{"total":121,"rows":[{"id":"2309.11495","title":"Chain-of-Verification Reduces Hallucination in Large Language Models","created":"2023-09-20","cited_by_count":324,"area":null},{"id":"2309.14316","title":"Physics of Language Models: Part 3.1, Knowledge Storage and Extraction","created":"2023-09-25","cited_by_count":270,"area":null},{"id":"2509.04664","title":"Why Language Models Hallucinate","created":"2025-09-04","cited_by_count":220,"area":null},{"id":"2310.07521","title":"Survey on Factuality in Large Language Models: Knowledge, Retrieval and Domain-Specificity","created":"2023-10-11","cited_by_count":206,"area":null},{"id":"2309.14402","title":"Physics of Language Models: Part 3.2, Knowledge Manipulation","created":"2023-09-25","cited_by_count":143,"area":null},{"id":"2309.15098","title":"Attention Satisfies: A Constraint-Satisfaction Lens on Factual Errors of Language Models","created":"2023-09-26","cited_by_count":67,"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":"2404.13207","title":"STaRK: Benchmarking LLM Retrieval on Textual and Relational Knowledge Bases","created":"2024-04-19","cited_by_count":55,"area":null},{"id":"2402.05391","title":"Knowledge Graphs Meet Multi-Modal Learning: A Comprehensive Survey","created":"2024-02-08","cited_by_count":53,"area":null},{"id":"2310.00935","title":"Resolving Knowledge Conflicts in Large Language Models","created":"2023-10-02","cited_by_count":50,"area":null},{"id":"2310.06671","title":"Making Large Language Models Perform Better in Knowledge Graph Completion","created":"2023-10-10","cited_by_count":48,"area":null},{"id":"2311.09533","title":"Effective Large Language Model Adaptation for Improved Grounding and Citation Generation","created":"2023-11-16","cited_by_count":45,"area":null},{"id":"2503.05142","title":"RocketEval: Efficient Automated LLM Evaluation via Grading Checklist","created":"2025-03-07","cited_by_count":39,"area":null},{"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":"2311.08993","title":"When does In-context Learning Fall Short and Why? A Study on Specification-Heavy Tasks","created":"2023-11-15","cited_by_count":37,"area":null},{"id":"2403.02253","title":"KnowPhish: Large Language Models Meet Multimodal Knowledge Graphs for Enhancing Reference-Based Phishing Detection","created":"2024-03-04","cited_by_count":33,"area":null},{"id":"2402.06544","title":"Calibrating Long-form Generations from Large Language Models","created":"2024-02-09","cited_by_count":32,"area":null},{"id":"2310.11958","title":"Emptying the Ocean with a Spoon: Should We Edit Models?","created":"2023-10-18","cited_by_count":27,"area":null},{"id":"2312.11713","title":"Indoor and Outdoor 3D Scene Graph Generation via Language-Enabled Spatial Ontologies","created":"2023-12-18","cited_by_count":25,"area":null},{"id":"2404.08700","title":"DyKnow: Dynamically Verifying Time-Sensitive Factual Knowledge in LLMs","created":"2024-04-10","cited_by_count":24,"area":null},{"id":"2402.07016","title":"REALM: RAG-Driven Enhancement of Multimodal Electronic Health Records Analysis via Large Language Models","created":"2024-02-10","cited_by_count":23,"area":null},{"id":"2505.23628","title":"AutoSchemaKG: Autonomous Knowledge Graph Construction through Dynamic Schema Induction from Web-Scale Corpora","created":"2025-05-29","cited_by_count":23,"area":null},{"id":"2412.17032","title":"MINTQA: A Multi-Hop Question Answering Benchmark for Evaluating LLMs on New and Tail Knowledge","created":"2024-12-22","cited_by_count":20,"area":null},{"id":"2402.13492","title":"Retrieval Helps or Hurts? A Deeper Dive into the Efficacy of Retrieval Augmentation to Language Models","created":"2024-02-21","cited_by_count":19,"area":null},{"id":"2406.11131","title":"Are Large Language Models a Good Replacement of Taxonomies?","created":"2024-06-17","cited_by_count":19,"area":null},{"id":"2312.11518","title":"User Modeling in the