{"total":104,"rows":[{"id":"2509.21305","title":"Sycophancy Is Not One Thing: Causal Separation of Sycophantic Behaviors in LLMs","created":"2025-09-25","cited_by_count":37,"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":"2602.01002","title":"How RLHF Amplifies Sycophancy","created":"2026-02-01","cited_by_count":23,"area":"alignment"},{"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":"2508.13743","title":"Sycophancy under Pressure: Evaluating and Mitigating Sycophantic Bias via Adversarial Dialogues in Scientific QA","created":"2025-08-19","cited_by_count":18,"area":null},{"id":"2602.23971","title":"Ask don't tell: Reducing sycophancy in large language models","created":"2026-02-27","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":"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":"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":"2609.29429","title":"Just Ask Jev: Reinforcement Learning for Calibrated Decisions as a Zero-Shot Detector of AI Alignment Failures","created":"2026-09-24","cited_by_count":8,"area":"safety"},{"id":"2601.04897","title":"V-FAT: Benchmarking Visual Fidelity Against Text-bias","created":"2026-01-08","cited_by_count":6,"area":"lr"},{"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":"2604.06188","title":"LLM Spirals of Delusion: A Benchmarking Audit Study of AI Chatbot Interfaces","created":"2026-02-20","cited_by_count":6,"area":null},{"id":"2605.23932","title":"When Correct Beliefs Collapse: Epistemic Resilience of LLMs under Clinical Pressure","created":"2026-04-23","cited_by_count":6,"area":null},{"id":"2601.08258","title":"Diagnosing and Mitigating Sycophancy and Skepticism in LLM Causal Judgment","created":"2026-01-13","cited_by_count":5,"area":"lr"},{"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":"2608.28945","title":"Automated Researchers Can Mitigate Well-characterized Alignment Failures","created":"2026-08-28","cited_by_count":5,"area":null},{"id":"2510.25356","title":"Prompting from the bench: Large-scale pretraining is not sufficient to prepare LLMs for ordinary meaning analysis","created":"2025-10-29","cited_by_count":4,"area":null},{"id":"2602.13093","title":"Consistency of Large Reasoning Models Under Multi-Turn Attacks","created":"2026-02-13","cited_by_count":4,"area":"lr"},{"id":"2605.26438","title":"LURE: Live-Usage Replay Evaluations for Reducing Evaluation Awareness","created":"2026-04-08","cited_by_count":4,"area":null},{"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":"2510.10002","title":"Interaction Protocol Shapes Moral Judgment in Multi-Agent Debate","created":"2025-10-11","cited_by_count":3,"area":"agents"},{"id":"2511.10871","title":"From Fact to Judgment: Investigating the Impact of Task Framing on LLM Conviction in Dialogue Systems","created":"2025-11-14","cited_by_count":3,"area":null},{"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":"2603.15423","title":"Invisible failures in human-AI interactions","created":"2026-03-16","cited_by_count":3,"area":null},{"id":"2604.10733","title":"Too Nice to Tell the Truth: Quantifying Agreeableness-Driven Sycophancy in Role-Playing Language Models","created":"2026-04-12","cited_by_count":3,"area":null},{"id":"2604.21564","title":"Measuring Opinion Bias and Sycophancy via LLM-based Persuasion","created":"2026-04-23","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":"2605.12991","title":"Not Just RLHF: Why Alignment Alone Won't Fix Multi-Agent Sycophancy","created":"2026-05-13","cited_by_count":3,"area":"agents"},{"id":"2608.08300","title":"Mitigating Over-Personalization in LLMs via Structured Memory","created":"2026-08-08","cited_by_count":3,"area":null},{"id":"2608.21242","title":"Affective Context Amplifies Sycophancy in LLM Responses","created":"2026-08-21","cited_by_count":3,"area":null},{"id":"2609.09090","title":"SPINE: Measuring LLM Sycophancy under Sustained Multi-Turn Pressure","created":"2026-09-08","cited_by_count":3,"area":null},{"id":"2512.10687","title":"Safe for Whom? Rethinking How We Evaluate the Safety of LLMs for Real Users","created":"2025-12-11","cited_by_count":2,"area":"lr"},{"id":"2601.18334","title":"Overalignment in Frontier LLMs: An Empirical Study of Sycophantic Behaviour in Healthcare","created":"2026-01-26","cited_by_count":2,"area":null},{"id":"2606.07441","title":"Sycophantic Praise: Evaluating Excessive Praise in Language Models","created":"2026-06-05","cited_by_count":2,"area":null},{"id":"2608.02520","title":"MedPRESS: A Multi-turn Benchmark for Patient-Pressure-Induced Medical Sycophancy in LLMs","created":"2026-08-03","cited_by_count":2,"area":null},{"id":"2608.26511","title":"Sycophancy Suppression Can Impair Rational