{"total":94,"rows":[{"id":"2310.13548","title":"Towards Understanding Sycophancy in Language Models","created":"2023-10-20","cited_by_count":1040,"area":null},{"id":"2309.01219","title":"Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models","created":"2023-09-03","cited_by_count":698,"area":null},{"id":"2309.05653","title":"MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuning","created":"2023-09-11","cited_by_count":487,"area":null},{"id":"2309.01029","title":"Explainability for Large Language Models: A Survey","created":"2023-09-02","cited_by_count":333,"area":null},{"id":"2505.13995","title":"ELEPHANT: Measuring and understanding social sycophancy in LLMs","created":"2025-05-20","cited_by_count":129,"area":null},{"id":"2405.08813","title":"CinePile: A Long Video Question Answering Dataset and Benchmark","created":"2024-05-14","cited_by_count":114,"area":null},{"id":"2411.15287","title":"Sycophancy in Large Language Models: Causes and Mitigations","created":"2024-11-22","cited_by_count":101,"area":null},{"id":"2311.11829","title":"System 2 Attention (is something you might need too)","created":"2023-11-20","cited_by_count":89,"area":null},{"id":"2309.15840","title":"How to Catch an AI Liar: Lie Detection in Black-Box LLMs by Asking Unrelated Questions","created":"2023-09-26","cited_by_count":83,"area":null},{"id":"2401.05778","title":"Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems","created":"2024-01-11","cited_by_count":66,"area":null},{"id":"2409.01658","title":"From Yes-Men to Truth-Tellers: Addressing Sycophancy in Large Language Models with Pinpoint Tuning","created":"2024-09-03","cited_by_count":54,"area":null},{"id":"2310.17688","title":"Managing extreme AI risks amid rapid progress","created":"2023-10-26","cited_by_count":48,"area":null},{"id":"2407.18369","title":"AI Safety in Generative AI Large Language Models: A Survey","created":"2024-07-06","cited_by_count":33,"area":null},{"id":"2310.06827","title":"Teaching Language Models to Hallucinate Less with Synthetic Tasks","created":"2023-10-10","cited_by_count":31,"area":null},{"id":"2409.03219","title":"Content Moderation by LLM: From Accuracy to Legitimacy","created":"2024-09-05","cited_by_count":30,"area":null},{"id":"2409.15723","title":"Federated Large Language Models: Current Progress and Future Directions","created":"2024-09-24","cited_by_count":27,"area":null},{"id":"2510.04721","title":"BrokenMath: A Benchmark for Sycophancy in Theorem Proving with LLMs","created":"2025-10-06","cited_by_count":27,"area":null},{"id":"2310.11053","title":"Denevil: Towards Deciphering and Navigating the Ethical Values of Large Language Models via Instruction Learning","created":"2023-10-17","cited_by_count":26,"area":null},{"id":"2407.08039","title":"Knowledge Overshadowing Causes Amalgamated Hallucination in Large Language Models","created":"2024-07-10","cited_by_count":25,"area":null},{"id":"2406.13261","title":"BeHonest: Benchmarking Honesty in Large Language Models","created":"2024-06-19","cited_by_count":24,"area":null},{"id":"2406.00380","title":"HonestLLM: Toward an Honest and Helpful Large Language Model","created":"2024-06-01","cited_by_count":18,"area":null},{"id":"2412.02802","title":"Flattering to Deceive: The Impact of Sycophantic Behavior on User Trust in Large Language Model","created":"2024-12-03","cited_by_count":15,"area":null},{"id":"2504.12691","title":"Why and How LLMs Hallucinate: Connecting the Dots with Subsequence Associations","created":"2025-04-17","cited_by_count":15,"area":null},{"id":"2409.12106","title":"Measuring Human and AI Values Based on Generative Psychometrics with Large Language Models","created":"2024-09-18","cited_by_count":13,"area":null},{"id":"2601.16993","title":"BibAgent: An Agentic Framework for Traceable Miscitation Detection in Scientific Literature","created":"2026-01-12","cited_by_count":9,"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":"2310.02174","title":"Ask Again, Then Fail: Large Language Models' Vacillations in Judgment","created":"2023-10-03","cited_by_count":8,"area":null},{"id":"2404.05783","title":"A Survey on Responsible Generative AI: What to Generate and What