Era of Large Language Models: Current Research and Future Directions","created":"2023-12-11","cited_by_count":18,"area":null},{"id":"2402.01729","title":"Contextualization Distillation from Large Language Model for Knowledge Graph Completion","created":"2024-01-28","cited_by_count":18,"area":null},{"id":"2311.09174","title":"AbsPyramid: Benchmarking the Abstraction Ability of Language Models with a Unified Entailment Graph","created":"2023-11-15","cited_by_count":17,"area":null},{"id":"2404.14809","title":"A Survey of Large Language Models on Generative Graph Analytics: Query, Learning, and Applications","created":"2024-04-23","cited_by_count":17,"area":null},{"id":"2505.18091","title":"Data Mixing Can Induce Phase Transitions in Knowledge Acquisition","created":"2025-05-23","cited_by_count":16,"area":null},{"id":"2403.14358","title":"Exploring the Potential of Large Language Models in Graph Generation","created":"2024-03-21","cited_by_count":15,"area":null},{"id":"2412.16100","title":"Logical Consistency of Large Language Models in Fact-checking","created":"2024-12-20","cited_by_count":15,"area":null},{"id":"2504.12691","title":"Why and How LLMs Hallucinate: Connecting the Dots with Subsequence Associations","created":"2025-04-17","cited_by_count":15,"area":null},{"id":"2407.04693","title":"ANAH-v2: Scaling Analytical Hallucination Annotation of Large Language Models","created":"2024-07-05","cited_by_count":14,"area":null},{"id":"2409.03708","title":"RAG based Question-Answering for Contextual Response Prediction System","created":"2024-09-05","cited_by_count":14,"area":null},{"id":"2502.14502","title":"How Much Knowledge Can You Pack into a LoRA Adapter without Harming LLM?","created":"2025-02-20","cited_by_count":13,"area":null},{"id":"2508.09494","title":"Learning Facts at Scale with Active Reading","created":"2025-08-13","cited_by_count":13,"area":null},{"id":"2409.07497","title":"OneEdit: A Neural-Symbolic Collaboratively Knowledge Editing System","created":"2024-09-09","cited_by_count":12,"area":null},{"id":"2411.04920","title":"Enabling LLM Knowledge Analysis via Extensive Materialization","created":"2024-11-07","cited_by_count":12,"area":null},{"id":"2501.01124","title":"Graph2text or Graph2token: A Perspective of Large Language Models for Graph Learning","created":"2025-01-02","cited_by_count":12,"area":null},{"id":"2310.15511","title":"KITAB: Evaluating LLMs on Constraint Satisfaction for Information Retrieval","created":"2023-10-24","cited_by_count":11,"area":null},{"id":"2404.00942","title":"Evaluating the Factuality of Large Language Models using Large-Scale Knowledge Graphs","created":"2024-04-01","cited_by_count":10,"area":null},{"id":"2408.09070","title":"CodeTaxo: Enhancing Taxonomy Expansion with Limited Examples via Code Language Prompts","created":"2024-08-17","cited_by_count":10,"area":null},{"id":"2410.08133","title":"Assessing Episodic Memory in LLMs with Sequence Order Recall Tasks","created":"2024-10-10","cited_by_count":10,"area":null},{"id":"2412.20251","title":"ComparisonQA: Evaluating Factuality Robustness of LLMs Through Knowledge Frequency Control and Uncertainty","created":"2024-12-28","cited_by_count":10,"area":null},{"id":"2501.12774","title":"LLMs as Repositories of Factual Knowledge: Limitations and Solutions","created":"2025-01-22","cited_by_count":10,"area":null},{"id":"2508.17670","title":"CoCoA: Confidence and Context-Aware Adaptive Decoding for Resolving Knowledge Conflicts in Large Language Models","created":"2025-08-25","cited_by_count":10,"area":null},{"id":"2310.14771","title":"Evaluating the Knowledge Base Completion Potential of GPT","created":"2023-10-23","cited_by_count":9,"area":null},{"id":"2403.05266","title":"ERBench: An Entity-Relationship based Automatically Verifiable Hallucination Benchmark for Large Language Models","created":"2024-03-08","cited_by_count":9,"area":null},{"id":"2402.14858","title":"ChatEL: