{"total":108,"rows":[{"id":"2505.13995","title":"ELEPHANT: Measuring and understanding social sycophancy in LLMs","created":"2025-05-20","cited_by_count":129,"area":null},{"id":"2509.23055","title":"Peacemaker or Troublemaker: How Sycophancy Shapes Multi-Agent Debate","created":"2025-09-27","cited_by_count":29,"area":"agents"},{"id":"2506.07180","title":"Flattery in Motion: Benchmarking and Analyzing Sycophancy in Video-LLMs","created":"2025-06-08","cited_by_count":21,"area":"lr"},{"id":"2510.07517","title":"When Identity Skews Debate: Anonymization for Bias-Reduced Multi-Agent Reasoning","created":"2025-10-08","cited_by_count":21,"area":"lr"},{"id":"2602.19141","title":"Sycophantic Chatbots Cause Delusional Spiraling, Even in Ideal Bayesians","created":"2026-02-22","cited_by_count":21,"area":null},{"id":"2508.05687","title":"Risk Analysis Techniques for Governed LLM-based Multi-Agent Systems","created":"2025-08-06","cited_by_count":18,"area":"agents"},{"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":"2509.18052","title":"The PIMMUR Principles: Ensuring Validity in Collective Behavior of LLM Societies","created":"2025-09-22","cited_by_count":14,"area":null},{"id":"2511.06419","title":"MONICA: Real-Time Monitoring and Calibration of Chain-of-Thought Sycophancy in Large Reasoning Models","created":"2025-11-09","cited_by_count":12,"area":"lr"},{"id":"2602.14270","title":"A Rational Analysis of the Effects of Sycophantic AI","created":"2026-02-15","cited_by_count":12,"area":null},{"id":"2603.23848","title":"BeliefShift: Benchmarking Temporal Belief Consistency and Opinion Drift in LLM Agents","created":"2026-03-25","cited_by_count":12,"area":"agents"},{"id":"2607.01071","title":"MemSyco-Bench: Benchmarking Sycophancy in Agent Memory","created":"2026-07-01","cited_by_count":12,"area":"agents"},{"id":"2509.10970","title":"The Psychogenic Machine: Simulating AI Psychosis, Delusion Reinforcement and Harm Enablement in Large Language Models","created":"2025-09-13","cited_by_count":11,"area":null},{"id":"2509.20146","title":"EchoBench: Benchmarking Sycophancy in Medical Large Vision-Language Models","created":"2025-09-24","cited_by_count":9,"area":"mllm"},{"id":"2508.09998","title":"INTIMA: A Benchmark for Human-AI Companionship Behavior","created":"2025-08-04","cited_by_count":8,"area":null},{"id":"2603.05651","title":"The Fragility Of Moral Judgment In Large Language Models","created":"2026-03-05","cited_by_count":8,"area":null},{"id":"2604.02423","title":"SWAY: A Counterfactual Computational Linguistic Approach to Measuring and Mitigating Sycophancy","created":"2026-04-02","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":"2601.21276","title":"More Code, Less Reuse: Investigating Code Quality and Reviewer Sentiment towards AI-generated Pull Requests","created":"2026-01-29","cited_by_count":7,"area":"agents"},{"id":"2508.16213","title":"MedOmni-45{\\deg}: A Safety-Performance Benchmark for Reasoning-Oriented LLMs in Medicine","created":"2025-08-22","cited_by_count":6,"area":"lr"},{"id":"2509.19163","title":"Measuring AI \"Slop\" in Text","created":"2025-09-23","cited_by_count":6,"area":null},{"id":"2510.01395","title":"Sycophantic AI Decreases Prosocial Intentions and Promotes Dependence","created":"2025-10-01","cited_by_count":6,"area":null},{"id":"2511.14972","title":"Harmful Traits of AI Companions","created":"2025-11-18","cited_by_count":6,"area":null},{"id":"2604.02668","title":"Too Polite to Disagree: Understanding Sycophancy Propagation in Multi-Agent Systems","created":"2026-04-03","cited_by_count":6,"area":"agents"},{"id":"2607.07003","title":"Dissociating the Internal Representations of Sycophancy in LLMs","created":"2026-07-08","cited_by_count":6,"area":"mechinterp"},{"id":"2601.16529","title":"SycoEval-EM: Sycophancy Evaluation of Large Language Models in Simulated Clinical Encounters for Emergency Care","created":"2026-01-23","cited_by_count":5,"area":null},{"id":"2603.00024","title":"Personalization Increases Affective Alignment but Has Role-Dependent Effects on Epistemic Independence in