{"total":51,"rows":[{"id":"2403.08319","title":"Knowledge Conflicts for LLMs: A Survey","created":"2024-03-13","cited_by_count":283,"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":"2310.06356","title":"A Semantic Invariant Robust Watermark for Large Language Models","created":"2023-10-10","cited_by_count":112,"area":"safety"},{"id":"2401.06853","title":"Large Language Models Can Learn Temporal Reasoning","created":"2024-01-12","cited_by_count":111,"area":"lr"},{"id":"2402.11163","title":"KG-Agent: An Efficient Autonomous Agent Framework for Complex Reasoning over Knowledge Graph","created":"2024-02-17","cited_by_count":93,"area":"lr"},{"id":"2406.09170","title":"Test of Time: A Benchmark for Evaluating LLMs on Temporal Reasoning","created":"2024-06-13","cited_by_count":88,"area":"lr"},{"id":"2312.15710","title":"Alleviating Hallucinations of Large Language Models through Induced Hallucinations","created":"2023-12-25","cited_by_count":79,"area":null},{"id":"2402.03190","title":"Unified Hallucination Detection for Multimodal Large Language Models","created":"2024-02-05","cited_by_count":75,"area":"mllm"},{"id":"2503.03750","title":"The MASK Benchmark: Disentangling Honesty From Accuracy in AI Systems","created":"2025-03-05","cited_by_count":72,"area":"agents"},{"id":"2405.12063","title":"CLAMBER: A Benchmark of Identifying and Clarifying Ambiguous Information Needs in Large Language Models","created":"2024-05-20","cited_by_count":54,"area":null},{"id":"2405.07001","title":"ChartInsights: Evaluating Multimodal Large Language Models for Low-Level Chart Question Answering","created":"2024-05-11","cited_by_count":50,"area":"mllm"},{"id":"2402.16499","title":"LLMArena: Assessing Capabilities of Large Language Models in Dynamic Multi-Agent Environments","created":"2024-02-26","cited_by_count":36,"area":"agents"},{"id":"2408.09429","title":"Reefknot: A Comprehensive Benchmark for Relation Hallucination Evaluation, Analysis and Mitigation in Multimodal Large Language Models","created":"2024-08-18","cited_by_count":30,"area":"mllm"},{"id":"2310.12086","title":"FactCHD: Benchmarking Fact-Conflicting Hallucination Detection","created":"2023-10-18","cited_by_count":29,"area":null},{"id":"2311.08398","title":"Are Large Language Models Temporally Grounded?","created":"2023-11-14","cited_by_count":27,"area":null},{"id":"2402.16063","title":"Citation-Enhanced Generation for LLM-based Chatbots","created":"2024-02-25","cited_by_count":25,"area":null},{"id":"2407.02351","title":"Generative Large Language Models in Automated Fact-Checking: A Survey","created":"2024-07-02","cited_by_count":19,"area":null},{"id":"2408.12325","title":"Improving Factuality in Large Language Models via Decoding-Time Hallucinatory and Truthful Comparators","created":"2024-08-22","cited_by_count":19,"area":null},{"id":"2502.17924","title":"FACT-AUDIT: An Adaptive Multi-Agent Framework for Dynamic Fact-Checking Evaluation of Large Language Models","created":"2025-02-25","cited_by_count":19,"area":"agents"},{"id":"2401.15498","title":"Do We Need Language-Specific Fact-Checking Models? The Case of Chinese","created":"2024-01-27","cited_by_count":15,"area":null},{"id":"2406.11288","title":"MFC-Bench: Benchmarking Multimodal Fact-Checking with Large Vision-Language Models","created":"2024-06-17","cited_by_count":15,"area":"lr"},{"id":"2403.03627","title":"Multimodal Large Language Models to Support Real-World Fact-Checking","created":"2024-03-06","cited_by_count":13,"area":"mllm"},{"id":"2402.08277","title":"Towards Faithful and Robust LLM Specialists for Evidence-Based Question-Answering","created":"2024-02-13","cited_by_count":11,"area":null},{"id":"2406.10318","title":"Creating a Lens of Chinese Culture: A Multimodal Dataset for Chinese Pun Rebus Art Understanding","created":"2024-06-14","cited_by_count":11,"area":"mllm"},{"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":"2402.10735","title":"Assessing the Reasoning Capabilities of LLMs in the context of Evidence-based Claim Verification","created":"2024-02-16","cited_by_count":9,"area":"lr"},{"id":"2402.12411","title":"Deep