Entity Linking with Chatbots","created":"2024-02-20","cited_by_count":8,"area":null},{"id":"2404.16164","title":"Towards a Holistic Evaluation of LLMs on Factual Knowledge Recall","created":"2024-04-24","cited_by_count":8,"area":null},{"id":"2411.17375","title":"The Extractive-Abstractive Spectrum: Uncovering Verifiability Trade-offs in LLM Generations","created":"2024-11-26","cited_by_count":8,"area":null},{"id":"2402.06738","title":"EntGPT: Entity Linking with Generative Large Language Models","created":"2024-02-09","cited_by_count":7,"area":null},{"id":"2404.12957","title":"Towards Reliable Latent Knowledge Estimation in LLMs: Zero-Prompt Many-Shot Based Factual Knowledge Extraction","created":"2024-04-19","cited_by_count":7,"area":null},{"id":"2405.20315","title":"ANAH: Analytical Annotation of Hallucinations in Large Language Models","created":"2024-05-30","cited_by_count":7,"area":null},{"id":"2412.07420","title":"RAG-based Question Answering over Heterogeneous Data and Text","created":"2024-12-10","cited_by_count":7,"area":null},{"id":"2412.20331","title":"Mind the Data Gap: Bridging LLMs to Enterprise Data Integration","created":"2024-12-29","cited_by_count":7,"area":null},{"id":"2601.02391","title":"WearVox: An Egocentric Multichannel Voice Assistant Benchmark for Wearables","created":"2025-12-25","cited_by_count":7,"area":null},{"id":"2412.14847","title":"A Survey of RWKV","created":"2024-12-19","cited_by_count":6,"area":null},{"id":"2503.15990","title":"ECKGBench: Benchmarking Large Language Models in E-commerce Leveraging Knowledge Graph","created":"2025-03-20","cited_by_count":6,"area":null},{"id":"2310.11638","title":"Systematic Assessment of Factual Knowledge in Large Language Models","created":"2023-10-18","cited_by_count":5,"area":null},{"id":"2312.05276","title":"Making Large Language Models Better Knowledge Miners for Online Marketing with Progressive Prompting Augmentation","created":"2023-12-08","cited_by_count":5,"area":null},{"id":"2507.05740","title":"GPTKB v1.5: A Massive Knowledge Base for Exploring Factual LLM Knowledge","created":"2025-07-08","cited_by_count":5,"area":null},{"id":"2310.09725","title":"KGQuiz: Evaluating the Generalization of Encoded Knowledge in Large Language Models","created":"2023-10-15","cited_by_count":4,"area":null},{"id":"2311.06697","title":"Trusted Source Alignment in Large Language Models","created":"2023-11-12","cited_by_count":4,"area":null},{"id":"2401.06792","title":"LightHouse: A Survey of AGI Hallucination","created":"2024-01-08","cited_by_count":4,"area":null},{"id":"2412.12468","title":"Transferable and Forecastable User Targeting Foundation Model","created":"2024-12-17","cited_by_count":4,"area":null},{"id":"2401.00761","title":"Identifying the Achilles' Heel: An Iterative Method for Dynamically Uncovering Factual Errors in Large Language Models","created":"2024-01-01","cited_by_count":3,"area":null},{"id":"2401.14931","title":"Do LLMs Dream of Ontologies?","created":"2024-01-26","cited_by_count":3,"area":null},{"id":"2406.14828","title":"Word Matters: What Influences Domain Adaptation in Summarization?","created":"2024-06-21","cited_by_count":3,"area":null},{"id":"2409.15902","title":"Konstruktor: A Strong Baseline for Simple Knowledge Graph Question Answering","created":"2024-09-24","cited_by_count":3,"area":null},{"id":"2411.00686","title":"Latent Paraphrasing: Perturbation on Layers Improves Knowledge Injection in Language Models","created":"2024-11-01","cited_by_count":3,"area":null},{"id":"2501.18158","title":"Large Language Models for Cryptocurrency Transaction Analysis: A Bitcoin Case Study","created":"2025-01-30","cited_by_count":3,"area":null},{"id":"2508.06030","title":"Efficient Knowledge Probing of Large Language Models by Adapting Pre-trained Embeddings","created":"2025-08-08","cited_by_count":3,"area":null},{"id":"2510.07024","title":"Auditing