{"total":94,"rows":[{"id":"2305.14251","title":"FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation","created":"2023-05-23","cited_by_count":1282,"area":null},{"id":"2405.17428","title":"NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models","created":"2024-05-27","cited_by_count":472,"area":null},{"id":"2305.12744","title":"Fact-Checking Complex Claims with Program-Guided Reasoning","created":"2023-05-22","cited_by_count":146,"area":"lr"},{"id":"2305.13117","title":"AVeriTeC: A Dataset for Real-world Claim Verification with Evidence from the Web","created":"2023-05-22","cited_by_count":144,"area":null},{"id":"2407.01725","title":"DiscoveryBench: Towards Data-Driven Discovery with Large Language Models","created":"2024-07-01","cited_by_count":109,"area":"agents"},{"id":"2504.17550","title":"HalluLens: LLM Hallucination Benchmark","created":"2025-04-24","cited_by_count":92,"area":null},{"id":"2305.16859","title":"Scientific Fact-Checking: A Survey of Resources and Approaches","created":"2023-05-26","cited_by_count":54,"area":null},{"id":"2305.13186","title":"SCITAB: A Challenging Benchmark for Compositional Reasoning and Claim Verification on Scientific Tables","created":"2023-05-22","cited_by_count":51,"area":"lr"},{"id":"2310.05177","title":"Do Large Language Models Know about Facts?","created":"2023-10-08","cited_by_count":51,"area":null},{"id":"2511.07025","title":"Llama-Embed-Nemotron-8B: A Universal Text Embedding Model for Multilingual and Cross-Lingual Tasks","created":"2025-11-10","cited_by_count":51,"area":null},{"id":"2407.12861","title":"CiteME: Can Language Models Accurately Cite Scientific Claims?","created":"2024-07-10","cited_by_count":48,"area":null},{"id":"2502.05151","title":"Transforming Science with Large Language Models: A Survey on AI-assisted Scientific Discovery, Experimentation, Content Generation, and Evaluation","created":"2025-02-07","cited_by_count":42,"area":"mllm"},{"id":"2508.15804","title":"ReportBench: Evaluating Deep Research Agents via Academic Survey Tasks","created":"2025-08-14","cited_by_count":38,"area":"agents"},{"id":"2310.05253","title":"Explainable Claim Verification via Knowledge-Grounded Reasoning with Large Language Models","created":"2023-10-08","cited_by_count":37,"area":"lr"},{"id":"2309.08793","title":"Fin-Fact: A Benchmark Dataset for Multimodal Financial Fact Checking and Explanation Generation","created":"2023-09-15","cited_by_count":25,"area":null},{"id":"2405.06563","title":"What Can Natural Language Processing Do for Peer Review?","created":"2024-05-10","cited_by_count":25,"area":null},{"id":"2305.15053","title":"Decomposing Complex Queries for Tip-of-the-tongue Retrieval","created":"2023-05-24","cited_by_count":24,"area":null},{"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":"2411.05764","title":"FinDVer: Explainable Claim Verification over Long and Hybrid-Content Financial Documents","created":"2024-11-08","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":"2305.13693","title":"Automated Metrics for Medical Multi-Document Summarization Disagree with Human Evaluations","created":"2023-05-23","cited_by_count":18,"area":null},{"id":"2506.15569","title":"SciVer: Evaluating Foundation Models for Multimodal Scientific Claim Verification","created":"2025-06-18","cited_by_count":17,"area":null},{"id":"2503.04644","title":"IFIR: A Comprehensive Benchmark for Evaluating Instruction-Following in Expert-Domain Information Retrieval","created":"2025-03-06","cited_by_count":16,"area":null},{"id":"2406.03181","title":"Missci: Reconstructing Fallacies in Misrepresented Science","created":"2024-06-05","cited_by_count":14,"area":null},{"id":"2404.08359","title":"Improving Health Question Answering with Reliable