{"total":116,"rows":[{"id":"2311.05232","title":"A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions","created":"2023-11-09","cited_by_count":1601,"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":"2411.04368","title":"Measuring short-form factuality in large language models","created":"2024-11-07","cited_by_count":373,"area":null},{"id":"2309.11495","title":"Chain-of-Verification Reduces Hallucination in Large Language Models","created":"2023-09-20","cited_by_count":324,"area":null},{"id":"2401.00396","title":"RAGTruth: A Hallucination Corpus for Developing Trustworthy Retrieval-Augmented Language Models","created":"2023-12-31","cited_by_count":283,"area":"rag"},{"id":"2403.08319","title":"Knowledge Conflicts for LLMs: A Survey","created":"2024-03-13","cited_by_count":283,"area":null},{"id":"2404.10719","title":"Is DPO Superior to PPO for LLM Alignment? A Comprehensive Study","created":"2024-04-16","cited_by_count":262,"area":"alignment"},{"id":"2406.15927","title":"Semantic Entropy Probes: Robust and Cheap Hallucination Detection in LLMs","created":"2024-06-22","cited_by_count":259,"area":null},{"id":"2311.08401","title":"Fine-tuning Language Models for Factuality","created":"2023-11-14","cited_by_count":221,"area":null},{"id":"2509.04664","title":"Why Language Models Hallucinate","created":"2025-09-04","cited_by_count":220,"area":null},{"id":"2309.13788","title":"Can LLM-Generated Misinformation Be Detected?","created":"2023-09-25","cited_by_count":177,"area":null},{"id":"2405.20362","title":"Hallucination-Free? Assessing the Reliability of Leading AI Legal Research Tools","created":"2024-05-30","cited_by_count":176,"area":null},{"id":"2401.01301","title":"Large Legal Fictions: Profiling Legal Hallucinations in Large Language Models","created":"2024-01-02","cited_by_count":150,"area":null},{"id":"2310.04988","title":"The Troubling Emergence of Hallucination in Large Language Models -- An Extensive Definition, Quantification, and Prescriptive Remediations","created":"2023-10-08","cited_by_count":131,"area":null},{"id":"2311.14648","title":"Calibrated Language Models Must Hallucinate","created":"2023-11-24","cited_by_count":115,"area":null},{"id":"2405.20974","title":"SaySelf: Teaching LLMs to Express Confidence with Self-Reflective Rationales","created":"2024-05-31","cited_by_count":105,"area":null},{"id":"2409.17504","title":"HaloScope: Harnessing Unlabeled LLM Generations for Hallucination Detection","created":"2024-09-26","cited_by_count":99,"area":null},{"id":"2311.00059","title":"The Generative AI Paradox: \"What It Can Create, It May Not Understand\"","created":"2023-10-31","cited_by_count":98,"area":null},{"id":"2309.07852","title":"ExpertQA: Expert-Curated Questions and Attributed Answers","created":"2023-09-14","cited_by_count":97,"area":null},{"id":"2401.13136","title":"The Language Barrier: Dissecting Safety Challenges of LLMs in Multilingual Contexts","created":"2024-01-23","cited_by_count":94,"area":"alignment"},{"id":"2409.20550","title":"LLM Hallucinations in Practical Code Generation: Phenomena, Mechanism, and Mitigation","created":"2024-09-30","cited_by_count":93,"area":null},{"id":"2311.01740","title":"SAC3: Reliable Hallucination Detection in Black-Box Language Models via Semantic-aware Cross-check Consistency","created":"2023-11-03","cited_by_count":90,"area":null},{"id":"2310.08559","title":"Phenomenal Yet Puzzling: Testing Inductive Reasoning Capabilities of Language Models with Hypothesis Refinement","created":"2023-10-12","cited_by_count":89,"area":"lr"},{"id":"2401.03205","title":"The Dawn After the Dark: An Empirical Study on Factuality Hallucination in Large Language Models","created":"2024-01-06","cited_by_count":88,"area":null},{"id":"2403.05612","title":"Unfamiliar Finetuning Examples Control How Language Models Hallucinate","created":"2024-03-08","cited_by_count":87,"area":"alignment"},{"id":"2309.06794","title":"Cognitive Mirage: A Review of Hallucinations in Large Language