{"total":117,"rows":[{"id":"2509.25760","title":"TruthRL: Incentivizing Truthful LLMs via Reinforcement Learning","created":"2025-09-30","cited_by_count":27,"area":null},{"id":"2512.08093","title":"Training LLMs for Honesty via Confessions","created":"2025-12-08","cited_by_count":22,"area":null},{"id":"2602.08169","title":"Spherical Steering: Geometry-Aware Activation Rotation for Language Models","created":"2026-02-09","cited_by_count":21,"area":null},{"id":"2512.19920","title":"Mitigating LLM Hallucination via Behaviorally Calibrated Reinforcement Learning","created":"2025-12-22","cited_by_count":18,"area":null},{"id":"2601.05503","title":"Over-Searching in Search-Augmented Large Language Models","created":"2026-01-09","cited_by_count":11,"area":null},{"id":"2602.14233","title":"Evaluating LLMs in Finance Requires Explicit Bias Consideration","created":"2026-02-15","cited_by_count":11,"area":null},{"id":"2511.19933","title":"Failure Modes in LLM Systems: A System-Level Taxonomy for Reliable AI Applications","created":"2025-11-25","cited_by_count":10,"area":null},{"id":"2603.22161","title":"Causal Evidence that Language Models use Confidence to Drive Behavior","created":"2026-03-23","cited_by_count":10,"area":null},{"id":"2511.05759","title":"Language Generation: Complexity Barriers and Implications for Learning","created":"2025-11-07","cited_by_count":9,"area":null},{"id":"2604.03216","title":"BAS: A Decision-Theoretic Approach to Evaluating Large Language Model Confidence","created":"2026-04-03","cited_by_count":7,"area":null},{"id":"2606.30850","title":"BayesBench: Evaluating LLM Belief Trajectories Under Multi-Turn Evidence Accumulation","created":"2026-06-29","cited_by_count":7,"area":null},{"id":"2509.09711","title":"PsychiatryBench: A Multi-Task Benchmark for LLMs in Psychiatry","created":"2025-09-07","cited_by_count":6,"area":null},{"id":"2512.16883","title":"AdaSearch: Balancing Parametric Knowledge and Search in Large Language Models via Reinforcement Learning","created":"2025-12-18","cited_by_count":6,"area":null},{"id":"2511.11500","title":"Honesty over Accuracy: Trustworthy Language Models through Reinforced Hesitation","created":"2025-11-14","cited_by_count":5,"area":null},{"id":"2601.22548","title":"Are LLM Evaluators Really Narcissists? Sanity Checking Self-Preference Evaluations","created":"2026-01-30","cited_by_count":5,"area":null},{"id":"2604.03904","title":"I-CALM: Incentivizing Confidence-Aware Abstention for LLM Selective Answering","created":"2026-04-05","cited_by_count":5,"area":null},{"id":"2509.08182","title":"XML Prompting as Grammar-Constrained Interaction: Fixed-Point Semantics, Convergence Guarantees, and Human-AI Protocols","created":"2025-09-09","cited_by_count":4,"area":null},{"id":"2510.05126","title":"Generalization of Fine-Tuned Uncertainty Communication and Metacognition in Large Language Models","created":"2025-09-30","cited_by_count":4,"area":null},{"id":"2511.01348","title":"The Future of Generative AI in Software Engineering: A Vision from Industry and Academia in the European GENIUS Project","created":"2025-11-03","cited_by_count":4,"area":null},{"id":"2512.10652","title":"TriDF: Evaluating Perception, Detection, and Hallucination for Interpretable DeepFake Detection","created":"2025-12-11","cited_by_count":4,"area":null},{"id":"2602.16162","title":"LLMs Exhibit Significantly Lower Uncertainty in Creative Writing Than Professional Writers","created":"2026-02-18","cited_by_count":4,"area":null},{"id":"2607.11022","title":"When the Reward Suite Is Leaky: A Preregistered Causal Contrast of Natural Verifier False Positives in RLVR","created":"2026-07-13","cited_by_count":4,"area":null},{"id":"2510.22242","title":"PaperAsk: A Benchmark for Reliability Evaluation of LLMs in Paper Search and Reading","created":"2025-10-25","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":"2511.08877","title":"Hierarchical Memorization in Large Language Models: Evidence from Citation Generation","created":"2025-11-12","cited_by_count":3,"area":null},{"id":"2512.23547","title":"Lie to Me: Knowledge Graphs for Robust Hallucination Self-Detection in LLMs","created":"2025-12-29","cited_by_count":3,"area":null},{"id":"2603.00801","title":"The Synthetic Web: Adversarially-Curated Mini-Internets for Diagnosing Epistemic Weaknesses of Language Agents","created":"2026-02-28","cited_by_count":3,"area":null},{"id":"2604.23505","title":"Uncertainty Propagation in LLM-Based Systems","created":"2026-04-26","cited_by_count":3,"area":null},{"id":"2605.05134","title":"Low-Cost Black-Box Detection of LLM Hallucinations via Dynamical System Prediction","created":"2026-05-06","cited_by_count":3,"area":null},{"id":"2510.05116","title":"Hallucination is Inevitable for LLMs with the Open World Assumption","created":"2025-09-29","cited_by_count":2,"area":null},{"id":"2510.13852","title":"ConsistencyAI: A Benchmark to Assess LLMs' Factual Consistency When Responding to Different Demographic Groups","created":"2025-10-11","cited_by_count":2,"area":null},{"id":"2510.20075","title":"LLMs can hide text in other text of the same length","created":"2025-10-22","cited_by_count":2,"area":null},{"id":"2510.25378","title":"Hallucinations in Bibliographic Recommendation: Citation Frequency as a Proxy for Training Data Redundancy","created":"2025-10-29","cited_by_count":2,"area":null},{"id":"2601.06116","title":"The Homogenization Problem in LLMs: Towards Meaningful Diversity in AI Safety","created":"2026-01-03","cited_by_count":2,"area":null},{"id":"2602.00906","title":"Hallucination is a Consequence of Space-Optimality: A Rate-Distortion Theorem for Membership Testing","created":"2026-01-31","cited_by_count":2,"area":null},{"id":"2602.02018","title":"Do I Really Know? Learning Factual Self-Verification for Hallucination Reduction","created":"2026-02-02","cited_by_count":2,"area":null},{"id":"2602.11166","title":"Small Updates, Big Doubts: Does Parameter-Efficient Fine-tuning Enhance Hallucination Detection ?","created":"2026-01-17","cited_by_count":2,"area":null},{"id":"2602.19844","title":"LLM-enabled Applications Require System-Level Threat Monitoring","created":"2026-02-23","cited_by_count":2,"area":null},{"id":"2604.14829","title":"Beyond Literal Summarization: Redefining Hallucination for Medical SOAP Note Evaluation","created":"2026-04-16","cited_by_count":2,"area":null},{"id":"2604.22779","title":"KARL: Mitigating Hallucinations in LLMs via Knowledge-Boundary-Aware Reinforcement Learning","created":"2026-04-03","cited_by_count":2,"area":null},{"id":"2605.01011","title":"CLEAR: Revealing How Noise and Ambiguity Degrade Reliability in LLMs for Medicine","created":"2026-05-01","cited_by_count":2,"area":null},{"id":"2609.07879","title":"Do Large Language Models Know What They Don't Know II? A Fully Behavioral, Non-Cognitive Measure of Epistemic Honesty","created":"2026-09-07","cited_by_count":2,"area":null},{"id":"2510.19886","title":"An Expert-grounded benchmark of General Purpose LLMs in LCA","created":"2025-10-22","cited_by_count":1,"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":"2512.14801","title":"Incentives or Ontology? A Structural Rebuttal to OpenAI's Hallucination Thesis","created":"2025-12-16","cited_by_count":1,"area":null},{"id":"2512.16750","title":"Plausibility as Failure: How LLMs and Humans Co-Construct Epistemic Error","created":"2025-12-18","cited_by_count":1,"area":null},{"id":"2601.15714","title":"Even GPT-5.2 Can't Count to Five: The Case for Zero-Error Horizons in Trustworthy LLMs","created":"2026-01-22","cited_by_count":1,"area":null},{"id":"2601.19839","title":"HARMONI: Multimodal Personalization of Multi-User Human-Robot Interactions with LLMs","created":"2026-01-27","cited_by_count":1,"area":null},{"id":"2601.22648","title":"UCPO: Uncertainty-Aware Policy Optimization","created":"2026-01-30","cited_by_count":1,"area":null},{"id":"2602.05279","title":"Hallucination-Resistant Security Planning with a Large Language Model","created":"2026-02-05","cited_by_count":1,"area":null},{"id":"2602.07259","title":"Incentive-Aware AI Safety via Strategic Resource Allocation: A Stackelberg Security Games