a KB Elicitation of Frontier LLM Knowledge: A Multi-dimensional Analysis of GPTKB v1.5","created":"2025-10-08","cited_by_count":3,"area":null},{"id":"2510.16096","title":"Facts in Stats: Impacts of Pretraining Diversity on Language Model Generalization","created":"2025-10-17","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":"2511.20892","title":"Representation Interventions Enable Lifelong Knowledge Memory Control in LLMs","created":"2025-11-25","cited_by_count":3,"area":null},{"id":"2603.24080","title":"LLMpedia: A Transparent Framework to Materialize an LLM's Encyclopedic Knowledge at Scale","created":"2026-03-25","cited_by_count":3,"area":null},{"id":"2310.03376","title":"Procedural Text Mining with Large Language Models","created":"2023-10-05","cited_by_count":2,"area":null},{"id":"2310.19503","title":"Trust, Accountability, and Autonomy in Knowledge Graph-based AI for Self-determination","created":"2023-10-30","cited_by_count":2,"area":null},{"id":"2406.03855","title":"Performance of large language models in numerical vs. semantic medical knowledge: Benchmarking on evidence-based Q&As","created":"2024-06-06","cited_by_count":2,"area":null},{"id":"2411.03964","title":"What Really is Commonsense Knowledge?","created":"2024-11-06","cited_by_count":2,"area":null},{"id":"2501.19301","title":"Beyond checkmate: exploring the creative chokepoints in AI text","created":"2025-01-31","cited_by_count":2,"area":null},{"id":"2502.09168","title":"Musical Heritage Historical Entity Linking","created":"2025-02-13","cited_by_count":2,"area":null},{"id":"2502.14275","title":"Fact or Guesswork? Evaluating Large Language Models' Medical Knowledge with Structured One-Hop Judgments","created":"2025-02-20","cited_by_count":2,"area":null},{"id":"2608.20316","title":"Pandora's AI Model Routing Box: Efficient Allocation with Costly Value Estimation","created":"2026-08-20","cited_by_count":2,"area":null},{"id":"2408.07494","title":"QirK: Question Answering via Intermediate Representation on Knowledge Graphs","created":"2024-08-14","cited_by_count":1,"area":null},{"id":"2412.07965","title":"HalluCana: Fixing LLM Hallucination with A Canary Lookahead","created":"2024-12-10","cited_by_count":1,"area":null},{"id":"2412.17189","title":"Talking with Tables for Better LLM Factual Data Interactions","created":"2024-12-22","cited_by_count":1,"area":null},{"id":"2412.20846","title":"Are LLMs Really Not Knowledgeable? Mining the Submerged Knowledge in LLMs' Memory","created":"2024-12-30","cited_by_count":1,"area":null},{"id":"2502.01220","title":"Factual Knowledge in Language Models: Robustness and Anomalies under Simple Temporal Context Variations","created":"2025-02-03","cited_by_count":1,"area":null},{"id":"2505.12452","title":"Missing vs. Unused Knowledge Hypothesis for Language Model Bottlenecks in Patent Understanding","created":"2025-05-18","cited_by_count":1,"area":null},{"id":"2506.01312","title":"Growing Through Experience: Scaling Episodic Grounding in Language Models","created":"2025-06-02","cited_by_count":1,"area":null},{"id":"2602.01875","title":"PretrainRL: Alleviating Factuality Hallucination of Large Language Models at the Beginning","created":"2026-02-02","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":"2608.19670","title":"The Asymmetric Harms of LLM Compression","created":"2026-08-20","cited_by_count":1,"area":null},{"id":"2312.02317","title":"GNN2R: Weakly-Supervised Rationale-Providing Question Answering over Knowledge Graphs","created":"2023-12-04","cited_by_count":0,"area":null},{"id":"2404.10500","title":"When Emotional Stimuli meet Prompt Designing: An Auto-Prompt Graphical Paradigm","created":"2024-04-16","cited_by_count":0,"area":null},{"id":"2408.05365","title":"FiSTECH: Financial Style Transfer to Enhance Creativity without Hallucinations in LLMs","created":"2024-08-09","cited_by_count":0,"area":null}],"next_cursor":"100"}