and Time-Aware Evidence Retrieval","created":"2024-04-12","cited_by_count":12,"area":null},{"id":"2503.21717","title":"CLAIMCHECK: How Grounded are LLM Critiques of Scientific Papers?","created":"2025-03-27","cited_by_count":12,"area":null},{"id":"2402.01360","title":"What Makes Medical Claims (Un)Verifiable? Analyzing Entity and Relation Properties for Fact Verification","created":"2024-02-02","cited_by_count":10,"area":null},{"id":"2402.02844","title":"Comparing Knowledge Sources for Open-Domain Scientific Claim Verification","created":"2024-02-05","cited_by_count":10,"area":null},{"id":"2402.14268","title":"Can Large Language Models Detect Misinformation in Scientific News Reporting?","created":"2024-02-22","cited_by_count":9,"area":null},{"id":"2407.03545","title":"On Evaluating Explanation Utility for Human-AI Decision Making in NLP","created":"2024-07-03","cited_by_count":9,"area":null},{"id":"2506.04410","title":"Matter-of-Fact: A Benchmark for Verifying the Feasibility of Literature-Supported Claims in Materials Science","created":"2025-06-04","cited_by_count":9,"area":null},{"id":"2507.11810","title":"Evolving Roles of LLMs in Scientific Innovation: Assistant, Collaborator, Scientist, and Evaluator","created":"2025-07-16","cited_by_count":9,"area":null},{"id":"2305.07984","title":"SCENE: Self-Labeled Counterfactuals for Extrapolating to Negative Examples","created":"2023-05-13","cited_by_count":8,"area":null},{"id":"2503.01424","title":"From Hypothesis to Publication: A Comprehensive Survey of AI-Driven Research Support Systems","created":"2025-03-03","cited_by_count":8,"area":null},{"id":"2506.04585","title":"MuSciClaims: Multimodal Scientific Claim Verification","created":"2025-06-05","cited_by_count":8,"area":null},{"id":"2602.07621","title":"SciClaimEval: Cross-modal Claim Verification in Scientific Papers","created":"2026-02-07","cited_by_count":7,"area":null},{"id":"2211.05289","title":"Combating Health Misinformation in Social Media: Characterization, Detection, Intervention, and Open Issues","created":"2022-11-10","cited_by_count":6,"area":null},{"id":"2309.06578","title":"Can Large Language Models Discern Evidence for Scientific Hypotheses? Case Studies in the Social Sciences","created":"2023-09-07","cited_by_count":6,"area":null},{"id":"2506.20844","title":"The Next Phase of Scientific Fact-Checking: Advanced Evidence Retrieval from Complex Structured Academic Papers","created":"2025-06-25","cited_by_count":6,"area":null},{"id":"2404.13985","title":"Information Re-Organization Improves Reasoning in Large Language Models","created":"2024-04-22","cited_by_count":5,"area":"lr"},{"id":"2504.18639","title":"Span-Level Hallucination Detection for LLM-Generated Answers","created":"2025-04-25","cited_by_count":5,"area":null},{"id":"2601.22984","title":"Why Your Deep Research Agent Fails? On Hallucination Evaluation in Full Research Trajectory","created":"2026-01-30","cited_by_count":5,"area":"agents"},{"id":"2401.12566","title":"Automated Fact-Checking of Climate Change Claims with Large Language Models","created":"2024-01-23","cited_by_count":4,"area":null},{"id":"2502.10003","title":"SciClaimHunt: A Large Dataset for Evidence-based Scientific Claim Verification","created":"2025-02-14","cited_by_count":4,"area":null},{"id":"2407.18367","title":"Robust Claim Verification Through Fact Detection","created":"2024-07-25","cited_by_count":3,"area":null},{"id":"2510.22055","title":"A Benchmark for Open-Domain Numerical Fact-Checking Enhanced by Claim Decomposition","created":"2025-10-24","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":"2601.04350","title":"RIGOURATE: Quantifying Scientific Exaggeration with Evidence-Aligned Claim