{"total":117,"rows":[{"id":"2502.02542","title":"OverThink: Slowdown Attacks on Reasoning LLMs","created":"2025-02-04","cited_by_count":96,"area":"lr"},{"id":"2504.17550","title":"HalluLens: LLM Hallucination Benchmark","created":"2025-04-24","cited_by_count":92,"area":null},{"id":"2503.05061","title":"No Free Labels: Limitations of LLM-as-a-Judge Without Human Grounding","created":"2025-03-07","cited_by_count":54,"area":null},{"id":"2509.07968","title":"SimpleQA Verified: A Reliable Factuality Benchmark to Measure Parametric Knowledge","created":"2025-09-09","cited_by_count":54,"area":null},{"id":"2501.03200","title":"The FACTS Grounding Leaderboard: Benchmarking LLMs' Ability to Ground Responses to Long-Form Input","created":"2025-01-06","cited_by_count":52,"area":null},{"id":"2601.20975","title":"DeepSearchQA: Bridging the Comprehensiveness Gap for Deep Research Agents","created":"2026-01-28","cited_by_count":50,"area":"agents"},{"id":"2411.02400","title":"Decomposition Dilemmas: Does Claim Decomposition Boost or Burden Fact-Checking Performance?","created":"2024-10-17","cited_by_count":36,"area":null},{"id":"2409.11242","title":"Measuring and Enhancing Trustworthiness of LLMs in RAG through Grounded Attributions and Learning to Refuse","created":"2024-09-17","cited_by_count":34,"area":"rag"},{"id":"2410.22257","title":"FactBench: A Dynamic Benchmark for In-the-Wild Language Model Factuality Evaluation","created":"2024-10-29","cited_by_count":25,"area":null},{"id":"2506.08500","title":"DRAGged into Conflicts: Detecting and Addressing Conflicting Sources in Search-Augmented LLMs","created":"2025-06-10","cited_by_count":25,"area":"rag"},{"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":"2410.13246","title":"Atomic Calibration of LLMs in Long-Form Generations","created":"2024-10-17","cited_by_count":24,"area":null},{"id":"2412.13175","title":"DnDScore: Decontextualization and Decomposition for Factuality Verification in Long-Form Text Generation","created":"2024-12-17","cited_by_count":22,"area":null},{"id":"2502.19110","title":"Conformal Linguistic Calibration: Trading-off between Factuality and Specificity","created":"2025-02-26","cited_by_count":20,"area":null},{"id":"2504.14891","title":"Retrieval Augmented Generation Evaluation in the Era of Large Language Models: A Comprehensive Survey","created":"2025-04-21","cited_by_count":20,"area":"rag"},{"id":"2502.10855","title":"Towards Effective Extraction and Evaluation of Factual Claims","created":"2025-02-15","cited_by_count":19,"area":null},{"id":"2505.11080","title":"BLEUBERI: BLEU is a surprisingly effective reward for instruction following","created":"2025-05-16","cited_by_count":17,"area":"alignment"},{"id":"2407.03572","title":"Core: Robust Factual Precision with Informative Sub-Claim Identification","created":"2024-07-04","cited_by_count":16,"area":null},{"id":"2508.15658","title":"SurGE: A Benchmark and Evaluation Framework for Scientific Survey Generation","created":"2025-08-21","cited_by_count":16,"area":null},{"id":"2501.03545","title":"Beyond Factual Accuracy: Evaluating Coverage of Diverse Factual Information in Long-form Text Generation","created":"2025-01-07","cited_by_count":15,"area":null},{"id":"2407.21057","title":"Multi-group Uncertainty Quantification for Long-form Text Generation","created":"2024-07-25","cited_by_count":13,"area":null},{"id":"2506.13342","title":"Verifying the Verifiers: Unveiling Pitfalls and Potentials in Fact Verifiers","created":"2025-06-16","cited_by_count":13,"area":null},{"id":"2505.16922","title":"UNCLE: Benchmarking Uncertainty Expressions in Long-Form Generation","created":"2025-05-22","cited_by_count":11,"area":null},{"id":"2412.18069","title":"Improving Factuality with Explicit Working Memory","created":"2024-12-24","cited_by_count":10,"area":null},{"id":"2503.15354","title":"Optimizing Decomposition for Optimal Claim Verification","created":"2025-03-19","cited_by_count":10,"area":null},{"id":"2505.20276","title":"Does quantization affect