Not","created":"2024-04-08","cited_by_count":8,"area":null},{"id":"2602.20273","title":"The Truthfulness Spectrum Hypothesis","created":"2026-02-23","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":"2406.09788","title":"OpenCapBench: A Benchmark to Bridge Pose Estimation and Biomechanics","created":"2024-06-14","cited_by_count":7,"area":null},{"id":"2507.07484","title":"Machine Bullshit: Characterizing the Emergent Disregard for Truth in Large Language Models","created":"2025-07-10","cited_by_count":7,"area":null},{"id":"2407.12393","title":"PersLLM: A Personified Training Approach for Large Language Models","created":"2024-07-17","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":"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":"2503.01844","title":"Can (A)I Change Your Mind?","created":"2025-03-03","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":"2403.19219","title":"Collaborative Knowledge Infusion for Low-resource Stance Detection","created":"2024-03-28","cited_by_count":4,"area":null},{"id":"2405.16579","title":"Automatically Generating Numerous Context-Driven SFT Data for LLMs across Diverse Granularity","created":"2024-05-26","cited_by_count":4,"area":null},{"id":"2510.19152","title":"Subliminal Corruption: Mechanisms, Thresholds, and Interpretability","created":"2025-10-22","cited_by_count":4,"area":null},{"id":"2605.09228","title":"ProactBench: Beyond What The User Asked For","created":"2026-05-09","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":"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":"2412.04235","title":"Addressing Hallucinations with RAG and NMISS in Italian Healthcare LLM Chatbots","created":"2024-12-05","cited_by_count":3,"area":null},{"id":"2508.15815","title":"User-Assistant Bias in LLMs","created":"2025-08-16","cited_by_count":3,"area":null},{"id":"2511.07318","title":"When Bias Pretends to Be Truth: How Spurious Correlations Undermine Hallucination Detection in LLMs","created":"2025-11-10","cited_by_count":3,"area":null},{"id":"2603.18373","title":"To See or To Please: Uncovering Visual Sycophancy and Split Beliefs in VLMs","created":"2026-03-19","cited_by_count":3,"area":null},{"id":"2605.05957","title":"Knowing but Not Correcting: Routine Task Requests Suppress Factual Correction in LLMs","created":"2026-05-07","cited_by_count":3,"area":null},{"id":"2606.30383","title":"Whose Side Is Your Agent On? Multi-Party Principal Loyalty in LLM Agents","created":"2026-06-29","cited_by_count":3,"area":null},{"id":"2608.23875","title":"AI Finds A Way","created":"2026-08-24","cited_by_count":3,"area":null},{"id":"2309.13079","title":"MiChao-HuaFen 1.0: A Specialized Pre-trained Corpus Dataset for Domain-specific Large Models","created":"2023-09-21","cited_by_count":2,"area":null},{"id":"2505.12182","title":"Truth Neurons","created":"2025-05-18","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":"2605.09314","title":"How LLMs Are Persuaded: A Few Attention Heads, Rerouted","created":"2026-05-10","cited_by_count":2,"area":null},{"id":"2605.13737","title":"Senses Wide Shut: A Representation-Action Gap in Omnimodal LLMs","created":"2026-05-13","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":"2410.05349","title":"SoK: Towards Security and Safety of Edge AI","created":"2024-10-07","cited_by_count":1,"area":null},{"id":"2410.11684","title":"Are UFOs Driving Innovation? The Illusion of Causality in Large Language Models","created":"2024-10-15","cited_by_count":1,"area":null},{"id":"2504.00408","title":"From Intuition to Understanding: Using AI Peers to Overcome Physics Misconceptions","created":"2025-04-01","cited_by_count":1,"area":null},{"id":"2509.00869","title":"Exploring and Mitigating Fawning Hallucinations in Large Language Models","created":"2025-08-31","cited_by_count":1,"area":null},{"id":"2509.08950","title":"Deploying AI for Signal Processing education: Selected challenges and intriguing opportunities","created":"2025-09-10","cited_by_count":1,"area":null},{"id":"2601.04369","title":"Generalization to Political Beliefs from Fine-Tuning on Sports Team Preferences","created":"2026-01-07","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":"2603.03970","title":"Generative AI for Managerial Decision-Making under