{"total":126,"rows":[{"id":"2401.01286","title":"A Comprehensive Study of Knowledge Editing for Large Language Models","created":"2024-01-02","cited_by_count":163,"area":null},{"id":"2402.04253","title":"AnyTool: Self-Reflective, Hierarchical Agents for Large-Scale API Calls","created":"2024-02-06","cited_by_count":124,"area":"agents"},{"id":"2410.05983","title":"Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAG","created":"2024-10-08","cited_by_count":123,"area":"rag"},{"id":"2504.17550","title":"HalluLens: LLM Hallucination Benchmark","created":"2025-04-24","cited_by_count":92,"area":null},{"id":"2504.13079","title":"Retrieval-Augmented Generation with Conflicting Evidence","created":"2025-04-17","cited_by_count":63,"area":"rag"},{"id":"2407.12861","title":"CiteME: Can Language Models Accurately Cite Scientific Claims?","created":"2024-07-10","cited_by_count":48,"area":null},{"id":"2402.18059","title":"Token-Specific Watermarking with Enhanced Detectability and Semantic Coherence for Large Language Models","created":"2024-02-28","cited_by_count":34,"area":"safety"},{"id":"2406.17753","title":"Measuring and Benchmarking Large Language Models' Capabilities to Generate Persuasive Language","created":"2024-06-25","cited_by_count":31,"area":null},{"id":"2409.13724","title":"Logically Consistent Language Models via Neuro-Symbolic Integration","created":"2024-09-09","cited_by_count":30,"area":null},{"id":"2411.14258","title":"Knowledge Graphs, Large Language Models, and Hallucinations: An NLP Perspective","created":"2024-11-21","cited_by_count":29,"area":null},{"id":"2502.09083","title":"Show Me the Work: Fact-Checkers' Requirements for Explainable Automated Fact-Checking","created":"2025-02-13","cited_by_count":29,"area":null},{"id":"2402.05904","title":"FACT-GPT: Fact-Checking Augmentation via Claim Matching with LLMs","created":"2024-02-08","cited_by_count":27,"area":null},{"id":"2504.11975","title":"SemEval-2025 Task 3: Mu-SHROOM, the Multilingual Shared Task on Hallucinations and Related Observable Overgeneration Mistakes","created":"2025-04-16","cited_by_count":27,"area":null},{"id":"2504.14772","title":"Knowledge Distillation and Dataset Distillation of Large Language Models: Emerging Trends, Challenges, and Future Directions","created":"2025-04-20","cited_by_count":26,"area":"distill"},{"id":"2408.14317","title":"Claim Verification in the Age of Large Language Models: A Survey","created":"2024-08-26","cited_by_count":24,"area":null},{"id":"2510.12697","title":"Multi-Agent Debate for LLM Judges with Adaptive Stability Detection","created":"2025-10-14","cited_by_count":23,"area":"lr"},{"id":"2310.09223","title":"Automated Claim Matching with Large Language Models: Empowering Fact-Checkers in the Fight Against Misinformation","created":"2023-10-13","cited_by_count":19,"area":null},{"id":"2405.11874","title":"xFinder: Large Language Models as Automated Evaluators for Reliable Evaluation","created":"2024-05-20","cited_by_count":19,"area":null},{"id":"2410.22954","title":"Retrieval-Augmented Generation with Estimation of Source Reliability","created":"2024-10-30","cited_by_count":19,"area":"rag"},{"id":"2406.09920","title":"Knowledge Editing in Language Models via Adapted Direct Preference Optimization","created":"2024-06-14","cited_by_count":17,"area":"alignment"},{"id":"2410.14259","title":"Beyond Binary: Towards Fine-Grained LLM-Generated Text Detection via Role Recognition and Involvement Measurement","created":"2024-10-18","cited_by_count":17,"area":null},{"id":"2311.04917","title":"Adapting Fake News Detection to the Era of Large Language Models","created":"2023-11-02","cited_by_count":14,"area":null},{"id":"2508.03860","title":"Hallucination to Truth: A Review of Fact-Checking and Factuality Evaluation in Large Language Models","created":"2025-08-05","cited_by_count":13,"area":"rag"},{"id":"2606.07937","title":"Hallucination Cascade: Analyzing Error Propagation in Multi-Agent LLM Systems","created":"2026-06-06","cited_by_count":12,"area":"agents"},{"id":"2506.12349","title":"Information Suppression in Large Language Models: Auditing, Quantifying, and Characterizing Censorship in