{"total":109,"rows":[{"id":"2401.06373","title":"How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs","created":"2024-01-12","cited_by_count":573,"area":"lr"},{"id":"2403.08319","title":"Knowledge Conflicts for LLMs: A Survey","created":"2024-03-13","cited_by_count":283,"area":null},{"id":"2407.18418","title":"Know Your Limits: A Survey of Abstention in Large Language Models","created":"2024-07-25","cited_by_count":121,"area":null},{"id":"2504.13079","title":"Retrieval-Augmented Generation with Conflicting Evidence","created":"2025-04-17","cited_by_count":63,"area":"rag"},{"id":"2403.04893","title":"A Safe Harbor for AI Evaluation and Red Teaming","created":"2024-03-07","cited_by_count":47,"area":"safety"},{"id":"2412.14959","title":"Understanding the Dark Side of LLMs' Intrinsic Self-Correction","created":"2024-12-19","cited_by_count":42,"area":"lr"},{"id":"2402.10426","title":"DELL: Generating Reactions and Explanations for LLM-Based Misinformation Detection","created":"2024-02-16","cited_by_count":41,"area":null},{"id":"2412.12472","title":"Knowledge Boundary of Large Language Models: A Survey","created":"2024-12-17","cited_by_count":40,"area":null},{"id":"2407.17023","title":"DYNAMICQA: Tracing Internal Knowledge Conflicts in Language Models","created":"2024-07-24","cited_by_count":34,"area":null},{"id":"2502.11903","title":"MMRC: A Large-Scale Benchmark for Understanding Multimodal Large Language Model in Real-World Conversation","created":"2025-02-17","cited_by_count":29,"area":"mllm"},{"id":"2406.18841","title":"Navigating LLM Ethics: Advancements, Challenges, and Future Directions","created":"2024-05-14","cited_by_count":28,"area":null},{"id":"2502.11355","title":"Nuclear Deployed: Analyzing Catastrophic Risks in Decision-making of Autonomous LLM Agents","created":"2025-02-17","cited_by_count":27,"area":"lr"},{"id":"2502.12964","title":"Trust Me, I'm Wrong: LLMs Hallucinate with Certainty Despite Knowing the Answer","created":"2025-02-18","cited_by_count":27,"area":null},{"id":"2503.01829","title":"Persuade Me if You Can: A Framework for Evaluating Persuasion Effectiveness and Susceptibility Among Large Language Models","created":"2025-03-03","cited_by_count":27,"area":null},{"id":"2402.00371","title":"What Does the Bot Say? Opportunities and Risks of Large Language Models in Social Media Bot Detection","created":"2024-02-01","cited_by_count":25,"area":null},{"id":"2405.05378","title":"\"They are uncultured\": Unveiling Covert Harms and Social Threats in LLM Generated Conversations","created":"2024-05-08","cited_by_count":25,"area":null},{"id":"2406.19354","title":"Fundamental Problems With Model Editing: How Should Rational Belief Revision Work in LLMs?","created":"2024-06-27","cited_by_count":24,"area":null},{"id":"2412.03920","title":"A Survey on Large Language Model-Based Social Agents in Game-Theoretic Scenarios","created":"2024-12-05","cited_by_count":23,"area":"agents"},{"id":"2504.10430","title":"LLM Can be a Dangerous Persuader: Empirical Study of Persuasion Safety in Large Language Models","created":"2025-04-14","cited_by_count":23,"area":null},{"id":"2601.16644","title":"Sycophancy Hides Linearly in the Attention Heads","created":"2026-01-23","cited_by_count":23,"area":null},{"id":"2502.11190","title":"ReLearn: Unlearning via Learning for Large Language Models","created":"2025-02-16","cited_by_count":22,"area":"safety"},{"id":"2403.15115","title":"Language Models in Dialogue: Conversational Maxims for Human-AI Interactions","created":"2024-03-22","cited_by_count":21,"area":null},{"id":"2405.06800","title":"LLM-Generated Black-box Explanations Can Be Adversarially Helpful","created":"2024-05-10","cited_by_count":21,"area":null},{"id":"2404.09971","title":"Constructing Benchmarks and Interventions for Combating Hallucinations in LLMs","created":"2024-04-15","cited_by_count":19,"area":null},{"id":"2405.20902","title":"Preemptive Answer \"Attacks\" on Chain-of-Thought Reasoning","created":"2024-05-31","cited_by_count":19,"area":"lr"},{"id":"2410.14596","title":"Teaching Models to Balance Resisting