":null},{"id":"2605.23055","title":"Decomposing and Measuring Evaluation Awareness","created":"2026-05-21","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":"2607.14345","title":"Value Leakage: An LLM's Answers Are Silently Shaped by Its Own Values","created":"2026-07-15","cited_by_count":3,"area":null},{"id":"2607.26191","title":"Position: Evaluation Scores Are Perishable Knowledge Claims","created":"2026-07-28","cited_by_count":3,"area":null},{"id":"2510.16815","title":"Knowing the Facts but Choosing the Shortcut: Understanding How Large Language Models Compare Entities","created":"2025-10-19","cited_by_count":2,"area":null},{"id":"2511.09373","title":"Routesplain: Towards Faithful and Intervenable Routing for Software-related Tasks","created":"2025-11-12","cited_by_count":2,"area":null},{"id":"2602.05164","title":"Position: Capability Control Should be a Separate Goal From Alignment","created":"2026-02-05","cited_by_count":2,"area":null},{"id":"2605.20098","title":"Neurosymbolic Learning for Inference-Time Argumentation","created":"2026-05-19","cited_by_count":2,"area":null},{"id":"2505.08739","title":"Probability Consistency in Large Language Models: Theoretical Foundations Meet Empirical Discrepancies","created":"2025-05-13","cited_by_count":1,"area":null},{"id":"2508.18467","title":"The AI in the Mirror: LLM Self-Recognition in an Iterated Public Goods Game","created":"2025-08-25","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":"2602.23546","title":"Humans and LLMs Diverge on Probabilistic Inferences","created":"2026-02-26","cited_by_count":1,"area":null},{"id":"2603.25861","title":"Why Safety Probes Catch Liars But Miss Fanatics","created":"2026-03-26","cited_by_count":1,"area":null},{"id":"2604.11120","title":"Persona Non Grata: Single-Method Safety Evaluation Is Incomplete for Persona-Imbued LLMs","created":"2026-04-13","cited_by_count":1,"area":null},{"id":"2606.23597","title":"Against Proxy Optimization","created":"2026-06-22","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":"2607.05017","title":"Hyperparameter Transfer in Graph Neural Networks","created":"2026-07-06","cited_by_count":1,"area":null},{"id":"2608.30980","title":"Evaluating and Improving LLM Self-Modeling","created":"2026-08-31","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":"2609.25518","title":"Matryoshka attribution: Learning to attribute language model outputs to representations and weights","created":"2026-09-22","cited_by_count":1,"area":null},{"id":"2505.22987","title":"Strategic Reflectivism In Intelligent Systems","created":"2025-05-29","cited_by_count":0,"area":null},{"id":"2511.21931","title":"Does the Model Say What the Data Says? A Simple Heuristic for Model Data Alignment","created":"2025-11-26","cited_by_count":0,"area":null},{"id":"2512.07288","title":"Investigating Training and Generalization in Faithful Self-Explanations of Large Language Models","created":"2025-12-08","cited_by_count":0,"area":null},{"id":"2601.10926","title":"Selecting Language Models for Social Science: Start Small, Start Open, and Validate","created":"2026-01-16","cited_by_count":0,"area":null},{"id":"2602.17676","title":"Epistemic Traps: Rational Misalignment Driven by Model Misspecification","created":"2026-01-27","cited_by_count":0,"area":null},{"id":"2603.17504","title":"Inducing Epistemological Humility in Large Language Models: A Targeted SFT Approach to Reducing Hallucination","created":"2026-03-18","cited_by_count":0,"area":null},{"id":"2603.24037","title":"A$^3$: Towards Advertising Aesthetic Assessment","created":"2026-03-25","cited_by_count":0,"area":null},{"id":"2604.00324","title":"The Persistent Vulnerability of Aligned AI Systems","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2604.24966","title":"Risk Reporting for Developers' Internal AI Model Use","created":"2026-04-27","cited_by_count":0,"area":null},{"id":"2605.01164","title":"LLMs Should Not Yet Be Credited with Decision Explanation","created":"2026-05-01","cited_by_count":0,"area":null},{"id":"2605.09716","title":"Medical Model Synthesis Architectures: A Case Study","created":"2026-05-10","cited_by_count":0,"area":null},{"id":"2605.10601","title":"The Open-Box Fallacy: Why AI Deployment Needs a Calibrated Verification