DeepSeek","created":"2025-06-14","cited_by_count":11,"area":null},{"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":"2508.02999","title":"AGENTiGraph: A Multi-Agent Knowledge Graph Framework for Interactive, Domain-Specific LLM Chatbots","created":"2025-08-05","cited_by_count":10,"area":"agents"},{"id":"2403.11169","title":"Customized large language models can outperform Community Notes in correcting misinformation","created":"2024-03-17","cited_by_count":9,"area":null},{"id":"2409.03843","title":"Persona Setting Pitfall: Persistent Outgroup Biases in Large Language Models Arising from Social Identity Adoption","created":"2024-09-05","cited_by_count":9,"area":null},{"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":"2410.11531","title":"AGENTiGraph: An Interactive Knowledge Graph Platform for LLM-based Chatbots Utilizing Private Data","created":"2024-10-15","cited_by_count":8,"area":"lr"},{"id":"2502.14132","title":"Can Community Notes Replace Professional Fact-Checkers?","created":"2025-02-19","cited_by_count":8,"area":null},{"id":"2410.13237","title":"Large Language Models are Easily Confused: A Quantitative Metric, Security Implications and Typological Analysis","created":"2024-10-17","cited_by_count":7,"area":null},{"id":"2509.13930","title":"Linguistic Nepotism: Trading-off Quality for Language Preference in Multilingual RAG","created":"2025-09-17","cited_by_count":7,"area":"rag"},{"id":"2406.11260","title":"Adversarial Style Augmentation via Large Language Model for Robust Fake News Detection","created":"2024-06-17","cited_by_count":6,"area":null},{"id":"2410.15308","title":"LlamaLens: Specialized Multilingual LLM for Analyzing News and Social Media Content","created":"2024-10-20","cited_by_count":6,"area":null},{"id":"2411.01511","title":"Integration of Large Vision Language Models for Efficient Post-disaster Damage Assessment and Reporting","created":"2024-11-03","cited_by_count":6,"area":"mllm"},{"id":"2503.05565","title":"Evaluating open-source Large Language Models for automated fact-checking","created":"2025-03-07","cited_by_count":6,"area":null},{"id":"2505.23295","title":"How Does Response Length Affect Long-Form Factuality","created":"2025-05-29","cited_by_count":6,"area":null},{"id":"2512.09487","title":"RouteRAG: Efficient Retrieval-Augmented Generation from Text and Graph via Reinforcement Learning","created":"2025-12-10","cited_by_count":6,"area":"lr"},{"id":"2602.00854","title":"Position: Human-Centric AI Requires a Minimum Viable Level of Human Understanding","created":"2026-01-31","cited_by_count":6,"area":null},{"id":"2402.10436","title":"I Am Not Them: Fluid Identities and Persistent Out-group Bias in Large Language Models","created":"2024-02-16","cited_by_count":5,"area":null},{"id":"2409.06729","title":"How will advanced AI systems impact democracy?","created":"2024-08-27","cited_by_count":5,"area":null},{"id":"2411.02461","title":"Enhancing Multiple Dimensions of Trustworthiness in LLMs via Sparse Activation Control","created":"2024-11-04","cited_by_count":5,"area":null},{"id":"2505.20067","title":"Community Moderation and the New Epistemology of Fact Checking on Social Media","created":"2025-05-26","cited_by_count":5,"area":null},{"id":"2507.09174","title":"RAMA: Retrieval-Augmented Multi-Agent Framework for Misinformation Detection in Multimodal Fact-Checking","created":"2025-07-12","cited_by_count":5,"area":"rag"},{"id":"2508.11779","title":"A Multi-Task Evaluation of LLMs' Processing of Academic Text Input","created":"2025-08-15","cited_by_count":5,"area":null},{"id":"2509.08463","title":"Adversarial Attacks Against Automated Fact-Checking: A Survey","created":"2025-09-10","cited_by_count":5,"area":null},{"id":"2601.00306","title":"The Generative AI Paradox: GenAI and the Erosion of Trust, the Corrosion of Information Verification, and the Demise of Truth","created":"2026-01-01","cited_by_count":5,"area":null},{"id":"2603.19532","title":"EvidenceRL: Reinforcing Evidence Consistency for Trustworthy Language Models","created":"2026-03-20","cited_by_count":5,"area":null},{"id":"2502.11753","title":"HintsOfTruth: A Multimodal Checkworthiness Detection Dataset with Real and Synthetic