Ambiguity and Sycophancy","created":"2026-03-04","cited_by_count":1,"area":null},{"id":"2604.25934","title":"LLM Psychosis: A Theoretical and Diagnostic Framework for Reality-Boundary Failures in Large Language Models","created":"2026-04-07","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":"2606.09068","title":"Emergent Misalignment Can Be Induced by Sycophancy and Reversed via Alignment Gating","created":"2026-06-08","cited_by_count":1,"area":null},{"id":"2607.10608","title":"The Compliance Trap: Diagnosing How AI Agents Consume Conflicting Memory","created":"2026-07-12","cited_by_count":1,"area":null},{"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":"2608.01835","title":"Rewriting or Reweighting? A Geometric Account in Language Models","created":"2026-08-03","cited_by_count":1,"area":null},{"id":"2506.16064","title":"Self-Critique-Guided Curiosity Refinement: Enhancing Honesty and Helpfulness in Large Language Models via In-Context Learning","created":"2025-06-19","cited_by_count":0,"area":null},{"id":"2508.19463","title":"\"She was useful, but a bit too optimistic\": Augmenting Design with Interactive Virtual Personas","created":"2025-08-26","cited_by_count":0,"area":null},{"id":"2508.19620","title":"A Scenario-Oriented Survey of Federated Recommender Systems: Techniques, Challenges, and Future Directions","created":"2025-08-27","cited_by_count":0,"area":null},{"id":"2601.13122","title":"Responsible AI for General-Purpose Systems: Overview, Challenges, and A Path Forward","created":"2026-01-19","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":"2602.20400","title":"Three Concrete Challenges and Two Hopes for the Safety of Unsupervised Elicitation","created":"2026-02-23","cited_by_count":0,"area":null},{"id":"2603.13356","title":"Learning When to Trust in Contextual Social Bandits","created":"2026-03-09","cited_by_count":0,"area":null},{"id":"2604.20652","title":"Large Language Models Outperform Humans in Fraud Detection and Resistance to Motivated Investor Pressure","created":"2026-04-22","cited_by_count":0,"area":null},{"id":"2605.02010","title":"Reliable AI Needs to Externalize Implicit Knowledge: A Human-AI Collaboration Perspective","created":"2026-05-03","cited_by_count":0,"area":null},{"id":"2605.29027","title":"Mind Your Tone: Does Tone Alter LLM Performance?","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2606.04035","title":"Unpredictable Safety: Domain-Dependent Compliance and the Transparency Gap in Open-Weight LLMs","created":"2026-06-01","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":"2606.16914","title":"Greed Is Learned: Visible Incentives as Reward-Hacking Triggers","created":"2026-06-15","cited_by_count":0,"area":null},{"id":"2606.26102","title":"Helpfulness Hurts: Domain-Dependent Degradation of Mid-Trained Compassion Values Under Post-Training","created":"2026-04-30","cited_by_count":0,"area":null},{"id":"2607.09306","title":"Exposure is not manifestation: measurement target and output resolution jointly determine which behavioural-faithfulness evaluator wins","created":"2026-07-10","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":"2608.16650","title":"PCA-guided Activation Scaling for Monotonic Bidirectional Control over LLM Sycophancy","created":"2026-08-17","cited_by_count":0,"area":null},{"id":"2608.25267","title":"Mitigating LLM sycophancy with RL-based fine-tuning: Bayesian Truth Serum approach","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2609.04445","title":"Conformity Breaks Conformal Prediction","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2609.30028","title":"How does Adversarial Influence Scale in Multi-Agent Systems?","created":"2026-09-24","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":"2609.39863","title":"FIGS: Evaluating Multi-Turn Sycophancy Without Penalizing Empathy","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.06522","title":"Anatomy of LLM Sycophancy: What a Flip Rate Hides","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.11305","title":"BeliefScope: Diagnosing Evidence-Driven Revision and Pressure-Induced Shifts in Large Language Models","created":"2026-10-08","cited_by_count":0,"area":null}],"next_cursor":null}