{"total":140,"rows":[{"id":"2407.10817","title":"Foundational Autoraters: Taming Large Language Models for Better Automatic Evaluation","created":"2024-07-15","cited_by_count":74,"area":null},{"id":"2510.06265","title":"Large Language Models Hallucination: A Comprehensive Survey","created":"2025-10-05","cited_by_count":49,"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":"2503.15620","title":"Does Context Matter? ContextualJudgeBench for Evaluating LLM-based Judges in Contextual Settings","created":"2025-03-19","cited_by_count":24,"area":null},{"id":"2504.10063","title":"Hallucination Detection in LLMs with Topological Divergence on Attention Graphs","created":"2025-04-14","cited_by_count":19,"area":null},{"id":"2412.12004","title":"The Open Source Advantage in Large Language Models (LLMs)","created":"2024-12-16","cited_by_count":18,"area":null},{"id":"2506.07671","title":"GaRAGe: A Benchmark with Grounding Annotations for RAG Evaluation","created":"2025-06-09","cited_by_count":18,"area":null},{"id":"2407.06992","title":"Robust Neural Information Retrieval: An Adversarial and Out-of-distribution Perspective","created":"2024-07-09","cited_by_count":15,"area":null},{"id":"2410.18359","title":"Improving Model Factuality with Fine-grained Critique-based Evaluator","created":"2024-10-24","cited_by_count":15,"area":null},{"id":"2502.07184","title":"Refine Knowledge of Large Language Models via Adaptive Contrastive Learning","created":"2025-02-11","cited_by_count":15,"area":null},{"id":"2504.13128","title":"FreshStack: Building Realistic Benchmarks for Evaluating Retrieval on Technical Documents","created":"2025-04-17","cited_by_count":15,"area":null},{"id":"2504.17004","title":"(Im)possibility of Automated Hallucination Detection in Large Language Models","created":"2025-04-23","cited_by_count":15,"area":null},{"id":"2407.12943","title":"Halu-J: Critique-Based Hallucination Judge","created":"2024-07-17","cited_by_count":14,"area":null},{"id":"2501.17144","title":"FactCG: Enhancing Fact Checkers with Graph-Based Multi-Hop Data","created":"2025-01-28","cited_by_count":14,"area":null},{"id":"2510.04849","title":"When Models Lie, We Learn: Multilingual Span-Level Hallucination Detection with PsiloQA","created":"2025-10-06","cited_by_count":14,"area":null},{"id":"2504.07069","title":"HalluciNot: Hallucination Detection Through Context and Common Knowledge Verification","created":"2025-04-09","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":"2402.05359","title":"An Examination on the Effectiveness of Divide-and-Conquer Prompting in Large Language Models","created":"2024-02-08","cited_by_count":12,"area":null},{"id":"2411.16638","title":"Do Automatic Factuality Metrics Measure Factuality? A Critical Evaluation","created":"2024-11-25","cited_by_count":11,"area":null},{"id":"2501.06582","title":"ACORD: An Expert-Annotated Retrieval Dataset for Legal Contract Drafting","created":"2025-01-11","cited_by_count":11,"area":null},{"id":"2412.17056","title":"The HalluRAG Dataset: Detecting Closed-Domain Hallucinations in RAG Applications Using an LLM's Internal States","created":"2024-12-22","cited_by_count":10,"area":null},{"id":"2506.08354","title":"Position: Text Embeddings Should Capture Implicit Semantics, Not Just Surface Meaning","created":"2025-06-10","cited_by_count":10,"area":null},{"id":"2508.08287","title":"Sacred or Synthetic? Evaluating LLM Reliability and Abstention for Religious Questions","created":"2025-08-04","cited_by_count":10,"area":null},{"id":"2507.14239","title":"CCL-XCoT: An Efficient Cross-Lingual Knowledge Transfer Method for Mitigating Hallucination Generation","created":"2025-07-17","cited_by_count":9,"area":null},{"id":"2501.14883","title":"Verify with Caution: The Pitfalls of Relying on Imperfect Factuality Metrics","created":"2025-01-24","cited_by_count":8,"area":null},{"id":"2503.07158","title":"Generative AI in Transportation Planning: A Survey","created":"2025-03-10","cited_by_count":8,"area":null},{"id":"2508.05201","title":"FAITH: A Framework for Assessing Intrinsic Tabular Hallucinations in Finance","created":"2025-08-07","cited_by_count":8,"area":null},{"id":"2602.02888","title":"HALT: Hallucination Assessment via Log-probs as Time series","created":"2026-02-02","cited_by_count":8,"area":null},{"id":"2404.12041","title":"A Survey of Automatic Hallucination Evaluation on Natural Language Generation","created":"2024-04-18","cited_by_count":7,"area":null},{"id":"2507.02870","title":"Loki's Dance of Illusions: A Comprehensive Survey of Hallucination in Large Language Models","created":"2025-06-06","cited_by_count":7,"area":null},{"id":"2406.17095","title":"Attention Instruction: Amplifying Attention in the Middle via Prompting","created":"2024-06-24","cited_by_count":6,"area":null},{"id":"2411.07688","title":"ImageRAG: Enhancing Ultra High Resolution Remote Sensing Imagery Analysis with ImageRAG","created":"2024-11-12","cited_by_count":6,"area":null},{"id":"2503.10690","title":"Battling Misinformation: An Empirical Study on Adversarial Factuality in Open-Source Large Language Models","created":"2025-03-12","cited_by_count":6,"area":null},{"id":"2504.04335","title":"Hallucinated Span Detection with Multi-View Attention Features","created":"2025-04-06","cited_by_count":6,"area":null},{"id":"2406.00975","title":"Luna: An Evaluation Foundation Model to Catch Language Model Hallucinations with High Accuracy and Low Cost","created":"2024-06-03","cited_by_count":5,"area":null},{"id":"2412.11404","title":"Attention with Dependency Parsing Augmentation for Fine-Grained Attribution","created":"2024-12-16","cited_by_count":5,"area":null},{"id":"2504.05324","title":"Hybrid Retrieval for Hallucination Mitigation in Large Language Models: A Comparative Analysis","created":"2025-02-28","cited_by_count":5,"area":null},{"id":"2508.19720","title":"Continuously Steering LLMs Sensitivity to Contextual Knowledge with Proxy Models","created":"2025-08-27","cited_by_count":5,"area":null},{"id":"2606.30306","title":"Always-OnAgents:A Survey of Persistent Memory, State, and Governance in LLMAgents","created":"2026-06-29","cited_by_count":5,"area":null},{"id":"2608.28945","title":"Automated Researchers Can Mitigate Well-characterized Alignment Failures","created":"2026-08-28","cited_by_count":5,"area":null},{"id":"2408.12748","title":"SLM Meets LLM: Balancing Latency, Interpretability and Consistency in Hallucination Detection","created":"2024-08-22","cited_by_count":4,"area":null},{"id":"2409.11353","title":"THaMES: An End-to-End Tool for Hallucination Mitigation and Evaluation in Large Language Models","created":"2024-09-17","cited_by_count":4,"area":null},{"id":"2507.20836","title":"First Hallucination Tokens Are Different from Conditional Ones","created":"2025-07-28","cited_by_count":4,"area":null},{"id":"2509.19372","title":"Representation-based Broad Hallucination Detectors Fail to Generalize Out of Distribution","created":"2025-09-19","cited_by_count":4,"area":null},{"id":"2510.06354","title":"LLM Bias Detection and Mitigation through the Lens of Desired Distributions","created":"2025-10-07","cited_by_count":4,"area":null},{"id":"2608.01021","title":"Can Humans Dream of Electric Sheep? Human-Written Samples for Fine-Grained Vision-and-Language Hallucination Benchmarking","created":"2026-08-02","cited_by_count":4,"area":null},{"id":"2505.00506","title":"HalluMix: A Task-Agnostic, Multi-Domain Benchmark for Real-World Hallucination Detection","created":"2025-05-01","cited_by_count":3,"area":null},{"id":"2506.06020","title":"When to Trust Context: Self-Reflective Debates for Context Reliability","created":"2025-06-06","cited_by_count":3,"area":null},{"id":"2603.09296","title":"Diagnosing and Repairing Citation Failures in Generative Engine Optimization","created":"2026-03-10","cited_by_count":3,"area":null},{"id":"2605.17028","title":"PARALLAX: Separating Genuine Hallucination Detection from Benchmark Construction