Claims","created":"2025-02-17","cited_by_count":4,"area":null},{"id":"2502.14714","title":"From Knowledge Generation to Knowledge Verification: Examining the BioMedical Generative Capabilities of ChatGPT","created":"2025-02-20","cited_by_count":4,"area":null},{"id":"2505.02344","title":"An End-to-End Model for Logits-Based Large Language Models Watermarking","created":"2025-05-05","cited_by_count":4,"area":"safety"},{"id":"2505.19288","title":"Hypercube-Based Retrieval-Augmented Generation for Scientific Question-Answering","created":"2025-05-25","cited_by_count":4,"area":"rag"},{"id":"2508.04086","title":"ToolGrad: Efficient Tool-use Dataset Generation with Textual \"Gradients\"","created":"2025-08-06","cited_by_count":4,"area":"agents"},{"id":"2410.21360","title":"A Survey on Automatic Credibility Assessment Using Textual Credibility Signals in the Era of Large Language Models","created":"2024-10-28","cited_by_count":3,"area":null},{"id":"2411.07845","title":"Ethical Concern Identification in NLP: A Corpus of ACL Anthology Ethics Statements","created":"2024-11-12","cited_by_count":3,"area":null},{"id":"2501.10909","title":"Fine-Grained Appropriate Reliance: Human-AI Collaboration with a Multi-Step Transparent Decision Workflow for Complex Task Decomposition","created":"2025-01-19","cited_by_count":3,"area":null},{"id":"2503.17599","title":"Evaluating Clinical Competencies of Large Language Models with a General Practice Benchmark","created":"2025-03-22","cited_by_count":3,"area":null},{"id":"2512.18853","title":"VizDefender: Unmasking Visualization Tampering through Proactive Localization and Intent Inference","created":"2025-12-21","cited_by_count":3,"area":null},{"id":"2602.15898","title":"MultiCube-RAG for Multi-hop Question Answering","created":"2026-02-11","cited_by_count":3,"area":null},{"id":"2603.02960","title":"Architecting Trust in Artificial Epistemic Agents","created":"2026-03-03","cited_by_count":3,"area":"agents"},{"id":"2411.17912","title":"Can LLMs plan paths in the real world?","created":"2024-11-26","cited_by_count":2,"area":null},{"id":"2412.05223","title":"100% Elimination of Hallucinations on RAGTruth for GPT-4 and GPT-3.5 Turbo","created":"2024-12-06","cited_by_count":2,"area":null},{"id":"2501.18265","title":"Efficiency and Effectiveness of LLM-Based Summarization of Evidence in Crowdsourced Fact-Checking","created":"2025-01-30","cited_by_count":2,"area":null},{"id":"2502.14383","title":"Rumor Detection by Multi-task Suffix Learning based on Time-series Dual Sentiments","created":"2025-02-20","cited_by_count":2,"area":null},{"id":"2503.01902","title":"How LLMs Fail to Support Fact-Checking","created":"2025-02-28","cited_by_count":2,"area":null},{"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":"2505.24830","title":"Improving Reliability and Explainability of Medical Question Answering through Atomic Fact Checking in Retrieval-Augmented LLMs","created":"2025-05-30","cited_by_count":2,"area":"rag"},{"id":"2506.15794","title":"Veracity: An Open-Source AI Fact-Checking System","created":"2025-06-18","cited_by_count":2,"area":null},{"id":"2510.13852","title":"ConsistencyAI: A Benchmark to Assess LLMs' Factual Consistency When Responding to Different Demographic Groups","created":"2025-10-11","cited_by_count":2,"area":null},{"id":"2510.18918","title":"Misinformation Detection using Large Language Models with Explainability","created":"2025-10-21","cited_by_count":2,"area":null},{"id":"2511.18749","title":"Large Language Models Require Curated Context for Reliable Political Fact-Checking -- Even with Reasoning and Web Search","created":"2025-11-24","cited_by_count":2,"area":"lr"},{"id":"2601.16478","title":"DeepEra: A Deep Evidence Reranking Agent for Scientific Retrieval-Augmented Generated Question Answering","created":"2026-01-23","cited_by_count":2,"area":"rag"},{"id":"2602.21857","title":"Distill and Align Decomposition for Enhanced Claim Verification","created":"2026-02-25","cited_by_count":2,"area":null},{"id":"2603.05308","title":"Med-V1: Small Language Models for Zero-shot and Scalable Biomedical Evidence Attribution","created":"2026-03-05","cited_by_count":2,"area":null},{"id":"2604.15372","title":"The