{"total":92,"rows":[{"id":"2506.09038","title":"AbstentionBench: Reasoning LLMs Fail on Unanswerable Questions","created":"2025-06-10","cited_by_count":145,"area":"lr"},{"id":"2506.22355","title":"Embodied AI Agents: Modeling the World","created":"2025-06-27","cited_by_count":61,"area":"wm"},{"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":"2507.21017","title":"MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them","created":"2025-07-28","cited_by_count":16,"area":"agents"},{"id":"2505.17815","title":"Evaluation Faking: Unveiling Observer Effects in Safety Evaluation of Frontier AI Systems","created":"2025-05-23","cited_by_count":14,"area":"lr"},{"id":"2509.06861","title":"Test-Time Scaling in Reasoning Models Is Not Effective for Knowledge-Intensive Tasks Yet","created":"2025-09-08","cited_by_count":11,"area":"lr"},{"id":"2512.06914","title":"SoK: Trust-Authorization Mismatch in LLM Agent Interactions","created":"2025-12-07","cited_by_count":11,"area":"agents"},{"id":"2602.04705","title":"ERNIE 5.0 Technical Report","created":"2026-02-04","cited_by_count":11,"area":"moe"},{"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":"2506.02992","title":"Mitigating Manipulation and Enhancing Persuasion: A Reflective Multi-Agent Approach for Legal Argument Generation","created":"2025-06-03","cited_by_count":8,"area":"agents"},{"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":"2601.11004","title":"NOVA: NOise-aware Verbal Confidence CAlibration for Robust Large Language Models in RAG Systems","created":"2026-01-16","cited_by_count":6,"area":"rag"},{"id":"2508.06361","title":"Beyond Prompt-Induced Lies: Investigating LLM Deception on Benign Prompts","created":"2025-08-08","cited_by_count":5,"area":"lr"},{"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":"2603.15408","title":"TrinityGuard: A Unified Framework for Safeguarding Multi-Agent Systems","created":"2026-03-16","cited_by_count":5,"area":"agents"},{"id":"2507.09751","title":"Sound and Complete Neurosymbolic Reasoning with LLM-Grounded Interpretations","created":"2025-07-13","cited_by_count":4,"area":"lr"},{"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":"2509.23765","title":"Knowledge-Level Consistency Reinforcement Learning: Dual-Fact Alignment for Long-Form Factuality","created":"2025-09-28","cited_by_count":4,"area":"alignment"},{"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":"2512.01909","title":"Latent Debate: A Surrogate Framework for Interpreting LLM Thinking","created":"2025-12-01","cited_by_count":3,"area":"lr"},{"id":"2604.17284","title":"HalluClear: Diagnosing, Evaluating and Mitigating Hallucinations in GUI Agents","created":"2026-04-19","cited_by_count":3,"area":"agents"},{"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":"2506.06331","title":"How Significant Are the Real Performance Gains? An Unbiased Evaluation Framework for GraphRAG","created":"2025-05-31","cited_by_count":2,"area":"rag"},{"id":"2507.08038","title":"AblationBench: Evaluating Automated Planning of Ablations in Empirical AI Research","created":"2025-07-09","cited_by_count":2,"area":"agents"},{"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":"2510.24476","title":"Mitigating Hallucination in Large Language Models (LLMs): An Application-Oriented Survey on RAG, Reasoning, and Agentic Systems","created":"2025-10-28","cited_by_count":2,"area":"lr"},{"id":"2510.26495","title":"Rethinking Text-to-SQL: Dynamic Multi-turn SQL Interaction for Real-world Database Exploration","created":"2025-10-30","cited_by_count":2,"area":"lr"},{"id":"2602.21857","title":"Distill and Align Decomposition for Enhanced Claim Verification","created":"2026-02-25","cited_by_count":2,"area":null},{"id":"2605.01546","title":"6G Needs Agents: Toward Agentic AI-Native Networks for Autonomous Intelligence","created":"2026-05-02","cited_by_count":2,"area":"agents"},{"id":"2605.19192","title":"Hallucination as Exploit: Evidence-Carrying Multimodal Agents","created":"2026-05-18","cited_by_count":2,"area":"agents"},{"id":"2605.19341","title":"HalluWorld: A Controlled Benchmark for Hallucination via Reference World Models","created":"2026-05-19","cited_by_count":2,"area":"wm"},{"id":"2606.11105","title":"PhantomBench: Benchmarking the