and Accepting Persuasion","created":"2024-10-18","cited_by_count":19,"area":null},{"id":"2601.01685","title":"Lying with Truths: Open-Channel Multi-Agent Collusion for Belief Manipulation via Generative Montage","created":"2026-01-04","cited_by_count":19,"area":"lr"},{"id":"2503.09598","title":"How to Protect Yourself from 5G Radiation? Investigating LLM Responses to Implicit Misinformation","created":"2025-03-12","cited_by_count":18,"area":null},{"id":"2405.16631","title":"Let Silence Speak: Enhancing Fake News Detection with Generated Comments from Large Language Models","created":"2024-05-26","cited_by_count":17,"area":null},{"id":"2502.21017","title":"PersuasiveToM: A Benchmark for Evaluating Machine Theory of Mind in Persuasive Dialogues","created":"2025-02-28","cited_by_count":17,"area":null},{"id":"2410.22071","title":"Distinguishing Ignorance from Error in LLM Hallucinations","created":"2024-10-29","cited_by_count":14,"area":null},{"id":"2504.01205","title":"Epistemic Alignment: A Mediating Framework for User-LLM Knowledge Delivery","created":"2025-04-01","cited_by_count":14,"area":null},{"id":"2503.22353","title":"Firm or Fickle? Evaluating Large Language Models Consistency in Sequential Interactions","created":"2025-03-28","cited_by_count":13,"area":null},{"id":"2505.07775","title":"Must Read: A Comprehensive Survey of Computational Persuasion","created":"2025-05-12","cited_by_count":13,"area":null},{"id":"2508.17450","title":"Persuasion Dynamics in LLMs: Investigating Robustness and Adaptability in Knowledge and Safety with DuET-PD","created":"2025-08-24","cited_by_count":13,"area":null},{"id":"2504.00374","title":"When Persuasion Overrides Truth in Multi-Agent LLM Debates: Introducing a Confidence-Weighted Persuasion Override Rate (CW-POR)","created":"2025-04-01","cited_by_count":12,"area":"agents"},{"id":"2410.09412","title":"FB-Bench: A Fine-Grained Multi-Task Benchmark for Evaluating LLMs' Responsiveness to Human Feedback","created":"2024-10-12","cited_by_count":11,"area":"alignment"},{"id":"2506.11930","title":"Feedback Friction: LLMs Struggle to Fully Incorporate External Feedback","created":"2025-06-13","cited_by_count":11,"area":null},{"id":"2410.06195","title":"EgoSocialArena: Benchmarking the Social Intelligence of Large Language Models from a First-person Perspective","created":"2024-10-08","cited_by_count":10,"area":null},{"id":"2411.11731","title":"Moral Persuasion in Large Language Models: Evaluating Susceptibility and Ethical Alignment","created":"2024-11-18","cited_by_count":10,"area":null},{"id":"2505.24341","title":"Exploring Multimodal Challenges in Toxic Chinese Detection: Taxonomy, Benchmark, and Findings","created":"2025-05-30","cited_by_count":10,"area":null},{"id":"2504.13475","title":"LLM Sensitivity Evaluation Framework for Clinical Diagnosis","created":"2025-04-18","cited_by_count":7,"area":null},{"id":"2504.20084","title":"AI Awareness","created":"2025-04-25","cited_by_count":7,"area":null},{"id":"2506.03332","title":"Helpful Agent Meets Deceptive Judge: Understanding Vulnerabilities in Agentic Workflows","created":"2025-06-03","cited_by_count":7,"area":"agents"},{"id":"2510.14008","title":"Stop Reducing Responsibility in LLM-Powered Multi-Agent Systems to Local Alignment","created":"2025-10-15","cited_by_count":7,"area":"agents"},{"id":"2601.19202","title":"Do Images Speak Louder than Words? Investigating the Effect of Textual Misinformation in VLMs","created":"2026-01-27","cited_by_count":7,"area":"lr"},{"id":"2501.01336","title":"Aligning Large Language Models for Faithful Integrity Against Opposing Argument","created":"2025-01-02","cited_by_count":6,"area":"alignment"},{"id":"2510.24222","title":"HACK: Hallucinations Along Certainty and Knowledge Axes","created":"2025-10-28","cited_by_count":6,"area":null},{"id":"2601.06842","title":"Seeing through the Conflict: Transparent Knowledge Conflict Handling in Retrieval-Augmented Generation","created":"2026-01-11","cited_by_count":6,"area":"rag"},{"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":"2406.17992","title":"Catching