Evaluation","created":"2026-01-07","cited_by_count":3,"area":null},{"id":"2503.08600","title":"NSF-SciFy: Mining the NSF Awards Database for Scientific Claims","created":"2025-03-11","cited_by_count":2,"area":null},{"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":"2504.09866","title":"PASS-FC: Progressive and Adaptive Search Scheme for Fact Checking of Comprehensive Claims","created":"2025-04-14","cited_by_count":2,"area":null},{"id":"2505.21870","title":"Evaluating the Retrieval Robustness of Large Language Models","created":"2025-05-28","cited_by_count":2,"area":"rag"},{"id":"2506.08700","title":"ClimateViz: A Benchmark for Statistical Reasoning and Fact Verification on Scientific Charts","created":"2025-06-10","cited_by_count":2,"area":"lr"},{"id":"2508.11122","title":"+VeriRel: Verification Feedback to Enhance Document Retrieval for Scientific Fact Checking","created":"2025-08-14","cited_by_count":2,"area":null},{"id":"2510.09217","title":"IRIS: An Iterative and Integrated Framework for Verifiable Causal Discovery in the Absence of Tabular Data","created":"2025-10-10","cited_by_count":2,"area":null},{"id":"2510.22395","title":"Confabulations from ACL Publications (CAP): A Dataset for Scientific Hallucination Detection","created":"2025-10-25","cited_by_count":2,"area":null},{"id":"2601.04646","title":"Succeeding at Scale: Enterprise Retrieval Benchmark Construction and Index-Preserving Query Adaptation for Multi-Tenant Search","created":"2026-01-08","cited_by_count":2,"area":null},{"id":"2602.21045","title":"PaperTrail: A Claim-Evidence Interface for Grounding Provenance in LLM-based Scholarly Q&A","created":"2026-02-24","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":"2305.14707","title":"SciFix: Outperforming GPT3 on Scientific Factual Error Correction","created":"2023-05-24","cited_by_count":1,"area":null},{"id":"2505.23250","title":"Deep Retrieval at CheckThat! 2025: Identifying Scientific Papers from Implicit Social Media Mentions via Hybrid Retrieval and Re-Ranking","created":"2025-05-29","cited_by_count":1,"area":null},{"id":"2511.05684","title":"A Representation Sharpening Framework for Zero Shot Dense Retrieval","created":"2025-11-07","cited_by_count":1,"area":null},{"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":"2602.13817","title":"What happens when reviewers receive AI feedback in their reviews?","created":"2026-02-14","cited_by_count":1,"area":null},{"id":"2603.14257","title":"Automatic Inter-document Multi-hop Scientific QA Generation","created":"2026-03-15","cited_by_count":1,"area":null},{"id":"2603.18235","title":"Toward Reliable, Safe, and Secure LLMs for Scientific Applications","created":"2026-03-18","cited_by_count":1,"area":"agents"},{"id":"2605.26663","title":"Evidence Absence Is Not Evidence Insufficiency: Diagnosing NEI Construction Artifacts in Fact Verification","created":"2026-05-26","cited_by_count":1,"area":null},{"id":"2605.27700","title":"CiteCheck: Retrieval-Grounded Detection of LLM Citation Hallucinations in Scientific Text","created":"2026-05-26","cited_by_count":1,"area":null},{"id":"2410.18670","title":"Health Misinformation in Social Networks: A Survey of IT Approaches","created":"2024-10-24","cited_by_count":0,"area":null},{"id":"2501.10642","title":"Iterative Tree Analysis for Medical Critics","created":"2025-01-18","cited_by_count":0,"area":null},{"id":"2508.16117","title":"Extending FKG.in: Towards a Food Claim Traceability Network","created":"2025-08-22","cited_by_count":0,"area":null},{"id":"2509.06902","title":"Proof-Carrying Numbers (PCN): A Protocol for Trustworthy Numeric Answers from LLMs via Claim Verification","created":"2025-09-08","cited_by_count":0,"area":null},{"id":"2601.04857","title":"MisSpans: Fine-Grained False Span