Artifacts","created":"2026-05-16","cited_by_count":3,"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":"2504.19472","title":"Conflicts in Texts: Data, Implications and Challenges","created":"2025-04-28","cited_by_count":2,"area":null},{"id":"2504.20610","title":"Information Retrieval in the Age of Generative AI: The RGB Model","created":"2025-04-29","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":"2506.06539","title":"Beyond Facts: Evaluating Intent Hallucination in Large Language Models","created":"2025-06-06","cited_by_count":2,"area":null},{"id":"2509.17671","title":"Turk-LettuceDetect: A Hallucination Detection Models for Turkish RAG Applications","created":"2025-09-22","cited_by_count":2,"area":null},{"id":"2510.20690","title":"Neural Diversity Regularizes Hallucinations in Language Models","created":"2025-10-23","cited_by_count":2,"area":null},{"id":"2601.01552","title":"HalluZig: Hallucination Detection using Zigzag Persistence","created":"2026-01-04","cited_by_count":2,"area":null},{"id":"2601.21969","title":"Token-Guard: Towards Token-Level Hallucination Control via Self-Checking Decoding","created":"2026-01-29","cited_by_count":2,"area":null},{"id":"2602.18145","title":"Detecting Contextual Hallucinations in LLMs with Frequency-Aware Attention","created":"2026-02-20","cited_by_count":2,"area":null},{"id":"2605.30637","title":"EHRBench: An Automated and Reliable EHR-based Benchmark for Clinical Decision Making with LLMs","created":"2026-05-28","cited_by_count":2,"area":null},{"id":"2606.16151","title":"GRACE: Step-Level Benchmark for Faithful Reasoning over Context","created":"2026-06-15","cited_by_count":2,"area":null},{"id":"2607.04029","title":"CrossHallu: Do Hallucination Signals Generalize Across Languages and Domains in Large Language Model's Internals?","created":"2026-07-04","cited_by_count":2,"area":null},{"id":"2607.20219","title":"HalluTruthQA: A Fine-Grained Benchmark for Hallucination Detection, Localization, and Explanation in Arabic Question Answering","created":"2026-07-22","cited_by_count":2,"area":null},{"id":"2405.11040","title":"From Generalist to Specialist: Improving Large Language Models for Medical Physics Using ARCoT","created":"2024-05-17","cited_by_count":1,"area":null},{"id":"2406.01428","title":"Superhuman performance in urology board questions by an explainable large language model enabled for context integration of the European Association of Urology guidelines: the UroBot study","created":"2024-06-03","cited_by_count":1,"area":null},{"id":"2409.16984","title":"AXCEL: Automated eXplainable Consistency Evaluation using LLMs","created":"2024-09-25","cited_by_count":1,"area":null},{"id":"2410.18114","title":"Bridging Today and the Future of Humanity: AI Safety in 2024 and Beyond","created":"2024-10-09","cited_by_count":1,"area":null},{"id":"2411.03300","title":"VERITAS: A Unified Approach to Reliability Evaluation","created":"2024-11-05","cited_by_count":1,"area":null},{"id":"2503.21813","title":"OAEI-LLM-T: A TBox Benchmark Dataset for Understanding Large Language Model Hallucinations in Ontology Matching","created":"2025-03-25","cited_by_count":1,"area":null},{"id":"2504.15771","title":"ORION Grounded in Context: Retrieval-Based Method for Hallucination Detection","created":"2025-04-22","cited_by_count":1,"area":null},{"id":"2505.20767","title":"CogniBench: A Legal-inspired Framework and Dataset for Assessing Cognitive Faithfulness of Large Language Models","created":"2025-05-27","cited_by_count":1,"area":null},{"id":"2509.20278","title":"Quantifying LLM Biases Across Instruction Boundary in Mixed Question Forms","created":"2025-09-24","cited_by_count":1,"area":null},{"id":"2509.22582","title":"Fine-Grained Detection of Context-Grounded Hallucinations Using LLMs","created":"2025-09-26","cited_by_count":1,"area":null},{"id":"2510.19318","title":"HAD: HAllucination Detection Language Models Based on a Comprehensive Hallucination Taxonomy","created":"2025-10-22","cited_by_count":1,"area":null},{"id":"2510.21118","title":"The Gray Zone of