Chameleons: Detecting Evolving Disinformation Generated using Large Language Models","created":"2024-06-26","cited_by_count":5,"area":null},{"id":"2410.12600","title":"On the Risk of Evidence Pollution for Malicious Social Text Detection in the Era of LLMs","created":"2024-10-16","cited_by_count":5,"area":null},{"id":"2505.21608","title":"How does Misinformation Affect Large Language Model Behaviors and Preferences?","created":"2025-05-27","cited_by_count":5,"area":null},{"id":"2601.05201","title":"Mechanisms of Prompt-Induced Hallucination in Vision-Language Models","created":"2026-01-08","cited_by_count":5,"area":"mllm"},{"id":"2405.15984","title":"Evaluating and Safeguarding the Adversarial Robustness of Retrieval-Based In-Context Learning","created":"2024-05-24","cited_by_count":4,"area":"rag"},{"id":"2502.20231","title":"AI Will Always Love You: Studying Implicit Biases in Romantic AI Companions","created":"2025-02-27","cited_by_count":4,"area":null},{"id":"2505.17118","title":"After Retrieval, Before Generation: Enhancing the Trustworthiness of Large Language Models in Retrieval-Augmented Generation","created":"2025-05-21","cited_by_count":4,"area":"rag"},{"id":"2506.06800","title":"On the Adaptive Psychological Persuasion of Large Language Models","created":"2025-06-07","cited_by_count":4,"area":null},{"id":"2507.18203","title":"Exploring the Impact of Instruction-Tuning on LLM's Susceptibility to Misinformation","created":"2025-07-24","cited_by_count":4,"area":"safety"},{"id":"2510.11238","title":"Attacks by Content: Automated Fact-checking is an AI Security Issue","created":"2025-10-13","cited_by_count":4,"area":null},{"id":"2412.12632","title":"What External Knowledge is Preferred by LLMs? Characterizing and Exploring Chain of Evidence in Imperfect Context for Multi-Hop QA","created":"2024-12-17","cited_by_count":3,"area":null},{"id":"2502.09532","title":"Mind the Gap! Choice Independence in Using Multilingual LLMs for Persuasive Co-Writing Tasks in Different Languages","created":"2025-02-13","cited_by_count":3,"area":null},{"id":"2506.06020","title":"When to Trust Context: Self-Reflective Debates for Context Reliability","created":"2025-06-06","cited_by_count":3,"area":null},{"id":"2506.07458","title":"KScope: A Framework for Characterizing the Knowledge Status of Language Models","created":"2025-06-09","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":"2601.05478","title":"The Facade of Truth: Uncovering and Mitigating LLM Susceptibility to Deceptive Evidence","created":"2026-01-09","cited_by_count":3,"area":null},{"id":"2601.11886","title":"Faithfulness vs. Safety: Evaluating LLM Behavior Under Counterfactual Medical Evidence","created":"2026-01-17","cited_by_count":3,"area":null},{"id":"2604.08243","title":"Self-Debias: Self-correcting for Debiasing Large Language Models","created":"2026-04-09","cited_by_count":3,"area":"lr"},{"id":"2608.21242","title":"Affective Context Amplifies Sycophancy in LLM Responses","created":"2026-08-21","cited_by_count":3,"area":null},{"id":"2409.20385","title":"Wait, but Tylenol is Acetaminophen... Investigating and Improving Language Models' Ability to Resist Requests for Misinformation","created":"2024-09-30","cited_by_count":2,"area":null},{"id":"2410.23472","title":"Risk Sources and Risk Management Measures in Support of Standards for General-Purpose AI Systems","created":"2024-10-30","cited_by_count":2,"area":null},{"id":"2502.19779","title":"Do Retrieval-Augmented Language Models Adapt to Varying User Needs?","created":"2025-02-27","cited_by_count":2,"area":"rag"},{"id":"2504.02865","title":"The Illusionist's Prompt: Exposing the Factual Vulnerabilities of Large Language Models with Linguistic Nuances","created":"2025-04-01","cited_by_count":2,"area":null},{"id":"2508.05083","title":"MedMKEB: A Comprehensive Knowledge Editing Benchmark for Medical Multimodal Large Language Models","created":"2025-08-07","cited_by_count":2,"area":"mllm"},{"id":"2508.15858","title":"Building and Measuring Trust between Large Language