Perspective","created":"2026-02-06","cited_by_count":1,"area":null},{"id":"2602.13224","title":"A Geometric Taxonomy of Hallucinations in LLMs","created":"2026-01-26","cited_by_count":1,"area":null},{"id":"2602.18671","title":"Spilled Energy in Large Language Models","created":"2026-02-21","cited_by_count":1,"area":null},{"id":"2603.25711","title":"Seeing to Ground: Visual Attention for Hallucination-Resilient MDLLMs","created":"2026-03-26","cited_by_count":1,"area":null},{"id":"2604.03045","title":"STEAR: Layer-Aware Spatiotemporal Evidence Intervention for Hallucination Mitigation in Video Large Language Models","created":"2026-04-03","cited_by_count":1,"area":null},{"id":"2604.12543","title":"A Two-Stage LLM Framework for Accessible and Verified XAI Explanations","created":"2026-04-14","cited_by_count":1,"area":null},{"id":"2604.27906","title":"From Unstructured Recall to Schema-Grounded Memory: Reliable AI Memory via Iterative, Schema-Aware Extraction","created":"2026-04-30","cited_by_count":1,"area":null},{"id":"2605.02915","title":"When Should a Language Model Trust Itself? Same-Model Self-Verification as a Conditional Confidence Signal","created":"2026-04-08","cited_by_count":1,"area":null},{"id":"2605.14021","title":"Measuring Google AI Overviews: Activation, Source Quality, Claim Fidelity, and Publisher Impact","created":"2026-05-13","cited_by_count":1,"area":null},{"id":"2605.17561","title":"Automated Root-Cause Subclassification and No-Code Fix Generation for Invalid Bug Reports","created":"2026-05-17","cited_by_count":1,"area":null},{"id":"2605.18732","title":"Predictable Confabulations: Factual Recall by LLMs Scales with Model Size and Topic Frequency","created":"2026-05-18","cited_by_count":1,"area":null},{"id":"2606.06959","title":"OpenHalDet: A Unified Benchmark for Hallucination Detection across Diverse Generation Scenarios","created":"2026-06-05","cited_by_count":1,"area":null},{"id":"2509.06902","title":"Proof-Carrying Numbers (PCN): A Protocol for Trustworthy Numeric Answers from LLMs via Claim Verification","created":"2025-09-08","cited_by_count":0,"area":null},{"id":"2509.14386","title":"Disproving the Feasibility of Learned Confidence Calibration Under Binary Supervision: An Information-Theoretic Impossibility","created":"2025-09-17","cited_by_count":0,"area":null},{"id":"2509.21473","title":"Are Hallucinations Bad Estimations?","created":"2025-09-25","cited_by_count":0,"area":null},{"id":"2510.00821","title":"Logical Consistency Between Disagreeing Experts and Its Role in AI Safety","created":"2025-10-01","cited_by_count":0,"area":null},{"id":"2510.06029","title":"Fast Leave-One-Out Approximation from Fragment-Target Prevalence Vectors (molFTP) : From Dummy Masking to Key-LOO for Leakage-Free Feature Construction","created":"2025-10-07","cited_by_count":0,"area":null},{"id":"2510.17918","title":"JT-Safe: Intrinsically Enhancing the Safety and Trustworthiness of LLMs","created":"2025-10-20","cited_by_count":0,"area":null},{"id":"2511.01363","title":"Automatic Minds: Cognitive Parallels Between Hypnotic States and Large Language Model Processing","created":"2025-11-03","cited_by_count":0,"area":null},{"id":"2511.21753","title":"Extracting Disaster Impacts and Impact Related Locations in Social Media Posts Using Large Language Models","created":"2025-11-24","cited_by_count":0,"area":null},{"id":"2512.04442","title":"TaskEval: Synthesised Evaluation for Foundation-Model Tasks","created":"2025-12-04","cited_by_count":0,"area":null},{"id":"2512.05461","title":"Knowing Your Uncertainty -- On the application of LLM in social sciences","created":"2025-12-05","cited_by_count":0,"area":null},{"id":"2512.06001","title":"Small Language Models Reshape Higher Education: Courses, Textbooks, and Teaching","created":"2025-12-02","cited_by_count":0,"area":null},{"id":"2601.00641","title":"Probabilistic Guarantees for Reducing Contextual Hallucinations in LLMs","created":"2026-01-02","cited_by_count":0,"area":null},{"id":"2602.06197","title":"Personagram: Bridging Personas and Product Design for Creative Ideation with Multimodal