Models","created":"2023-09-13","cited_by_count":84,"area":null},{"id":"2311.03731","title":"A Survey of Large Language Models Attribution","created":"2023-11-07","cited_by_count":71,"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":"2310.17918","title":"Knowing What LLMs DO NOT Know: A Simple Yet Effective Self-Detection Method","created":"2023-10-27","cited_by_count":51,"area":null},{"id":"2403.08946","title":"Usable XAI: 10 Strategies Towards Exploiting Explainability in the LLM Era","created":"2024-03-13","cited_by_count":46,"area":null},{"id":"2401.15449","title":"Learning to Trust Your Feelings: Leveraging Self-awareness in LLMs for Hallucination Mitigation","created":"2024-01-27","cited_by_count":44,"area":null},{"id":"2404.17287","title":"When to Trust LLMs: Aligning Confidence with Response Quality","created":"2024-04-26","cited_by_count":43,"area":null},{"id":"2403.09972","title":"Think Twice Before Trusting: Self-Detection for Large Language Models through Comprehensive Answer Reflection","created":"2024-03-15","cited_by_count":41,"area":"lr"},{"id":"2410.23856","title":"Can Language Models Perform Robust Reasoning in Chain-of-thought Prompting with Noisy Rationales?","created":"2024-10-31","cited_by_count":41,"area":"lr"},{"id":"2311.09114","title":"Ever: Mitigating Hallucination in Large Language Models through Real-Time Verification and Rectification","created":"2023-11-15","cited_by_count":38,"area":null},{"id":"2402.10958","title":"Relative Preference Optimization: Enhancing LLM Alignment through Contrasting Responses across Identical and Diverse Prompts","created":"2024-02-12","cited_by_count":36,"area":"alignment"},{"id":"2311.09198","title":"Never Lost in the Middle: Mastering Long-Context Question Answering with Position-Agnostic Decompositional Training","created":"2023-11-15","cited_by_count":32,"area":null},{"id":"2409.14586","title":"Backtracking Improves Generation Safety","created":"2024-09-22","cited_by_count":32,"area":"alignment"},{"id":"2404.01019","title":"Source-Aware Training Enables Knowledge Attribution in Language Models","created":"2024-04-01","cited_by_count":30,"area":null},{"id":"2406.12053","title":"InternalInspector $I^2$: Robust Confidence Estimation in LLMs through Internal States","created":"2024-06-17","cited_by_count":30,"area":null},{"id":"2402.10612","title":"Rowen: Adaptive Retrieval-Augmented Generation for Hallucination Mitigation in LLMs","created":"2024-02-16","cited_by_count":27,"area":"rag"},{"id":"2403.04307","title":"HaluEval-Wild: Evaluating Hallucinations of Language Models in the Wild","created":"2024-03-07","cited_by_count":27,"area":null},{"id":"2502.15844","title":"Hallucination Detection in Large Language Models with Metamorphic Relations","created":"2025-02-20","cited_by_count":24,"area":null},{"id":"2502.15845","title":"Verify when Uncertain: Beyond Self-Consistency in Black Box Hallucination Detection","created":"2025-02-20","cited_by_count":18,"area":"lr"},{"id":"2504.19254","title":"Uncertainty Quantification for Language Models: A Suite of Black-Box, White-Box, LLM Judge, and Ensemble Scorers","created":"2025-04-27","cited_by_count":18,"area":null},{"id":"2406.10218","title":"Semantic Membership Inference Attack against Large Language Models","created":"2024-06-14","cited_by_count":17,"area":"safety"},{"id":"2412.13612","title":"Large Language Models for Automated Literature Review: An Evaluation of Reference Generation, Abstract Writing, and Review Composition","created":"2024-12-18","cited_by_count":17,"area":null},{"id":"2309.05217","title":"Quantifying and Attributing the Hallucination of Large Language Models via Association Analysis","created":"2023-09-11","cited_by_count":15,"area":null},{"id":"2310.03331","title":"Fine-tune Language Models to Approximate Unbiased In-context Learning","created":"2023-10-05","cited_by_count":12,"area":null},{"id":"2402.04957","title":"Reconfidencing LLMs from the Grouping Loss Perspective","created":"2024-02-07","cited_by_count":11,"area":null},{"id":"2406.07735","title":"REAL