{"total":51,"rows":[{"id":"2510.06265","title":"Large Language Models Hallucination: A Comprehensive Survey","created":"2025-10-05","cited_by_count":49,"area":null},{"id":"2509.25760","title":"TruthRL: Incentivizing Truthful LLMs via Reinforcement Learning","created":"2025-09-30","cited_by_count":27,"area":null},{"id":"2601.05752","title":"AutoMonitor-Bench: Evaluating the Reliability of LLM-Based Misbehavior Monitor","created":"2026-01-09","cited_by_count":10,"area":null},{"id":"2508.05201","title":"FAITH: A Framework for Assessing Intrinsic Tabular Hallucinations in Finance","created":"2025-08-07","cited_by_count":8,"area":null},{"id":"2508.00109","title":"FACTORY: A Challenging Human-Verified Prompt Set for Long-Form Factuality","created":"2025-07-31","cited_by_count":6,"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":"2601.06194","title":"Political Alignment in Large Language Models: A Multidimensional Audit of Psychometric Identity and Behavioral Bias","created":"2026-01-08","cited_by_count":5,"area":null},{"id":"2602.19715","title":"Pixels Don't Lie (But Your Detector Might): Bootstrapping MLLM-as-a-Judge for Trustworthy Deepfake Detection and Reasoning Supervision","created":"2026-02-23","cited_by_count":5,"area":null},{"id":"2509.06938","title":"From Noise to Narrative: Tracing the Origins of Hallucinations in Transformers","created":"2025-09-08","cited_by_count":4,"area":null},{"id":"2510.08005","title":"Past, Present, and Future of Bug Tracking in the Generative AI Era","created":"2025-10-09","cited_by_count":4,"area":null},{"id":"2601.07058","title":"Hallucinations Live in Variance","created":"2026-01-11","cited_by_count":4,"area":null},{"id":"2504.21625","title":"Meeseeks: A Feedback-Driven, Iterative Self-Correction Benchmark evaluating LLMs' Instruction Following Capability","created":"2025-04-30","cited_by_count":3,"area":null},{"id":"2511.20836","title":"Structured Prompts Improve Evaluation of Language Models","created":"2025-11-25","cited_by_count":3,"area":null},{"id":"2505.14101","title":"MultiHal: Multilingual Dataset for Knowledge-Graph Grounded Evaluation of LLM Hallucinations","created":"2025-05-20","cited_by_count":2,"area":null},{"id":"2510.22395","title":"Confabulations from ACL Publications (CAP): A Dataset for Scientific Hallucination Detection","created":"2025-10-25","cited_by_count":2,"area":null},{"id":"2602.21857","title":"Distill and Align Decomposition for Enhanced Claim Verification","created":"2026-02-25","cited_by_count":2,"area":null},{"id":"2606.11105","title":"PhantomBench: Benchmarking the Non-existential Threat of Language Models","created":"2026-06-09","cited_by_count":2,"area":null},{"id":"2505.11365","title":"Phare: A Safety Probe for Large Language Models","created":"2025-05-16","cited_by_count":1,"area":null},{"id":"2505.12621","title":"SAFE: Improving LLM Systems using Sentence-Level In-generation Attribution","created":"2025-05-19","cited_by_count":1,"area":null},{"id":"2509.20278","title":"Quantifying LLM Biases Across Instruction Boundary in Mixed Question Forms","created":"2025-09-24","cited_by_count":1,"area":null},{"id":"2512.03345","title":"HalluGen: Synthesizing Realistic and Controllable Hallucinations for Evaluating Image Restoration","created":"2025-12-03","cited_by_count":1,"area":null},{"id":"2602.04785","title":"Team, Then Trim: An Assembly-Line LLM Framework for High-Quality Tabular Data Generation","created":"2026-02-04","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":"2604.00920","title":"GPT-NL Public Corpus: A Permissively Licensed, Dutch-First Dataset for LLM Pre-training","created":"2026-04-01","cited_by_count":1,"area":null},{"id":"2605.05953","title":"Hallucination as an Anomaly: Dynamic Intervention via Probabilistic Circuits","created":"2026-05-07","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":"2606.13111","title":"M\\\"OVE: A Holistic LLM Benchmark for the German Public Sector","created":"2026-06-11","cited_by_count":1,"area":null},{"id":"2607.19257","title":"Prompt Design