LLMs","created":"2026-02-03","cited_by_count":5,"area":null},{"id":"2605.24279","title":"ContextEcho: A Benchmark for Persona Drift in Long Agentic-Coding Sessions","created":"2026-05-22","cited_by_count":5,"area":"agents"},{"id":"2512.19350","title":"PENDULUM: A Benchmark for Assessing Sycophancy in Multimodal Large Language Models","created":"2025-12-22","cited_by_count":4,"area":"mllm"},{"id":"2604.05279","title":"Pressure, What Pressure? Sycophancy Disentanglement in Language Models via Reward Decomposition","created":"2026-04-07","cited_by_count":4,"area":"alignment"},{"id":"2605.09278","title":"EquiMem: Calibrating Shared Memory in Multi-Agent Debate via Game-Theoretic Equilibrium","created":"2026-05-10","cited_by_count":4,"area":"agents"},{"id":"2606.06306","title":"Decomposing Factual Sycophancy in Language Models: How Size and Instruction Tuning Shape Robustness","created":"2026-06-04","cited_by_count":4,"area":null},{"id":"2606.10949","title":"Recalling Too Well: Sycophancy Evaluation and Mitigation in Memory-Augmented Models","created":"2026-06-09","cited_by_count":4,"area":null},{"id":"2505.17760","title":"But what is your honest answer? Aiding LLM-judges with honest alternatives using steering vectors","created":"2025-05-23","cited_by_count":3,"area":"mechinterp"},{"id":"2508.15815","title":"User-Assistant Bias in LLMs","created":"2025-08-16","cited_by_count":3,"area":null},{"id":"2510.16727","title":"Beacon: Single-Turn Diagnosis and Mitigation of Latent Sycophancy in Large Language Models","created":"2025-10-19","cited_by_count":3,"area":null},{"id":"2602.19948","title":"Assessing Risks of Large Language Models in Mental Health Support: A Framework for Automated Clinical AI Red Teaming","created":"2026-02-23","cited_by_count":3,"area":"safety"},{"id":"2603.03291","title":"One Bias After Another: Mechanistic Reward Shaping and Persistent Biases in Language Reward Models","created":"2026-02-06","cited_by_count":3,"area":"alignment"},{"id":"2603.18740","title":"Measuring and Exploiting Contextual Bias in LLM-Assisted Security Code Review","created":"2026-03-19","cited_by_count":3,"area":null},{"id":"2604.24668","title":"The Price of Agreement: Measuring LLM Sycophancy in Agentic Financial Applications","created":"2026-04-27","cited_by_count":3,"area":"agents"},{"id":"2506.10157","title":"One Patient, Many Contexts: Scaling Medical AI with Contextual Intelligence","created":"2025-06-11","cited_by_count":2,"area":"mllm"},{"id":"2506.19492","title":"Is Long-to-Short a Free Lunch? Investigating Inconsistency and Reasoning Efficiency in LRMs","created":"2025-06-24","cited_by_count":2,"area":"lr"},{"id":"2510.17256","title":"Explainability of Large Language Models: Opportunities and Challenges toward Generating Trustworthy Explanations","created":"2025-10-20","cited_by_count":2,"area":"mechinterp"},{"id":"2510.21180","title":"Social Simulations with Large Language Model Risk Utopian Illusion","created":"2025-10-24","cited_by_count":2,"area":null},{"id":"2512.00412","title":"Red Teaming Large Reasoning Models","created":"2025-11-29","cited_by_count":2,"area":"lr"},{"id":"2601.08768","title":"AI as Entertainment","created":"2026-01-13","cited_by_count":2,"area":null},{"id":"2602.16154","title":"Balancing Faithfulness and Performance in Reasoning via Multi-Listener Soft Execution","created":"2026-02-18","cited_by_count":2,"area":"lr"},{"id":"2603.22623","title":"To Agree or To Be Right? The Grounding-Sycophancy Tradeoff in Medical Vision-Language Models","created":"2026-03-23","cited_by_count":2,"area":"mllm"},{"id":"2604.00478","title":"The Silicon Mirror: Dynamic Behavioral Gating for Anti-Sycophancy in LLM Agents","created":"2026-04-01","cited_by_count":2,"area":"agents"},{"id":"2604.22749","title":"Representational Harms in LLM-Generated Narratives Against Global Majority Nationalities","created":"2026-04-24","cited_by_count":2,"area":null},{"id":"2604.23593","title":"When AI reviews science: Can we trust the referee?","created":"2026-04-26","cited_by_count":2,"area":null},{"id":"2605.09314","title":"How LLMs Are Persuaded: A Few Attention