Regime","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.16538","title":"LLMs in Qualitative Research: Opportunities, Limitations, and Practical Considerations","created":"2026-05-15","cited_by_count":0,"area":null},{"id":"2605.23970","title":"Faithful or Fabricated? A Causal Framework for Rationalization Bias in LLM Judges","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2606.08629","title":"Sycophancy Towards Researchers Drives Performative Misalignment","created":"2026-06-07","cited_by_count":0,"area":null},{"id":"2606.10456","title":"The Distributed Detectability Band Against Marginal-Preserving Attacks","created":"2026-06-09","cited_by_count":0,"area":null},{"id":"2606.11016","title":"Superficial Beliefs in LLM Decision-Making","created":"2026-06-09","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":"2606.28863","title":"Defeat Devices in AI Systems","created":"2026-06-27","cited_by_count":0,"area":null},{"id":"2607.16451","title":"Committed Before Reasoning: Behavioral Reproduction and Preliminary Activation-Level Evidence of Answer Pre-Commitment in an Open-Weight LLM","created":"2026-07-17","cited_by_count":0,"area":null},{"id":"2607.21090","title":"Training Large Language Models for Self-Explanation Faithfulness","created":"2026-07-23","cited_by_count":0,"area":null},{"id":"2607.22928","title":"Design Theater: Evaluating the Gap Between User-Facing Design Reasoning and Implementation in Generative UI Tools","created":"2026-07-24","cited_by_count":0,"area":null},{"id":"2608.06041","title":"LangChoiceBench: Measuring and Explaining Programming-Language Choice in LLMs","created":"2026-08-06","cited_by_count":0,"area":null},{"id":"2608.06578","title":"From Behavior to Mechanism: Tracing Divergent Response Modes in Frontier Language Models","created":"2026-08-06","cited_by_count":0,"area":null},{"id":"2608.14630","title":"Characterizing Rhetorical Misalignment in Decision-Making with Language Models","created":"2026-07-24","cited_by_count":0,"area":null},{"id":"2608.16213","title":"Process-Constituted Intelligence: A Shared Criterion for Humans and Machines","created":"2026-08-17","cited_by_count":0,"area":null},{"id":"2609.00805","title":"Towards a Reliable and Practical Eval Pipeline","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.04343","title":"A Removal Based Approach to Improve LLM Faithfulness at Test-Time","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2609.07353","title":"Human-like moral judgments conceal divergent motive attributions in large language models","created":"2026-09-07","cited_by_count":0,"area":null},{"id":"2609.14724","title":"Bayesian Intelligence from the Outside","created":"2026-09-13","cited_by_count":0,"area":null},{"id":"2609.32670","title":"What Would Falsify It? A Variable Specific Evidence Standard for Mechanistic Claims About Self Explanation","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.36049","title":"Improving scalable oversight with co-trained monitors","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.36079","title":"A Polyphonic Conception of AI Understanding","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.38369","title":"Can an AI Agent Rediscover a Blaschke-Curve Invariant?","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.38851","title":"Where MLLMs Fail and Why: Causal Task Decomposition for Capability Failure Diagnosis","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.00074","title":"K-Dense BYOK: An Open-Source AI Research Assistant That Runs Locally and Keeps a Hash-Chained Lab Notebook","created":"2026-09-04","cited_by_count":0,"area":null},{"id":"2610.07175","title":"CALR: Continuous Anchored Latent Reasoning via Render-of-Thought Compression","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.13999","title":"SemTree: Judge-Aware Semantic Decision Trees for Inspectable and Repairable Rule Decisions","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2610.17804","title":"Learning from fracture: Teaching language models to design through physical experience","created":"2026-10-13","cited_by_count":0,"area":null},{"id":"2610.19948","title":"When Protection Overrides Consequences: Understanding Protection Mode in Large Language Model Decision-Making","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}