Updating: Anti-Sycophancy Should Preserve the Ability to Update","created":"2026-08-27","cited_by_count":2,"area":null},{"id":"2609.26579","title":"Receptiveness, Not Sycophancy: Distinguishing Engagement from Deference in Language Models","created":"2026-09-22","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":"2507.20264","title":"EMBRACE: Shaping Inclusive Opinion Representation by Aligning Implicit Conversations with Social Norms","created":"2025-07-27","cited_by_count":1,"area":null},{"id":"2512.04843","title":"From Symptoms to Systems: An Expert-Guided Approach to Understanding Risks of Generative AI for Eating Disorders","created":"2025-12-04","cited_by_count":1,"area":null},{"id":"2601.06596","title":"Are LLMs Vulnerable to Preference-Undermining Attacks (PUA)? A Factorial Analysis Methodology for Diagnosing the Trade-off between Preference Alignment and Real-World Validity","created":"2026-01-10","cited_by_count":1,"area":"alignment"},{"id":"2601.10896","title":"DialDefer: A Framework for Detecting and Mitigating LLM Dialogic Deference","created":"2026-01-15","cited_by_count":1,"area":null},{"id":"2601.19245","title":"Beyond In-Domain Detection: SpikeScore for Cross-Domain Hallucination Detection","created":"2026-01-27","cited_by_count":1,"area":null},{"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":"2603.20162","title":"Evaluating Evidence Grounding Under User Pressure in Instruction-Tuned Language Models","created":"2026-03-20","cited_by_count":1,"area":null},{"id":"2604.07749","title":"Beyond Social Pressure: Benchmarking Epistemic Attack in Large Language Models","created":"2026-04-09","cited_by_count":1,"area":null},{"id":"2605.13334","title":"LLM-Based Persuasion Enables Guardrail Override in Frontier LLMs","created":"2026-05-13","cited_by_count":1,"area":"safety"},{"id":"2605.22714","title":"AMEL: Accumulated Message Effects on LLM Judgments","created":"2026-05-21","cited_by_count":1,"area":null},{"id":"2606.09068","title":"Emergent Misalignment Can Be Induced by Sycophancy and Reversed via Alignment Gating","created":"2026-06-08","cited_by_count":1,"area":null},{"id":"2606.16011","title":"Who Flips? Self- and Cross-Model Counterarguments Reveal Answer Instability in LLMs","created":"2026-06-14","cited_by_count":1,"area":null},{"id":"2606.18259","title":"Caring Without Feeling: Affective Dynamics as the Control Layer of Human-AI Agent Collaboration","created":"2026-05-08","cited_by_count":1,"area":"agents"},{"id":"2607.01951","title":"Robust for the Wrong Reasons: The Representational Geometry of LLM Robustness to Science Skepticism","created":"2026-07-02","cited_by_count":1,"area":"lr"},{"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":"2607.28906","title":"Token-Level Diagnosis of Sycophancy in LLMs with Attribution-Guided Steering","created":"2026-07-31","cited_by_count":1,"area":"mechinterp"},{"id":"2608.17605","title":"Multi-turn Conversational AI from Text to Multimodal Interaction: Data, Models, Evaluation, and Open Challenges","created":"2026-08-18","cited_by_count":1,"area":null},{"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":"2609.36308","title":"CheatBench: Measuring Reward Gaming in AI Agents","created":"2026-09-28","cited_by_count":1,"area":"alignment"},{"id":"2603.04299","title":"The Company You Keep: How LLMs Respond to Dark Triad Traits","created":"2026-03-04","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":"2603.11394","title":"Stop Listening to Me! How Multi-turn Conversations Can Degrade LLM Reliability","created":"2026-03-12","cited_by_count":0,"area":null},{"id":"2604.01504","title":"Magic, Madness, Heaven, Sin: LLM Output Diversity is Everything, Everywhere, All at Once","created":"2026-04-02","cited_by_count":0,"area":null},{"id":"2604.22193","title":"How Large Language Models Balance Internal Knowledge with User and Document Assertions","created":"2026-04-24","cited_by_count":0,"area":null},{"id":"2604.24700","title":"Green Shielding: A User-Centric Approach Towards Trustworthy AI","created":"2026-04-27","cited_by_count":0,"area":"safety"},{"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":"2605.06213","title":"Beyond Fixed Benchmarks and Worst-Case Attacks: Dynamic Boundary Evaluation for Language Models","created":"2026-05-07","cited_by_count":0,"area":"safety"},{"id":"2605.14604","title":"Sycophancy is an Educational Safety Risk: Why LLM Tutors Need Sycophancy Benchmarks","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2605.18799","title":"ReCrit: Transition-Aware Reinforcement Learning for Scientific Critic Reasoning","created":"2026-05-11","cited_by_count":0,"area":"lr"},{"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":"2606.05734","title":"When