Heads, Rerouted","created":"2026-05-10","cited_by_count":2,"area":null},{"id":"2607.13477","title":"Auditing Protocol-Level Shortcuts in Large Audio Language Model Judges for Speech Evaluation","created":"2026-07-15","cited_by_count":2,"area":null},{"id":"2609.37616","title":"Authority Bias in Language Models: Source Deference and User Agreement Are Not Interchangeable","created":"2026-09-29","cited_by_count":2,"area":null},{"id":"2512.00349","title":"Debate with Images: Detecting Deceptive Behaviors in Multimodal Large Language Models","created":"2025-11-29","cited_by_count":1,"area":"mllm"},{"id":"2601.01490","title":"Distortion Instead of Hallucination: The Effect of Reasoning Under Strict Constraints","created":"2026-01-04","cited_by_count":1,"area":"lr"},{"id":"2602.00851","title":"Persuasion Propagation: Does Persuasion Change AI Agent Behavior?","created":"2026-01-31","cited_by_count":1,"area":null},{"id":"2602.11244","title":"Stress Tests REVEAL Fragile Temporal and Visual Grounding in Video-Language Models","created":"2026-02-11","cited_by_count":1,"area":null},{"id":"2602.14518","title":"Diagnosing Knowledge Conflict in Multimodal Long-Chain Reasoning","created":"2026-02-16","cited_by_count":1,"area":"lr"},{"id":"2602.24080","title":"Human or Machine? A Preliminary Turing Test for Speech-to-Speech Interaction","created":"2026-02-27","cited_by_count":1,"area":null},{"id":"2603.03970","title":"Generative AI for Managerial Decision-Making under Ambiguity and Sycophancy","created":"2026-03-04","cited_by_count":1,"area":null},{"id":"2604.11477","title":"OOM-RL: Out-of-Money Reinforcement Learning Market-Driven Alignment for LLM-Based Multi-Agent Systems","created":"2026-04-13","cited_by_count":1,"area":"agents"},{"id":"2604.22119","title":"Emergent Strategic Reasoning Risks in AI: A Taxonomy-Driven Evaluation Framework","created":"2026-04-23","cited_by_count":1,"area":"lr"},{"id":"2605.07462","title":"The Moltbook Files: A Harmless Slopocalypse or Humanity's Last Experiment","created":"2026-05-08","cited_by_count":1,"area":null},{"id":"2606.13220","title":"LLM-as-an-Investigator: Evidence-First Reasoning for Robust Interactive Problem Diagnosis","created":"2026-06-11","cited_by_count":1,"area":"lr"},{"id":"2606.13757","title":"SEVRA-BENCH: Social Engineering of Vulnerabilities in Review Agents","created":"2026-06-11","cited_by_count":1,"area":"agents"},{"id":"2607.23976","title":"This Is a Good Paper, Right? How Tag Questions Affect Sycophancy Across 106 Language Models","created":"2026-07-27","cited_by_count":1,"area":null},{"id":"2609.17496","title":"Verifiable Social Reasoning for LLM Assistants","created":"2026-09-15","cited_by_count":1,"area":"lr"},{"id":"2609.18998","title":"One Axis, No Brake: Self-Knowledge Limits the Filtering of Harmful Peer Conformity in LLMs","created":"2026-07-17","cited_by_count":1,"area":"agents"},{"id":"2609.32867","title":"Are You Sure You're Sure? Two Confounds in a Sycophancy Benchmark","created":"2026-09-26","cited_by_count":1,"area":null},{"id":"2506.11110","title":"AssertBench: A Benchmark for Evaluating Self-Assertion in Large Language Models","created":"2025-06-08","cited_by_count":0,"area":null},{"id":"2601.01532","title":"Aletheia: Quantifying Cognitive Conviction in Reasoning Models via Regularized Inverse Confusion Matrix","created":"2026-01-04","cited_by_count":0,"area":"lr"},{"id":"2601.03285","title":"Feedback Indices to Evaluate LLM Responses to Rebuttals for Multiple Choice Type Questions","created":"2026-01-02","cited_by_count":0,"area":null},{"id":"2603.08412","title":"Aligning to Illusions: Choice Blindness in Human and AI Feedback","created":"2026-03-09","cited_by_count":0,"area":"alignment"},{"id":"2603.13244","title":"Agentic AI, Retrieval-Augmented Generation, and the Institutional Turn: Legal Architectures and Financial Governance in the Age of Distributional AGI","created":"2026-02-20","cited_by_count":0,"area":"agents"},{"id":"2603.13378","title":"Do Large Language Models Get Caught in Hofstadter-Mobius Loops?","created":"2026-03-10","cited_by_count":0,"area":null},{"id":"2603.13791","title":"DeceptGuard :A Constitutional