Sampling: Boosting Factuality and Diversity of Open-Ended Generation via Asymptotic Entropy","created":"2024-06-11","cited_by_count":11,"area":null},{"id":"2411.18659","title":"DHCP: Detecting Hallucinations by Cross-modal Attention Pattern in Large Vision-Language Models","created":"2024-11-27","cited_by_count":11,"area":"mllm"},{"id":"2310.00259","title":"AutoHall: Automated Factuality Hallucination Dataset Generation for Large Language Models","created":"2023-09-30","cited_by_count":10,"area":null},{"id":"2405.13131","title":"Atomic Self-Consistency for Better Long Form Generations","created":"2024-05-21","cited_by_count":10,"area":"lr"},{"id":"2412.17056","title":"The HalluRAG Dataset: Detecting Closed-Domain Hallucinations in RAG Applications Using an LLM's Internal States","created":"2024-12-22","cited_by_count":10,"area":null},{"id":"2504.02767","title":"How Deep Do Large Language Models Internalize Scientific Literature and Citation Practices?","created":"2025-04-03","cited_by_count":10,"area":null},{"id":"2602.01031","title":"HalluHard: A Hard Multi-Turn Hallucination Benchmark","created":"2026-02-01","cited_by_count":9,"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":"2404.07060","title":"Groundedness in Retrieval-augmented Long-form Generation: An Empirical Study","created":"2024-04-10","cited_by_count":7,"area":"rag"},{"id":"2405.20830","title":"Self-Augmented Preference Optimization: Off-Policy Paradigms for Language Model Alignment","created":"2024-05-31","cited_by_count":7,"area":"alignment"},{"id":"2410.20199","title":"Rethinking the Uncertainty: A Critical Review and Analysis in the Era of Large Language Models","created":"2024-10-26","cited_by_count":6,"area":"lr"},{"id":"2502.20847","title":"Gradient Imbalance in Direct Preference Optimization","created":"2025-02-28","cited_by_count":6,"area":"alignment"},{"id":"2506.15065","title":"HEAL: An Empirical Study on Hallucinations in Embodied Agents Driven by Large Language Models","created":"2025-06-18","cited_by_count":6,"area":"agents"},{"id":"2510.01782","title":"Can LLMs Refuse Questions They Do Not Know? Measuring Knowledge-Aware Refusal in Factual Tasks","created":"2025-10-02","cited_by_count":6,"area":null},{"id":"2601.05866","title":"FACTUM: Mechanistic Detection of Citation Hallucination in Long-Form RAG","created":"2026-01-09","cited_by_count":6,"area":"rag"},{"id":"2604.03173","title":"Detecting and Correcting Reference Hallucinations in Commercial LLMs and Deep Research Agents","created":"2026-04-03","cited_by_count":6,"area":"agents"},{"id":"2406.00975","title":"Luna: An Evaluation Foundation Model to Catch Language Model Hallucinations with High Accuracy and Low Cost","created":"2024-06-03","cited_by_count":5,"area":null},{"id":"2410.14748","title":"ETF: An Entity Tracing Framework for Hallucination Detection in Code Summaries","created":"2024-10-17","cited_by_count":5,"area":null},{"id":"2503.20504","title":"UniVRSE: Unified Vision-conditioned Response Semantic Entropy for Hallucination Detection in Medical Vision-Language Models","created":"2025-03-26","cited_by_count":5,"area":"mllm"},{"id":"2509.00117","title":"Embodied AI: Emerging Risks and Opportunities for Policy Action","created":"2025-08-28","cited_by_count":5,"area":null},{"id":"2602.15871","title":"CheckIfExist: Detecting Citation Hallucinations in the Era of AI-Generated Content","created":"2026-01-27","cited_by_count":5,"area":null},{"id":"2603.13768","title":"Causal Tracing of Audio-Text Fusion in Large Audio Language Models","created":"2026-03-14","cited_by_count":5,"area":null},{"id":"2604.18874","title":"How Adversarial Environments Mislead Agentic AI?","created":"2026-04-20","cited_by_count":5,"area":"agents"},{"id":"2308.11189","title":"Diversity Measures: Domain-Independent Proxies for Failure in Language Model Queries","created":"2023-08-22","cited_by_count":4,"area":null},{"id":"2408.07852","title":"Training Language Models on the Knowledge Graph: Insights on Hallucinations and Their Detectability","created":"2024-08-14","cited_by_count":4,"area":null},{"id":"2411.01022","title":"Provenance: A Light-weight Fact-checker for Retrieval Augmented LLM Generation Output","created":"2024-11-01","cited_by_count":4,"area":"rag"},{"id":"2504.18346","title":"Comparing Uncertainty Measurement and Mitigation Methods for Large Language Models: A Systematic Review","created":"2025-04-25","cited_by_count":4,"area":null},{"id":"2507.20836","title":"First Hallucination Tokens Are Different from Conditional Ones","created":"2025-07-28","cited_by_count":4,"area":null},{"id":"2508.19111","title":"Do LVLMs Know What They Know? A Systematic Study of Knowledge Boundary Perception in LVLMs","created":"2025-08-26","cited_by_count":4,"area":"mllm"},{"id":"2405.10128","title":"Red Teaming Language Models for Processing Contradictory Dialogues","created":"2024-05-16","cited_by_count":3,"area":"safety"},{"id":"2407.01122","title":"Calibrated Large Language Models for Binary Question Answering","created":"2024-07-01","cited_by_count":3,"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":"2511.07483","title":"Beyond Correctness: Confidence-Aware Reward Modeling for Enhancing Large Language Model Reasoning","created":"2025-11-09","cited_by_count":3,"area":"lr"},{"id":"2603.07287","title":"Do Deployment Constraints Make LLMs Hallucinate Citations? An Empirical Study across Four Models and Five Prompting Regimes","created":"2026-03-07","cited_by_count":3,"area":null},{"id":"2404.15157","title":"FASTTRACK: Fast and Accurate Fact Tracing for LLMs","created":"2024-04-22","cited_by_count":2,"area":null},{"id":"2412.05967","title":"Language hooks: a modular framework for augmenting LLM reasoning that decouples tool usage from the model and its prompt","created":"2024-12-08","cited_by_count":2,"area":"lr"},{"id":"2506.02696","title":"Shaking to Reveal: Perturbation-Based Detection of LLM Hallucinations","created":"2025-06-03","cited_by_count":2,"area":null},{"id":"2506.17585","title":"Cite Pretrain: Retrieval-Free Knowledge Attribution for Large Language Models","created":"2025-06-21","cited_by_count":2,"area":null},{"id":"2507.22720","title":"Investigating Hallucination in Conversations for Low Resource Languages","created":"2025-07-30","cited_by_count":2,"area":null},{"id":"2511.04683","title":"AI-Powered Citation Auditing: A Zero-Assumption Protocol for Systematic Reference Verification in Academic Research","created":"2025-10-17","cited_by_count":2,"area":null},{"id":"2604.03159","title":"BibTeX Citation Errors in Scientific Publishing Agents: Evaluation and Mitigation","created":"2026-04-03","cited_by_count":2,"area":null},{"id":"2405.07436","title":"Can Language Models Explain Their Own Classification Behavior?","created":"2024-05-13","cited_by_count":1,"area":null},{"id":"2407.12846","title":"Identifying the Source of Generation for Large Language Models","created":"2024-07-05","cited_by_count":1,"area":null},{"id":"2411.03300","title":"VERITAS: A Unified Approach to Reliability Evaluation","created":"2024-11-05","cited_by_count":1,"area":null},{"id":"2502.08666","title":"Hallucination, Monofacts, and Miscalibration: An Empirical Investigation","created":"2025-02-11","cited_by_count":1,"area":null},{"id":"2505.09039","title":"Atomic Consistency Preference Optimization for Long-Form Question Answering","created":"2025-05-14","cited_by_count":1,"area":"alignment"},{"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":"2604.15945","title":"RAGognizer: Hallucination-Aware Fine-Tuning via Detection Head Integration","created":"2026-04-17","cited_by_count":1,"area":"rag"},{"id":"2605.10862","title":"RUBEN: Rule-Based Explanations for Retrieval-Augmented LLM Systems","created":"2026-05-11","cited_by_count":1,"area":"rag"},{"id":"2607.00738","title":"Phantom References: Hallucinated Citations That Survive Peer Review at Top-Tier Conferences","created":"2026-07-01","cited_by_count":1,"area":null}],"next_cursor":"100"}