Faithfulness: Taming Ambiguity in Unfaithfulness Detection","created":"2025-10-24","cited_by_count":1,"area":null},{"id":"2511.01359","title":"PrefixNLI: Detecting Factual Inconsistencies as Soon as They Arise","created":"2025-11-03","cited_by_count":1,"area":null},{"id":"2511.01706","title":"Multi-Step Knowledge Interaction Analysis via Rank-2 Subspace Disentanglement","created":"2025-11-03","cited_by_count":1,"area":null},{"id":"2511.17081","title":"MUCH: A Multilingual Claim Hallucination Benchmark","created":"2025-11-21","cited_by_count":1,"area":null},{"id":"2601.19245","title":"Beyond In-Domain Detection: SpikeScore for Cross-Domain Hallucination Detection","created":"2026-01-27","cited_by_count":1,"area":null},{"id":"2602.13224","title":"A Geometric Taxonomy of Hallucinations in LLMs","created":"2026-01-26","cited_by_count":1,"area":null},{"id":"2605.21102","title":"ACL-Verbatim: hallucination-free question answering for research","created":"2026-05-20","cited_by_count":1,"area":null},{"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":"2606.06959","title":"OpenHalDet: A Unified Benchmark for Hallucination Detection across Diverse Generation Scenarios","created":"2026-06-05","cited_by_count":1,"area":null},{"id":"2606.12476","title":"Quickest Detection of Hallucination Onset: Delay Bounds and Learned CUSUM Statistics","created":"2026-06-10","cited_by_count":1,"area":null},{"id":"2606.21917","title":"Pre-Generation Hallucination Detection in Large Language Models via Soft-Target Attention Probing","created":"2026-06-20","cited_by_count":1,"area":null},{"id":"2606.31435","title":"CDR-Bench: Evaluating Faithful Execution of Compositional, Order-Sensitive Data Refinement Recipes","created":"2026-06-30","cited_by_count":1,"area":null},{"id":"2607.24054","title":"Success Is Not Self-Explanatory: Auditing Success Provenance in Agent Evaluation","created":"2026-07-27","cited_by_count":1,"area":null},{"id":"2608.03966","title":"HalluTruthQA-4K: A Fine-Grained Corpus and Annotation Process for Arabic Hallucination Detection and Truth Verification","created":"2026-08-04","cited_by_count":1,"area":null},{"id":"2608.18115","title":"Temporal Multi-Signal Fusion for Token-Level Hallucination Detection","created":"2026-06-30","cited_by_count":1,"area":null},{"id":"2608.21036","title":"Evaluating Large Language Model Performance on International Maritime Dangerous Goods Code Compliance","created":"2026-08-21","cited_by_count":1,"area":null},{"id":"2609.01337","title":"LEAP: Likelihood Elicitation and Aggregation for LLM-based Probabilistic Forecasting","created":"2026-09-01","cited_by_count":1,"area":null},{"id":"2609.35732","title":"Failure-Transparent Agents: Benchmarking Post-Failure Reporting in Tool-Using Language Models","created":"2026-09-28","cited_by_count":1,"area":null},{"id":"2505.03030","title":"UCSC at SemEval-2025 Task 3: Context, Models and Prompt Optimization for Automated Hallucination Detection in LLM Output","created":"2025-05-05","cited_by_count":0,"area":null},{"id":"2508.02279","title":"Dialogue Systems Engineering: A Survey and Future Directions","created":"2025-08-04","cited_by_count":0,"area":null},{"id":"2509.05360","title":"Beyond ROUGE: N-Gram Subspace Features for LLM Hallucination Detection","created":"2025-09-03","cited_by_count":0,"area":null},{"id":"2510.09915","title":"Enhancing Faithfulness in Abstractive Summarization via Span-Level Fine-Tuning","created":"2025-10-10","cited_by_count":0,"area":null},{"id":"2511.03900","title":"GRAD: Graph-Retrieved Adaptive Decoding for Hallucination Mitigation","created":"2025-11-05","cited_by_count":0,"area":null},{"id":"2601.03496","title":"STELLA: Self-Reflective Terminology-Aware Framework for Building an Aerospace Information Retrieval Benchmark","created":"2026-01-07","cited_by_count":0,"area":null},{"id":"2601.04212","title":"TrueBrief: Faithful Summarization through Small Language Models","created":"2025-12-12","cited_by_count":0,"area":null}],"next_cursor":"100"}