{"total":35,"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":"2602.19141","title":"Sycophantic Chatbots Cause Delusional Spiraling, Even in Ideal Bayesians","created":"2026-02-22","cited_by_count":21,"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":"2602.14270","title":"A Rational Analysis of the Effects of Sycophantic AI","created":"2026-02-15","cited_by_count":12,"area":null},{"id":"2604.19117","title":"LLMs Know They're Wrong and Agree Anyway: The Shared Sycophancy-Lying Circuit","created":"2026-04-21","cited_by_count":10,"area":null},{"id":"2607.00415","title":"A Mechanistic View of Authority Hierarchy in LLM Sycophancy","created":"2026-07-01","cited_by_count":9,"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":"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":"2608.21242","title":"Affective Context Amplifies Sycophancy in LLM Responses","created":"2026-08-21","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":"2603.10771","title":"Word Recovery in Large Language Models Enables Character-Level Tokenization Robustness","created":"2026-03-11","cited_by_count":2,"area":null},{"id":"2604.11609","title":"Intersectional Sycophancy: How Perceived User Demographics Shape False Validation in Large Language Models","created":"2026-04-13","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":"2511.07669","title":"Making LLMs Reliable When It Matters Most: A Five-Layer Architecture for High-Stakes Decisions","created":"2025-11-10","cited_by_count":1,"area":null},{"id":"2602.00300","title":"Faithful-Patchscopes: Understanding and Mitigating Model Bias in Hidden Representations Explanation of Large Language Models","created":"2026-01-30","cited_by_count":1,"area":null},{"id":"2602.04918","title":"Simulated Adoption: Decoupling Magnitude and Direction in LLM In-Context Conflict Resolution","created":"2026-02-04","cited_by_count":1,"area":null},{"id":"2606.05403","title":"Trust, but Don't Verify: Epistemic Blind Spots in LLM Source Evaluation","created":"2026-06-03","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":"2606.20718","title":"Escape from Delusional Echo Trap: Symmetry Breaking, Stochastic Dynamics and Mathematical Mitigation Strategies for Algorithmic Sycophancy","created":"2026-06-16","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":"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":"2603.04299","title":"The Company You Keep: How LLMs Respond to Dark Triad Traits","created":"2026-03-04","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":"2605.18781","title":"Can LLMs Emulate Human Belief Dynamics?","created":"2026-05-05","cited_by_count":0,"area":null},{"id":"2607.15957","title":"From Plausible to Actionable: A Position on LLM Self-Explanations","created":"2026-07-17","cited_by_count":0,"area":null},{"id":"2607.18496","title":"Semi-Automated Detection of Gaps in LLM Security Knowledge","created":"2026-07-20","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":"2608.25267","title":"Mitigating LLM sycophancy with RL-based fine-tuning: Bayesian Truth Serum approach","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2609.00753","title":"How Do Language Models Choose Between Context and Memory?","created":"2026-09-01","cited_by_count":0,"area":null},{"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":"2609.17550","title":"No Usable Linear \"Capitulation Direction\" in Two Small LLMs: A Validation Protocol for Activation-Steering Claims, and a Cross-Family Behavioral Study of Sycophancy Under Pushback","created":"2026-07-16","cited_by_count":0,"area":null},{"id":"2609.22224","title":"From Trait Vectors to Circuits: Tracing Refusal and Sycophancy Through Language Models","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.35822","title":"Tracing mechanisms of sycophantic agreement in language models","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2610.07403","title":"Defense-in-Depth for LLMs: Evaluating Memory Gates Against Activation-Induced and Memory-Induced Sycophancy","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.17703","title":"Pushback in a Haystack: Language Models Respond to Factual Errors Ambiguously and Ineffectively","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}