Synthetic Media Shift: Tracking the Rise, Virality, and Detectability of AI-Generated Multimodal Misinformation","created":"2026-04-15","cited_by_count":2,"area":null},{"id":"2605.19228","title":"Diagnosing Multi-step Reasoning Failures in Black-box LLMs via Stepwise Confidence Attribution","created":"2026-05-19","cited_by_count":2,"area":"lr"},{"id":"2312.10626","title":"Decoding Concerns: Multi-label Classification of Vaccine Sentiments in Social Media","created":"2023-12-17","cited_by_count":1,"area":null},{"id":"2402.10527","title":"Assessing biomedical knowledge robustness in large language models by query-efficient sampling attacks","created":"2024-02-16","cited_by_count":1,"area":null},{"id":"2410.15064","title":"A Prompt Engineering Approach and a Knowledge Graph based Framework for Tackling Legal Implications of Large Language Model Answers","created":"2024-10-19","cited_by_count":1,"area":null},{"id":"2503.04271","title":"On Fact and Frequency: LLM Responses to Misinformation Expressed with Uncertainty","created":"2025-03-06","cited_by_count":1,"area":null},{"id":"2505.17380","title":"AI-Augmented LLMs Achieve Therapist-Level Responses in Motivational Interviewing","created":"2025-05-23","cited_by_count":1,"area":null},{"id":"2508.10010","title":"An Audit and Analysis of LLM-Assisted Health Misinformation Jailbreaks Against LLMs","created":"2025-08-06","cited_by_count":1,"area":"safety"},{"id":"2601.11293","title":"One LLM to Train Them All: Multi-Task Learning Framework for Fact-Checking","created":"2026-01-16","cited_by_count":1,"area":null},{"id":"2601.16890","title":"LLM-Based Adversarial Persuasion Attacks on Fact-Checking Systems","created":"2026-01-23","cited_by_count":1,"area":null},{"id":"2602.18693","title":"Contradiction to Consensus: Dual Perspective, Multi Source Retrieval Based Claim Verification with Source Level Disagreement using LLM","created":"2026-02-21","cited_by_count":1,"area":null},{"id":"2603.09654","title":"Understanding the Interplay between LLMs' Utilisation of Parametric and Contextual Knowledge: A keynote at ECIR 2025","created":"2026-03-10","cited_by_count":1,"area":null},{"id":"2603.19843","title":"Overreliance on AI in Information-seeking from Video Content","created":"2026-03-20","cited_by_count":1,"area":null},{"id":"2604.04177","title":"Position: Logical Soundness is not a Reliable Criterion for Neurosymbolic Fact-Checking with LLMs","created":"2026-04-05","cited_by_count":1,"area":null},{"id":"2604.06211","title":"Illocutionary Explanation Planning for Source-Faithful Explanations in Retrieval-Augmented Language Models","created":"2026-03-16","cited_by_count":1,"area":"rag"},{"id":"2410.17112","title":"Enhancing Answer Attribution for Faithful Text Generation with Large Language Models","created":"2024-10-22","cited_by_count":0,"area":null},{"id":"2504.05009","title":"Deconstructing Jazz Piano Style Using Machine Learning","created":"2025-04-07","cited_by_count":0,"area":null},{"id":"2505.21753","title":"From prosthetic memory to prosthetic denial: Auditing whether large language models are prone to mass atrocity denialism","created":"2025-05-27","cited_by_count":0,"area":null},{"id":"2506.23136","title":"LLM-Assisted Question-Answering on Technical Documents Using Structured Data-Aware Retrieval Augmented Generation","created":"2025-06-29","cited_by_count":0,"area":"rag"},{"id":"2508.10040","title":"Exploring Content and Social Connections of Fake News with Explainable Text and Graph Learning","created":"2025-08-11","cited_by_count":0,"area":null},{"id":"2509.02053","title":"Generative KI f\\\"ur TA","created":"2025-09-02","cited_by_count":0,"area":null},{"id":"2509.06838","title":"EPT Benchmark: Evaluation of Persian Trustworthiness in Large Language Models","created":"2025-09-08","cited_by_count":0,"area":null},{"id":"2509.11151","title":"AI-Generated Content in Cross-Domain Applications: Research Trends, Challenges and Propositions","created":"2025-09-14","cited_by_count":0,"area":null},{"id":"2510.22219","title":"Estimating the Error of Large Language Models at Pairwise Text Comparison","created":"2025-10-25","cited_by_count":0,"area":null}],"next_cursor":"100"}