LLMs","created":"2026-02-05","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":"2603.09986","title":"Quantifying Hallucinations in Language Language Models on Medical Textbooks","created":"2026-02-12","cited_by_count":0,"area":null},{"id":"2603.10047","title":"Toward Epistemic Stability: Engineering Consistent Procedures for Industrial LLM Hallucination Reduction","created":"2026-03-08","cited_by_count":0,"area":null},{"id":"2603.17872","title":"Mitigating LLM Hallucinations through Domain-Grounded Tiered Retrieval","created":"2026-03-18","cited_by_count":0,"area":null},{"id":"2603.26363","title":"A Formal Framework for Uncertainty Analysis of Text Generation with Large Language Models","created":"2026-03-27","cited_by_count":0,"area":null},{"id":"2603.27033","title":"RealBirdID: Benchmarking Bird Species Identification in the Era of MLLMs","created":"2026-03-27","cited_by_count":0,"area":null},{"id":"2603.29149","title":"Knowledge database development by large language models for countermeasures against viruses and marine toxins","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2604.05779","title":"What Models Know, How Well They Know It: Knowledge-Weighted Fine-Tuning for Learning When to Say \"I Don't Know\"","created":"2026-04-07","cited_by_count":0,"area":null},{"id":"2604.08454","title":"Less Data Approximates More: Earning Faithful Confidence in High-Stakes Domains","created":"2026-04-09","cited_by_count":0,"area":null},{"id":"2604.15460","title":"The Crutch or the Ceiling? How Different Generations of LLMs Shape EFL Student Writings","created":"2026-04-16","cited_by_count":0,"area":null},{"id":"2605.05025","title":"Detecting Hallucinations in Large Language Models via Internal Attention Divergence Signals","created":"2026-05-06","cited_by_count":0,"area":null},{"id":"2605.11163","title":"Benchmarking LLM-Based Static Analysis for Secure Smart Contract Development: Reliability, Limitations, and Potential Hybrid Solutions","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.12384","title":"Scalable Token-Level Hallucination Detection in Large Language Models","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2605.26400","title":"Plans for Evaluating Structured Generative Search Summaries","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2605.26808","title":"Innovation: An Almost Characterization of Hallucination","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2605.28264","title":"Entropy Distribution as a Fingerprint for Hallucinations in Generative Models","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2606.00919","title":"Towards Lightweight Reliability: Using Soft Prompts for Hallucination Mitigation in Large Language Models","created":"2026-05-30","cited_by_count":0,"area":null},{"id":"2606.04500","title":"SANE Schema-aware Natural-language Evaluation of Biological Data","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2606.16214","title":"Calibrated Sampling-Free Uncertainty Estimation in Bayesian Deep Learning","created":"2026-06-15","cited_by_count":0,"area":null},{"id":"2606.20585","title":"Turning Intent into Specifications: A Benchmark and an Interactive User-Assistant Agent","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2606.20776","title":"Formally Verified Code Synthesis for Structured Data Translation in a Medical Internet of Things","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2606.24790","title":"Grad Detect: Gradient-Based Hallucination Detection in LLMs","created":"2026-06-23","cited_by_count":0,"area":null},{"id":"2607.12687","title":"From Critic to Confidence: PPO for Language-Based Quantitative Prediction with Confidence Estimation","created":"2026-07-14","cited_by_count":0,"area":null},{"id":"2607.12831","title":"Knowledgeless Language Models: Suppressing Parametric Recall for Evidence-Grounded Language Modeling","created":"2026-07-14","cited_by_count":0,"area":null},{"id":"2607.17621","title":"Mechanistic Attention Guidance for Agent Memory Refinement","created":"2026-07-20","cited_by_count":0,"area":null}],"next_cursor":"100"}