Models","created":"2025-08-20","cited_by_count":2,"area":null},{"id":"2509.12521","title":"Phi: Preference Hijacking in Multi-modal Large Language Models at Inference Time","created":"2025-09-15","cited_by_count":2,"area":"mllm"},{"id":"2510.12993","title":"Tailored untruths: How personalisation challenges LLM safeguards","created":"2025-10-14","cited_by_count":2,"area":"safety"},{"id":"2511.13788","title":"Scaling Patterns in Adversarial Alignment: Evidence from Multi-LLM Jailbreak Experiments","created":"2025-11-16","cited_by_count":2,"area":"safety"},{"id":"2602.00428","title":"When Agents \"Misremember\" Collectively: Exploring the Mandela Effect in LLM-based Multi-Agent Systems","created":"2026-01-31","cited_by_count":2,"area":"agents"},{"id":"2603.15892","title":"Temporal Fact Conflicts in LLMs: Reproducibility Insights from Unifying DYNAMICQA and MULAN","created":"2026-03-16","cited_by_count":2,"area":null},{"id":"2604.05051","title":"This Treatment Works, Right? Evaluating LLM Sensitivity to Patient Question Framing in Medical QA","created":"2026-04-06","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":"2605.30219","title":"When Should Models Change Their Minds? Contextual Belief Management in Large Language Models","created":"2026-05-28","cited_by_count":2,"area":null},{"id":"2606.16710","title":"Misinformation Propagation in Benign Multi-Agent Systems","created":"2026-06-15","cited_by_count":2,"area":"agents"},{"id":"2504.08202","title":"Harnessing the Unseen: The Hidden Influence of Intrinsic Knowledge in Long-Context Language Models","created":"2025-04-11","cited_by_count":1,"area":null},{"id":"2509.15896","title":"The Psychology of Falsehood: A Human-Centric Survey of Misinformation Detection","created":"2025-09-19","cited_by_count":1,"area":null},{"id":"2510.22768","title":"Seeing is Believing? Evaluating Vision-Language Model Susceptibility in Agent-to-Agent Multimodal Persuasion","created":"2025-10-26","cited_by_count":1,"area":"mllm"},{"id":"2510.25732","title":"What the \"Spotless\" Mind Remembers: How Knowledge Entanglement Shapes What Leaks After Unlearning in LLMs","created":"2025-10-29","cited_by_count":1,"area":"safety"},{"id":"2601.13590","title":"Vulnerability of LLMs' Stated Beliefs? LLMs Belief Resistance Check Through Strategic Persuasive Conversation Interventions","created":"2026-01-20","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":"2604.05397","title":"Confidence Should Be Calibrated More Than One Turn Deep","created":"2026-04-07","cited_by_count":1,"area":null},{"id":"2606.14037","title":"Right or Wrong, Models Comply: Directional Blindness in LLM Moral Judgment","created":"2026-06-12","cited_by_count":1,"area":null},{"id":"2606.20245","title":"Navigating Unreliable Parametric and Contextual Knowledge: Explicit Knowledge Conflict Resolution for LLM Inference","created":"2026-06-18","cited_by_count":1,"area":null},{"id":"2607.18232","title":"It's Not What You Say, It's How You Say It: Evaluating LLM Responses to Expressions of Belief","created":"2026-07-20","cited_by_count":1,"area":null},{"id":"2608.12645","title":"Jagged Judges: Epistemic Stability Under Perturbation, Pressure, and Persistence","created":"2026-08-12","cited_by_count":1,"area":"alignment"},{"id":"2608.20769","title":"Do SpeechLMs Hear Their Own Opinions? Diagnosing and Mitigating Previous-Belief Contamination in Streaming Emotion Understanding","created":"2026-08-21","cited_by_count":1,"area":null},{"id":"2504.12996","title":"SHA256 at SemEval-2025 Task 4: Selective Amnesia -- Constrained Unlearning for Large Language Models via Knowledge Isolation","created":"2025-04-17","cited_by_count":0,"area":"safety"},{"id":"2603.04921","title":"AILS-NTUA at SemEval-2026 Task 10: Agentic LLMs for Psycholinguistic Marker Extraction and Conspiracy Endorsement Detection","created":"2026-03-05","cited_by_count":0,"area":"agents"},{"id":"2606.01020","title":"Tackling the Root of Misinformation by Teaching Laypeople about Logical Fallacies via Socratic Questioning and Critical Argumentation","created":"2026-05-31","cited_by_count":0,"area":null}],"next_cursor":"100"}