models' performance on long-context tasks?","created":"2025-05-26","cited_by_count":10,"area":null},{"id":"2603.05912","title":"DeepFact: Co-Evolving Benchmarks and Agents for Deep Research Factuality","created":"2026-03-06","cited_by_count":10,"area":"agents"},{"id":"2503.15272","title":"MAMM-Refine: A Recipe for Improving Faithfulness in Generation with Multi-Agent Collaboration","created":"2025-03-19","cited_by_count":9,"area":"agents"},{"id":"2608.05179","title":"Autonomous Research Agents: A Survey of AI Scientists and the Verification Gap","created":"2026-06-29","cited_by_count":9,"area":"agents"},{"id":"2505.16973","title":"VeriFastScore: Speeding up long-form factuality evaluation","created":"2025-05-22","cited_by_count":8,"area":null},{"id":"2510.12839","title":"FaStfact: Faster, Stronger Long-Form Factuality Evaluations in LLMs","created":"2025-10-13","cited_by_count":8,"area":null},{"id":"2503.17684","title":"Can LLMs Automate Fact-Checking Article Writing?","created":"2025-03-22","cited_by_count":7,"area":null},{"id":"2504.19457","title":"Towards Long Context Hallucination Detection","created":"2025-04-28","cited_by_count":7,"area":null},{"id":"2511.20513","title":"DesignPref: Capturing Personal Preferences in Visual Design Generation","created":"2025-11-25","cited_by_count":7,"area":null},{"id":"2605.00737","title":"To Call or Not to Call: A Framework to Assess and Optimize LLM Tool Calling","created":"2026-05-01","cited_by_count":7,"area":"agents"},{"id":"2505.23295","title":"How Does Response Length Affect Long-Form Factuality","created":"2025-05-29","cited_by_count":6,"area":null},{"id":"2508.00109","title":"FACTORY: A Challenging Human-Verified Prompt Set for Long-Form Factuality","created":"2025-07-31","cited_by_count":6,"area":null},{"id":"2510.07083","title":"All Claims Are Equal, but Some Claims Are More Equal Than Others: Importance-Sensitive Factuality Evaluation of LLM Generations","created":"2025-10-08","cited_by_count":6,"area":null},{"id":"2505.18452","title":"MedScore: Generalizable Factuality Evaluation of Free-Form Medical Answers by Domain-adapted Claim Decomposition and Verification","created":"2025-05-24","cited_by_count":5,"area":null},{"id":"2508.16838","title":"If We May De-Presuppose: Robustly Verifying Claims through Presupposition-Free Question Decomposition","created":"2025-08-22","cited_by_count":5,"area":null},{"id":"2510.09275","title":"Inflated Excellence or True Performance? Rethinking Medical Diagnostic Benchmarks with Dynamic Evaluation","created":"2025-10-10","cited_by_count":5,"area":"lr"},{"id":"2510.17733","title":"Train for Truth, Keep the Skills: Binary Retrieval-Augmented Reward Mitigates Hallucinations","created":"2025-10-20","cited_by_count":5,"area":"rag"},{"id":"2504.19339","title":"Explanatory Summarization with Discourse-Driven Planning","created":"2025-04-27","cited_by_count":4,"area":null},{"id":"2505.15792","title":"Long-Form Information Alignment Evaluation Beyond Atomic Facts","created":"2025-05-21","cited_by_count":4,"area":null},{"id":"2506.07309","title":"ConfRAG: Confidence-Guided Retrieval-Augmenting Generation","created":"2025-06-08","cited_by_count":4,"area":"rag"},{"id":"2507.08371","title":"The Curious Case of Factuality Finetuning: Models' Internal Beliefs Can Improve Factuality","created":"2025-07-11","cited_by_count":4,"area":"synth"},{"id":"2509.23233","title":"Detecting Corpus-Level Knowledge Inconsistencies in Wikipedia with Large Language Models","created":"2025-09-27","cited_by_count":4,"area":"rag"},{"id":"2509.23765","title":"Knowledge-Level Consistency Reinforcement Learning: Dual-Fact Alignment for Long-Form Factuality","created":"2025-09-28","cited_by_count":4,"area":"alignment"},{"id":"2510.22967","title":"MAD-Fact: A Multi-Agent Debate Framework for Long-Form Factuality Evaluation in LLMs","created":"2025-10-27","cited_by_count":4,"area":"agents"},{"id":"2510.24794","title":"MR-Align: Meta-Reasoning Informed Factuality Alignment for Large Reasoning