Non-existential Threat of Language Models","created":"2026-06-09","cited_by_count":2,"area":null},{"id":"2607.00918","title":"From Personas to Plot: Character-Grounded Multi-Agent Story Generation for Long-Form Narratives","created":"2026-07-01","cited_by_count":2,"area":"agents"},{"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":"2506.08625","title":"RAISE: Enhancing Scientific Reasoning in LLMs via Step-by-Step Retrieval","created":"2025-06-10","cited_by_count":1,"area":"lr"},{"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":"2604.24665","title":"Benchmarking Source-Sensitive Reasoning in Turkish: Humans and LLMs under Evidential Trust Manipulation","created":"2026-04-27","cited_by_count":1,"area":"lr"},{"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":"2606.15549","title":"One Goal, Many Commands: Characterizing Denylist Fragility in AI Agents","created":"2026-06-14","cited_by_count":1,"area":"agents"},{"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":"2608.14632","title":"DeMTS: Denoising Trajectories as Multivariate Time Series for Hallucination Detection in Diffusion Language Models","created":"2026-07-24","cited_by_count":1,"area":"diffusion"},{"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":"2509.00449","title":"GOSU: Retrieval-Augmented Generation with Global-Level Optimized Semantic Unit-Centric Framework","created":"2025-08-30","cited_by_count":0,"area":"rag"},{"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":"2511.21438","title":"Conversational No-code, Multi-agentic Disease Module Identification and Drug Repurposing Prediction with ChatDRex","created":"2025-11-26","cited_by_count":0,"area":"agents"},{"id":"2601.07315","title":"VLM-CAD: VLM-Optimized Collaborative Agent Design Workflow for Analog Circuit Sizing","created":"2026-01-12","cited_by_count":0,"area":"lr"},{"id":"2601.14280","title":"Hallucination-Free Automatic Question & Answer Generation for Intuitive Learning","created":"2026-01-13","cited_by_count":0,"area":null},{"id":"2602.17930","title":"MIRA: Memory-Integrated Reinforcement Learning Agent with Limited LLM Guidance","created":"2026-02-20","cited_by_count":0,"area":"agents"},{"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":"2603.02420","title":"Slurry-as-a-Service: A Modest Proposal on Scalable Pluralistic Alignment for Nutrient Optimization","created":"2026-03-02","cited_by_count":0,"area":"alignment"},{"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":"2605.14431","title":"FuzzAgent: Multi-Agent System for Evolutionary Library Fuzzing","created":"2026-05-14","cited_by_count":0,"area":"agents"},{"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":"2606.03142","title":"Disentangling Visual and Factual Correctness in LVLMs' Visualization Literacy","created":"2026-06-02","cited_by_count":0,"area":"mllm"},{"id":"2606.04612","title":"Hybrid Adversarial Defence for Natural Language Understanding Tasks","created":"2026-06-03","cited_by_count":0,"area":"safety"},{"id":"2606.06674","title":"What Do People Actually Want From AI? Mapping Preference Plurality","created":"2026-06-04","cited_by_count":0,"area":"alignment"},{"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":"2606.31033","title":"CORTEX: Token-Level Hallucination Detection in RAG via Comparative Internal Representations","created":"2026-06-30","cited_by_count":0,"area":"rag"},{"id":"2607.14499","title":"Contextualized Evaluation of Vision Language Models through Dynamic, Multi-turn Interactions","created":"2026-07-16","cited_by_count":0,"area":"mllm"},{"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":"2608.04286","title":"Eliciting Intrinsic Hallucinations in LLMs via Semantically Equivalent Adversarial Attacks","created":"2026-08-04","cited_by_count":0,"area":"rag"},{"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":"2609.28570","title":"DEEPO: Dual-Entropy Enhanced Policy Optimization for Hallucination in MLLMs","created":"2026-09-23","cited_by_count":0,"area":"lr"},{"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},{"id":"2610.20419","title":"Analyzing performance of Retrieval Augmented Generation models for Question Answering Tasks","created":"2026-10-14","cited_by_count":0,"area":"rag"}],"next_cursor":null}