at Scale: How Format, Instruction Count, and Context Length Shape Instruction Adherence and Hallucination in Large Language Models","created":"2026-07-21","cited_by_count":1,"area":null},{"id":"2607.22676","title":"How LLM Task-Adaptation Reshapes Alignment: A Multi-dimensional Study of Behavioral and Representational Drift","created":"2026-07-10","cited_by_count":1,"area":null},{"id":"2608.00939","title":"Temperature-driven inversion and nonlinear dynamics in ChatGPT-like AIs","created":"2026-08-02","cited_by_count":1,"area":null},{"id":"2506.13990","title":"Machine Mirages: Defining the Undefined","created":"2025-06-03","cited_by_count":0,"area":null},{"id":"2508.00600","title":"A Context-Aware Dual-Metric Framework for Confidence Estimation in Large Language Models","created":"2025-08-01","cited_by_count":0,"area":null},{"id":"2510.02326","title":"Hallucination-Resistant, Domain-Specific Research Assistant with Self-Evaluation and Vector-Grounded Retrieval","created":"2025-09-25","cited_by_count":0,"area":null},{"id":"2601.14280","title":"Hallucination-Free Automatic Question & Answer Generation for Intuitive Learning","created":"2026-01-13","cited_by_count":0,"area":null},{"id":"2602.19643","title":"KGHaluBench: A Knowledge Graph-Based Hallucination Benchmark for Evaluating the Breadth and Depth of LLM Knowledge","created":"2026-02-23","cited_by_count":0,"area":null},{"id":"2605.01372","title":"Embedding-based In-Context Prompt Training for Enhancing LLMs as Text Encoders","created":"2026-05-02","cited_by_count":0,"area":null},{"id":"2605.02504","title":"A multilingual hallucination benchmark: MultiWikiQHalluA","created":"2026-05-04","cited_by_count":0,"area":null},{"id":"2605.10442","title":"StereoTales: A Multilingual Framework for Open-Ended Stereotype Discovery in LLMs","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.19229","title":"Can Large Language Models Revolutionize Survey Research? Experiments with Disaster Preparedness Responses","created":"2026-05-19","cited_by_count":0,"area":null},{"id":"2605.20591","title":"Do No Harm? Hallucination and Actor-Level Abuse in Web-Deployed Medical Large Language Models","created":"2026-05-20","cited_by_count":0,"area":null},{"id":"2605.27016","title":"How Do Uncertainty Estimators Align with Hallucination Occurrence in LLMs?","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2605.30018","title":"Latent Performance Profiling of Large Language Models","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2605.30481","title":"When English Rewrites Local Knowledge: Global Narrative Dominance in Large Language Models","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2606.26857","title":"LCAi: Life Cycle Assessment with big data fusion and retrieval-augmented generation-assisted interpretation","created":"2026-06-25","cited_by_count":0,"area":null},{"id":"2607.17524","title":"Token-Level Off-Policy Learning for Faithful Generation Under Distribution Shift","created":"2026-07-20","cited_by_count":0,"area":null},{"id":"2607.20476","title":"Benchmarking Large Language Models on Multi-Sensor Physical Hazard Assessment","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2608.14210","title":"How Much Do Legal RAG Systems Still Hallucinate?","created":"2026-08-14","cited_by_count":0,"area":null},{"id":"2608.27716","title":"PCFBench: A Diagnostic Benchmark for Product Carbon Footprint Estimation","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2609.20195","title":"Music Hallucination in Audio-Language Models: A Hierarchical Formulation and Empirical Study","created":"2026-07-24","cited_by_count":0,"area":null},{"id":"2609.22152","title":"Is Imagination Derived from Hallucination? A Cross-Taxonomy Evaluation of Imagination and Hallucination in Large Language Models","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2610.03063","title":"HARPO: Hallucination-Aware Reinforcement Learning for Faithful and Creative Language Generation","created":"2026-10-02","cited_by_count":0,"area":null}],"next_cursor":null}