{"total":35,"rows":[{"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":"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":"2603.00539","title":"Are LLMs Reliable Code Reviewers? Systematic Overcorrection in Requirement Conformance Judgement","created":"2026-02-28","cited_by_count":4,"area":null},{"id":"2605.10186","title":"LegalCiteBench: Evaluating Citation Reliability in Legal Language Models","created":"2026-05-11","cited_by_count":3,"area":null},{"id":"2605.17007","title":"HalluScore: Large Language Model Hallucination Question Answering Benchmark","created":"2026-05-16","cited_by_count":2,"area":null},{"id":"2607.04029","title":"CrossHallu: Do Hallucination Signals Generalize Across Languages and Domains in Large Language Model's Internals?","created":"2026-07-04","cited_by_count":2,"area":null},{"id":"2607.20219","title":"HalluTruthQA: A Fine-Grained Benchmark for Hallucination Detection, Localization, and Explanation in Arabic Question Answering","created":"2026-07-22","cited_by_count":2,"area":null},{"id":"2602.13224","title":"A Geometric Taxonomy of Hallucinations in LLMs","created":"2026-01-26","cited_by_count":1,"area":null},{"id":"2603.25898","title":"On Integrating Resilience and Human Oversight into LLM-Assisted Modeling Workflows for Digital Twins","created":"2026-03-26","cited_by_count":1,"area":null},{"id":"2605.10125","title":"Useful for Exploration, Risky for Precision: Evaluating AI Tools in Academic Research","created":"2026-05-11","cited_by_count":1,"area":null},{"id":"2606.07537","title":"From Architecture to Output: Structural Origins of Hallucination in Large Language Models and the Amplifying Role of Data","created":"2026-04-29","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":"2608.03966","title":"HalluTruthQA-4K: A Fine-Grained Corpus and Annotation Process for Arabic Hallucination Detection and Truth Verification","created":"2026-08-04","cited_by_count":1,"area":null},{"id":"2608.26171","title":"Mitigating Fabrication in Multi-Stage LLM Pipelines for Hiring: An Empirical Evaluation of Prompt Guardrails and Human-in-the-Loop Checkpoints","created":"2026-07-22","cited_by_count":1,"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":"2603.23514","title":"DepthCharge: A Domain-Agnostic Framework for Measuring Depth-Dependent Knowledge in Large Language Models","created":"2026-03-05","cited_by_count":0,"area":null},{"id":"2604.00014","title":"Disentangling Prompt Element Level Risk Factors for Hallucinations and Omissions in Mental Health LLM Responses","created":"2026-03-10","cited_by_count":0,"area":null},{"id":"2604.10697","title":"Attention Sinks as Internal Signals for Hallucination Detection in Large Language Models","created":"2026-04-12","cited_by_count":0,"area":null},{"id":"2605.27394","title":"Human-AI Collaboration for Estimating Scientific Replicability","created":"2026-04-19","cited_by_count":0,"area":null},{"id":"2605.30459","title":"Can LLM Teams Play What? Where? When?","created":"2026-05-28","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":"2606.08658","title":"Extending Ontologies: From Dense Embeddings to Hybrid Quantum-Fuzzy Systems","created":"2026-06-07","cited_by_count":0,"area":null},{"id":"2606.15893","title":"BALTO: Balanced Token-Level Policy Optimization for Hallucination Mitigation","created":"2026-06-14","cited_by_count":0,"area":null},{"id":"2606.21595","title":"Per-Entity Bias Mapping for AI Visibility: Why Brand Mentions Require Entity-Specific Calibration","created":"2026-06-19","cited_by_count":0,"area":null},{"id":"2607.09324","title":"Letting the Data Speak: Extracting Keywords from Crowdsourced Collections with AI","created":"2026-07-10","cited_by_count":0,"area":null},{"id":"2607.23927","title":"Reality Monitoring in Large Language Models: Self-Knowledge That Transforms with Conversation Memory","created":"2026-07-27","cited_by_count":0,"area":null},{"id":"2608.00006","title":"Enhancing LLMs with Context-Specific Knowledge for Mitigating Misinformation in SMEs: A RAG-based Modeling and Analysis","created":"2026-06-08","cited_by_count":0,"area":null},{"id":"2608.03720","title":"Detecting Hallucinations and Recovering Verified Answers in Arabic Islamic Question Answering","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2608.23640","title":"Auditing the Synthetic Memoir: Measuring Scene-Level Confabulation in LLM-Generated Autobiography Against the Documented Record of the Life It Describes","created":"2026-08-23","cited_by_count":0,"area":null},{"id":"2609.05423","title":"Seeing Without Understanding: Large Language Model Evaluation of Mobile User Interface Quality, Failure Taxonomy, and Architectural Explanation","created":"2026-05-24","cited_by_count":0,"area":null},{"id":"2609.15745","title":"Look Before You Leap: Factual Decoding with Internal Attribution Signals","created":"2026-09-14","cited_by_count":0,"area":null},{"id":"2609.26927","title":"Building Socio-Affective Artificial Intelligence for Interactive Multi-Agent Simulations","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2609.35308","title":"Epistemic Policy Divergence in Multi-Turn LLM Contamination: A Protocol-Gradient Investigation","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.38355","title":"Halluscoring 2026: The first shared task on llms hallucination detection and answer verification","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}