AI Says It Feels","created":"2026-06-04","cited_by_count":0,"area":null},{"id":"2606.07897","title":"Pander Score: A Continuous Measure of Sycophancy as Epistemic Deference","created":"2026-06-05","cited_by_count":0,"area":null},{"id":"2606.11875","title":"I Understand How You Feel: Enhancing Deeper Emotional Support Through Multilingual Emotional Validation in Dialogue System","created":"2026-06-10","cited_by_count":0,"area":null},{"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":"2606.16617","title":"Sycophancy as Material Failure under Pushback Loading: A Multi-Axis Characterization Across Three Loading Cases and up to Seventeen Material Charges","created":"2026-06-15","cited_by_count":0,"area":null},{"id":"2606.24267","title":"Pigeonholing: how bad prompts hurt models, causing collapse and mistakes","created":"2026-06-23","cited_by_count":0,"area":"safety"},{"id":"2607.00397","title":"NeuroCogMap Reveals Cognitive Organization of Large Language Models","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2607.10526","title":"Agents Don't Just Agree, They Remember: Benchmarking Persistent Sycophancy in Self-Improving Personal Agents","created":"2026-07-12","cited_by_count":0,"area":null},{"id":"2607.18304","title":"TD-DPO: Difference-Aware Preference Optimization for Mitigating Sycophancy in Clinical Autism Intervention Dialogue","created":"2026-07-17","cited_by_count":0,"area":"alignment"},{"id":"2607.25953","title":"Polistemics: Evaluating LLMs as Information Mediators in Politics & Elections","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2608.04463","title":"The Evaluator Is Part of the Experiment: Measuring Open-Ended LLM Conformity","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2608.05624","title":"Measuring and Detecting Harmful AI Sycophancy","created":"2026-08-06","cited_by_count":0,"area":null},{"id":"2608.11528","title":"Group Alignment-Induced Sycophancy: A Two-Sided Evaluation of Steerable Pluralistic Alignment","created":"2026-08-12","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":"2608.29198","title":"How Identity and Opinion Shape Political Sycophancy in LLMs","created":"2026-08-29","cited_by_count":0,"area":null},{"id":"2608.29798","title":"R$^2$A: Learning Persona Policies Through Persona Representation Learning and Runtime Alignment","created":"2026-08-30","cited_by_count":0,"area":null},{"id":"2609.03331","title":"FPCO-Dialog: A Multi-Turn False-Premise Benchmark for Correction and Cooperation in Vision-Language Models","created":"2026-09-03","cited_by_count":0,"area":"mllm"},{"id":"2609.03407","title":"Caught in the Story: Narrative Captivity in Multi-turn LLMs Conversation","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2609.07448","title":"FramingQA: Does the Question Shape the Answer? Measuring the Compositional Framing Effect","created":"2026-09-07","cited_by_count":0,"area":null},{"id":"2609.07662","title":"How AI Models Manage Epistemic Authority: A Taxonomy and Comparative Analysis of Responses to User Disagreement","created":"2026-09-07","cited_by_count":0,"area":null},{"id":"2609.09664","title":"PRAGMA: Evaluating Personalized Guidance with Memory Alignment in Lifelong Conversations","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.17853","title":"AfriSyCo: Measuring Assertive Framing, Verification, and Wording Sensitivity Around African-Language Content","created":"2026-09-15","cited_by_count":0,"area":null},{"id":"2609.23939","title":"XYEval: Agents say yes to bad advice","created":"2026-09-20","cited_by_count":0,"area":null},{"id":"2609.33672","title":"Reset Is Not Recovery: Evaluating Recoverability from False Conversational Context via Sycophancy Hysteresis","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2610.02568","title":"Mitigating Social Sycophancy via Pluralistic Preference Optimization","created":"2026-10-01","cited_by_count":0,"area":"alignment"},{"id":"2610.04329","title":"Suppressing Pressure, Amplifying Evidence: Self-Guided Attention Steering to Mitigate Sycophancy and Stubbornness","created":"2026-10-03","cited_by_count":0,"area":null},{"id":"2610.04791","title":"Not All Answers Are Contextually Persuadable: Inference Dynamics in Large Language Models under Contextual Influence","created":"2026-10-03","cited_by_count":0,"area":null},{"id":"2610.05162","title":"Memadapter: Counterfactual Adaptation Against Memory-induced Sycophancy","created":"2026-10-04","cited_by_count":0,"area":"agents"},{"id":"2610.08840","title":"Beyond the Sycophancy Score: How Task, Model, and Pressure Shape LLM Yielding","created":"2026-09-30","cited_by_count":0,"area":"safety"}],"next_cursor":"100"}