Models","created":"2025-10-27","cited_by_count":4,"area":"lr"},{"id":"2601.02536","title":"MovieRecapsQA: A Multimodal Open-Ended Video Question-Answering Benchmark","created":"2026-01-05","cited_by_count":4,"area":null},{"id":"2601.13217","title":"Beyond Single-shot Writing: Deep Research Agents are Unreliable at Multi-turn Report Revision","created":"2026-01-19","cited_by_count":4,"area":"agents"},{"id":"2604.03141","title":"Beyond Precision: Importance-Aware Recall for Factuality Evaluation in Long-Form LLM Generation","created":"2026-04-03","cited_by_count":4,"area":null},{"id":"2608.14588","title":"The Hallucination Snowball: Modeling Error Propagation as State Transitions in Multi-Agent LLM Pipelines","created":"2026-06-22","cited_by_count":4,"area":"agents"},{"id":"2410.10372","title":"BookWorm: A Dataset for Character Description and Analysis","created":"2024-10-14","cited_by_count":3,"area":null},{"id":"2503.16575","title":"Extract, Match, and Score: An Evaluation Paradigm for Long Question-context-answer Triplets in Financial Analysis","created":"2025-03-20","cited_by_count":3,"area":null},{"id":"2504.02467","title":"BOOST: Bootstrapping Strategy-Driven Reasoning Programs for Program-Guided Fact-Checking","created":"2025-04-03","cited_by_count":3,"area":"lr"},{"id":"2505.16576","title":"EMULATE: A Multi-Agent Framework for Determining the Veracity of Atomic Claims by Emulating Human Actions","created":"2025-05-22","cited_by_count":3,"area":"agents"},{"id":"2505.21999","title":"Found in Translation: Measuring Multilingual LLM Consistency as Simple as Translate then Evaluate","created":"2025-05-28","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":"2606.18037","title":"ProvenanceGuard: Source-Aware Factuality Verification for MCP-Based LLM Agents","created":"2026-06-16","cited_by_count":3,"area":"agents"},{"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":"2506.04051","title":"High Accuracy, Less Talk (HALT): Reliable LLMs through Capability-Aligned Finetuning","created":"2025-06-04","cited_by_count":2,"area":null},{"id":"2510.07926","title":"Comprehensiveness Metrics for Automatic Evaluation of Factual Recall in Text Generation","created":"2025-10-09","cited_by_count":2,"area":null},{"id":"2510.24345","title":"LongWeave: A Long-Form Generation Benchmark Bridging Real-World Relevance and Verifiability","created":"2025-10-28","cited_by_count":2,"area":null},{"id":"2602.21857","title":"Distill and Align Decomposition for Enhanced Claim Verification","created":"2026-02-25","cited_by_count":2,"area":null},{"id":"2604.10556","title":"Lost in Diffusion: Uncovering Hallucination Patterns and Failure Modes in Diffusion Large Language Models","created":"2026-04-12","cited_by_count":2,"area":null},{"id":"2605.01704","title":"The Reasoning Trap: An Information-Theoretic Bound on Closed-System Multi-Step LLM Reasoning","created":"2026-05-03","cited_by_count":2,"area":"lr"},{"id":"2607.19322","title":"Two-Level Meta-Rubrics for Evaluating Open-Ended Generation: GAMUT, a Benchmark for Factual Completeness","created":"2026-07-21","cited_by_count":2,"area":null},{"id":"2505.10586","title":"Towards Automated Situation Awareness: A RAG-Based Framework for Peacebuilding Reports","created":"2025-05-14","cited_by_count":1,"area":null},{"id":"2505.12474","title":"What Are They Talking About? A Benchmark of Knowledge-Grounded Discussion Summarization","created":"2025-05-18","cited_by_count":1,"area":null},{"id":"2505.15633","title":"Listen to the Context: Towards Faithful Large Language Models for Retrieval Augmented Generation on Climate Questions","created":"2025-05-21","cited_by_count":1,"area":"rag"},{"id":"2506.00425","title":"Inter-Passage Verification for Multi-evidence Multi-answer QA","created":"2025-05-31","cited_by_count":1,"area":"rag"},{"id":"2509.26011","title":"RAGferee: Building Contextual Reward Models for Retrieval-Augmented Generation","created":"2025-09-30","cited_by_count":1,"area":"rag"},{"id":"2510.21891","title":"Embedding Trust: Semantic Isotropy Predicts Nonfactuality in Long-Form Text Generation","created":"2025-10-24","cited_by_count":1,"area":null},{"id":"2510.24870","title":"Seeing Through the MiRAGE: Evaluating Multimodal Retrieval Augmented Generation","created":"2025-10-28","cited_by_count":1,"area":"rag"},{"id":"2601.15714","title":"Even GPT-5.2 Can't Count to Five: The Case for Zero-Error Horizons in Trustworthy LLMs","created":"2026-01-22","cited_by_count":1,"area":null},{"id":"2603.27752","title":"Retromorphic Testing with Hierarchical Verification for Hallucination Detection in RAG","created":"2026-03-29","cited_by_count":1,"area":"rag"},{"id":"2604.15109","title":"IUQ: Interrogative Uncertainty Quantification for Long-Form Large Language Model Generation","created":"2026-04-16","cited_by_count":1,"area":null},{"id":"2605.26937","title":"Beyond Questions: Evaluating the Stated Knowledge of LLMs","created":"2026-05-26","cited_by_count":1,"area":null},{"id":"2606.03032","title":"The Deliberative Illusion: Diagnosing Factual Attrition and Stance Homogenization in Multi-Agent LLM Deliberation","created":"2026-06-02","cited_by_count":1,"area":"agents"},{"id":"2606.15974","title":"A Large-Scale Multi-Dimensional Empirical Study of LLMs for Conversation Summarization","created":"2026-06-14","cited_by_count":1,"area":null},{"id":"2507.20546","title":"Enhancing Hallucination Detection via Future Context","created":"2025-07-28","cited_by_count":0,"area":null},{"id":"2508.15085","title":"LongRecall: A Structured Approach for Robust Recall Evaluation in Long-Form Text","created":"2025-08-20","cited_by_count":0,"area":null},{"id":"2601.03605","title":"AEScorer: An Agentic Evidence-Grounded Framework for Graded Factuality Verification","created":"2026-01-07","cited_by_count":0,"area":"agents"},{"id":"2602.23603","title":"LFQA-HP-1M: A Large-Scale Human Preference Dataset for Long-Form Question Answering","created":"2026-02-27","cited_by_count":0,"area":"alignment"},{"id":"2604.00019","title":"The Chronicles of RiDiC: Generating Datasets with Controlled Popularity Distribution for Long-form Factuality Evaluation","created":"2026-03-11","cited_by_count":0,"area":null},{"id":"2604.09876","title":"Efficient Personalization of Generative User Interfaces","created":"2026-04-10","cited_by_count":0,"area":null},{"id":"2605.01749","title":"Only Say What You Know: Calibration-Aware Generation for Long-Form Factuality","created":"2026-05-03","cited_by_count":0,"area":"lr"},{"id":"2605.26955","title":"JuICE: A Benchmark for Evaluating LLM-Judge in Identifying Cultural Errors","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2605.29897","title":"ExCAM: Explainable Cultural Awareness Metrics","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2606.08000","title":"Summarization is Not Dead Yet","created":"2026-06-06","cited_by_count":0,"area":null},{"id":"2606.17041","title":"MetaSyn: A Benchmark for LLM Agents on Meta-Analysis Articles from Nature Portfolio","created":"2026-06-15","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":"2607.05069","title":"MIRAGE: Defending Long-Form RAG Against Misinformation Pollution","created":"2026-07-06","cited_by_count":0,"area":"rag"},{"id":"2607.10798","title":"Trust Before Fusion: QIMG-7 and Source-Aware Resolution for Polluted Multimodal RAG","created":"2026-07-12","cited_by_count":0,"area":"rag"},{"id":"2607.14044","title":"AI-accelerated End-to-End Framework for Rapid Professional Upskilling","created":"2026-07-15","cited_by_count":0,"area":null},{"id":"2608.00205","title":"Averaging Bias: Human Faithfulness Annotations are not Locally Faithful","created":"2026-07-31","cited_by_count":0,"area":null},{"id":"2608.03675","title":"VetScore: Risk-Weighted Fact Verification for Veterinary Long-Form QA with Citations","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2608.05228","title":"TriQua: Reconciling Granularity and Context in Factuality Evaluation","created":"2026-08-05","cited_by_count":0,"area":null}],"next_cursor":"100"}