Structural Knowledge Exploitation and Synergy for Estimating Node Importance Value on Heterogeneous Information Networks","created":"2024-02-19","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":"2403.12077","title":"Evaluating Robustness of Generative Search Engine on Adversarial Factual Questions","created":"2024-02-25","cited_by_count":9,"area":"rag"},{"id":"2506.12538","title":"RealFactBench: A Benchmark for Evaluating Large Language Models in Real-World Fact-Checking","created":"2025-06-14","cited_by_count":9,"area":null},{"id":"2510.08211","title":"LLMs Deceive Unintentionally: Emergent Misalignment in Dishonesty from Misaligned Samples to Biased Human-AI Interactions","created":"2025-10-09","cited_by_count":8,"area":null},{"id":"2503.01630","title":"Machine Learners Should Acknowledge the Legal Implications of Large Language Models as Personal Data","created":"2025-03-03","cited_by_count":5,"area":null},{"id":"2407.05434","title":"LTLBench: Towards Benchmarks for Evaluating Temporal Reasoning in Large Language Models","created":"2024-07-07","cited_by_count":4,"area":"lr"},{"id":"2506.03490","title":"Beyond Memorization: A Rigorous Evaluation Framework for Medical Knowledge Editing","created":"2025-06-04","cited_by_count":4,"area":null},{"id":"2407.12425","title":"Navigating the Noisy Crowd: Finding Key Information for Claim Verification","created":"2024-07-17","cited_by_count":3,"area":null},{"id":"2411.04448","title":"Gradient Localization Improves Lifelong Pretraining of Language Models","created":"2024-11-07","cited_by_count":3,"area":null},{"id":"2507.20700","title":"When Scale Meets Diversity: Evaluating Language Models on Fine-Grained Multilingual Claim Verification","created":"2025-07-28","cited_by_count":3,"area":null},{"id":"2601.02669","title":"Towards Comprehensive Stage-wise Benchmarking of Large Language Models in Fact-Checking","created":"2026-01-06","cited_by_count":3,"area":null},{"id":"2601.11047","title":"CoG: Controllable Graph Reasoning via Relational Blueprints and Failure-Aware Refinement over Knowledge Graphs","created":"2026-01-16","cited_by_count":3,"area":"lr"},{"id":"2504.06219","title":"Can Performant LLMs Be Ethical? Quantifying the Impact of Web Crawling Opt-Outs","created":"2025-04-08","cited_by_count":2,"area":null},{"id":"2504.19472","title":"Conflicts in Texts: Data, Implications and Challenges","created":"2025-04-28","cited_by_count":2,"area":null},{"id":"2508.16267","title":"From Confidence to Collapse in LLM Factual Robustness","created":"2025-08-22","cited_by_count":2,"area":null},{"id":"2410.10303","title":"A Comparative Study of Translation Bias and Accuracy in Multilingual Large Language Models for Cross-Language Claim Verification","created":"2024-10-14","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":"2504.03165","title":"Efficient Dynamic Clustering-Based Document Compression for Retrieval-Augmented-Generation","created":"2025-04-04","cited_by_count":1,"area":"rag"},{"id":"2510.20878","title":"HA-RAG: Hotness-Aware RAG Acceleration via Mixed Precision and Data Placement","created":"2025-10-23","cited_by_count":0,"area":"rag"},{"id":"2601.01156","title":"DHI: Leveraging Diverse Hallucination Induction for Enhanced Contrastive Factuality Control in Large Language Models","created":"2026-01-03","cited_by_count":0,"area":null},{"id":"2604.14172","title":"Tug-of-War within A Decade: Conflict Resolution in Vulnerability Analysis via Teacher-Guided Retrieval-Augmented Generations","created":"2026-03-25","cited_by_count":0,"area":"rag"},{"id":"2609.12678","title":"Detecting and Explaining Fake News Short Videos with Multimodal Content and Real-World Evidence","created":"2026-09-11","cited_by_count":0,"area":null},{"id":"2609.36515","title":"Large-scale factor analysis shows machine intelligence is only partially interpretable","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.14073","title":"Is the Future Predictable? Modeling Future Predictability for Reliable Temporal Reasoning","created":"2026-10-08","cited_by_count":0,"area":"lr"}],"next_cursor":null}