Oversight Framework For Detecting Deception in LLM Agents","created":"2026-03-14","cited_by_count":0,"area":"agents"},{"id":"2604.16009","title":"MEDLEY-BENCH: Benchmarking Behavioural Metacognition and Belief Revision Under Social Pressure in Large Language Models","created":"2026-04-17","cited_by_count":0,"area":null},{"id":"2604.19139","title":"The Rise of Verbal Tics in Large Language Models: A Systematic Analysis Across Frontier Models","created":"2026-04-21","cited_by_count":0,"area":"alignment"},{"id":"2604.24700","title":"Green Shielding: A User-Centric Approach Towards Trustworthy AI","created":"2026-04-27","cited_by_count":0,"area":"safety"},{"id":"2604.26233","title":"Assessing and Explaining the Persuadability of Large Language Models as Legal Decision Tools","created":"2026-04-29","cited_by_count":0,"area":null},{"id":"2605.05403","title":"When Helpfulness Becomes Sycophancy: Sycophancy is a Boundary Failure Between Social Alignment and Epistemic Integrity in Large Language Models","created":"2026-05-06","cited_by_count":0,"area":null},{"id":"2605.10440","title":"TourMart: A Parametric Audit Instrument for Commission Steering in LLM Travel Agents","created":"2026-05-11","cited_by_count":0,"area":"agents"},{"id":"2605.14544","title":"Complacent, Not Sycophantic: Reframing Large Language Models and Designing AI Literacy for Complacent Machines","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2606.05183","title":"The Granularity Gap: A Multi-Dimensional Cross-Generational Audit of Sycophancy in Gemini Models","created":"2026-04-19","cited_by_count":0,"area":"safety"},{"id":"2606.12731","title":"Normative Robustness as a Frontier for Non-Verifiable Reasoning in LLMs","created":"2026-06-10","cited_by_count":0,"area":"lr"},{"id":"2606.12923","title":"Order Is Not Control: Driven-Dissipative Response Laws Across Artificial and Biological Systems","created":"2026-06-11","cited_by_count":0,"area":null},{"id":"2606.30587","title":"Words Speak Louder Than Code: Investigating Cognitive Heuristics in LLM-Based Code Vulnerability Detection","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2606.31187","title":"Learning to Deny: Action Denial in Multimodal Large Language Models","created":"2026-06-30","cited_by_count":0,"area":"mllm"},{"id":"2607.07766","title":"Alignment Plausibility: A New Standard for Assuring AI in Healthcare","created":"2026-07-08","cited_by_count":0,"area":null},{"id":"2608.06115","title":"Mind the Gaps: Mixture-of-Minds for Human Simulation","created":"2026-08-06","cited_by_count":0,"area":null},{"id":"2608.10030","title":"Causal Behavioral Evaluation of AI Agents at Scale via Automated Behavioral Science","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2608.14631","title":"Accuracy and Reliability of Large Language Models in Cosmetic Chemistry and Skin Health: A Benchmarking Study","created":"2026-07-24","cited_by_count":0,"area":null},{"id":"2608.16650","title":"PCA-guided Activation Scaling for Monotonic Bidirectional Control over LLM Sycophancy","created":"2026-08-17","cited_by_count":0,"area":null},{"id":"2608.21325","title":"Move by Move: Measuring and Steering How LLMs Conduct Psychotherapy","created":"2026-08-21","cited_by_count":0,"area":null},{"id":"2608.25267","title":"Mitigating LLM sycophancy with RL-based fine-tuning: Bayesian Truth Serum approach","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2608.27465","title":"The Effect of Emotional Context on Large Language Models' Endorsement of Premature Decisions: Comparing Emotional Vulnerability Across Six Commercial Models","created":"2026-07-15","cited_by_count":0,"area":null},{"id":"2609.08016","title":"What Does Multi-Agent LLM Debate Actually Change? A Layered Analysis of Disagreement and Answer Quality","created":"2026-09-07","cited_by_count":0,"area":"agents"},{"id":"2609.23939","title":"XYEval: Agents say yes to bad advice","created":"2026-09-20","cited_by_count":0,"area":null},{"id":"2609.32081","title":"Toward Interactive Understanding of Code APIs","created":"2026-09-25","cited_by_count":0,"area":"agents"}],"next_cursor":"100"}