Identification in Cross-Domain Fake News","created":"2026-01-08","cited_by_count":0,"area":null},{"id":"2601.22361","title":"MERMAID: Memory-Enhanced Retrieval and Reasoning with Multi-Agent Iterative Knowledge Grounding for Veracity Assessment","created":"2026-01-29","cited_by_count":0,"area":"lr"},{"id":"2602.10833","title":"Training-Induced Bias Toward LLM-Generated Content in Dense Retrieval","created":"2026-02-11","cited_by_count":0,"area":null},{"id":"2603.26449","title":"ClimateCheck 2026: Scientific Fact-Checking and Disinformation Narrative Classification of Climate-related Claims","created":"2026-03-27","cited_by_count":0,"area":null},{"id":"2604.10990","title":"When Verification Fails: How Compositionally Infeasible Claims Escape Rejection","created":"2026-04-13","cited_by_count":0,"area":null},{"id":"2604.15591","title":"BioHiCL: Hierarchical Multi-Label Contrastive Learning for Biomedical Retrieval with MeSH Labels","created":"2026-04-17","cited_by_count":0,"area":null},{"id":"2605.10425","title":"Toward an Engineering of Science: Rebalancing Generation and Verification in the Age of AI","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.27710","title":"DeepSciVerify: Verifying Scientific Claim--Citation Alignment via LLM-Driven Evidence Escalation","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2606.11208","title":"BioDivergence: A Benchmark and Evaluation Framework for Hidden Contextual Contradictions in Biomedical Abstracts","created":"2026-04-23","cited_by_count":0,"area":null},{"id":"2606.20873","title":"SciLens: Multi-modal Scientific Claim Verification with Agentic Entailment and Grounding","created":"2026-06-18","cited_by_count":0,"area":"agents"},{"id":"2606.21359","title":"Does Finetuning with Scientific Data Increase Hallucinations? A Multi-domain Factuality Evaluation of LLMs","created":"2026-06-19","cited_by_count":0,"area":null},{"id":"2606.27383","title":"CalBrief: A Pilot Diagnostic Benchmark for Evidence-Calibrated Scientific Briefing with Large Language Models","created":"2026-06-11","cited_by_count":0,"area":null},{"id":"2606.29630","title":"SFBench: The SciFy Scientific Feasibility Benchmark","created":"2026-06-28","cited_by_count":0,"area":null},{"id":"2607.16131","title":"ToolSciVer: Multimodal Scientific Claim Verification with Visual Tool Augmented Reinforcement Learning","created":"2026-07-17","cited_by_count":0,"area":"lr"},{"id":"2607.24165","title":"Do Current Retrievers Cover All the Evidence? A Controlled Study of Conjunctive Cross-Page Retrieval","created":"2026-07-27","cited_by_count":0,"area":null},{"id":"2608.07204","title":"HNR-DAC: Hard-Negative Reranking and Distribution-Aligned Classification for Scientific Claim Verification","created":"2026-08-07","cited_by_count":0,"area":null},{"id":"2609.09388","title":"XAI-Refine: An Automated Explanation-Knowledge Loop for Brain-Age Prediction","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.11460","title":"ReGround: Grounding Reviewer Comments in Multimodal Evidence","created":"2026-09-10","cited_by_count":0,"area":null},{"id":"2609.14248","title":"ATTRICITE: Training an Open 4B Model for Citation Recovery toward Faithful Attribution","created":"2026-09-13","cited_by_count":0,"area":null},{"id":"2609.25833","title":"ARAFA: An LLM-Generated Arabic Fact-Checking Dataset","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2609.30467","title":"Where Does Retrieval-Based Open-Ended Evaluation Fail? Automatic Taxonomy Induction from Long-Form Medical Answer Factuality Verification","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2609.38766","title":"PathAnchor: Path-Structured Evidence for Scientific Agents","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}