{"total":97,"rows":[{"id":"2311.05232","title":"A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions","created":"2023-11-09","cited_by_count":1601,"area":null},{"id":"2309.01219","title":"Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models","created":"2023-09-03","cited_by_count":698,"area":null},{"id":"2308.10792","title":"Instruction Tuning for Large Language Models: A Survey","created":"2023-08-21","cited_by_count":623,"area":null},{"id":"2309.16289","title":"LawBench: Benchmarking Legal Knowledge of Large Language Models","created":"2023-09-28","cited_by_count":117,"area":null},{"id":"2405.12819","title":"Large Language Models Meet NLP: A Survey","created":"2024-05-21","cited_by_count":103,"area":null},{"id":"2402.18154","title":"Cutting Off the Head Ends the Conflict: A Mechanism for Interpreting and Mitigating Knowledge Conflicts in Language Models","created":"2024-02-28","cited_by_count":91,"area":null},{"id":"2309.06794","title":"Cognitive Mirage: A Review of Hallucinations in Large Language Models","created":"2023-09-13","cited_by_count":84,"area":null},{"id":"2405.06373","title":"LLM Discussion: Enhancing the Creativity of Large Language Models via Discussion Framework and Role-Play","created":"2024-05-10","cited_by_count":66,"area":null},{"id":"2312.14183","title":"On Early Detection of Hallucinations in Factual Question Answering","created":"2023-12-19","cited_by_count":56,"area":null},{"id":"2406.13121","title":"Can Long-Context Language Models Subsume Retrieval, RAG, SQL, and More?","created":"2024-06-19","cited_by_count":56,"area":null},{"id":"2403.08946","title":"Usable XAI: 10 Strategies Towards Exploiting Explainability in the LLM Era","created":"2024-03-13","cited_by_count":46,"area":null},{"id":"2410.07137","title":"Cheating Automatic LLM Benchmarks: Null Models Achieve High Win Rates","created":"2024-10-09","cited_by_count":45,"area":null},{"id":"2401.09865","title":"Improving fine-grained understanding in image-text pre-training","created":"2024-01-18","cited_by_count":44,"area":null},{"id":"2401.06796","title":"AI Hallucinations: A Misnomer Worth Clarifying","created":"2024-01-09","cited_by_count":34,"area":null},{"id":"2401.14367","title":"Genie: Achieving Human Parity in Content-Grounded Datasets Generation","created":"2024-01-25","cited_by_count":31,"area":null},{"id":"2406.11811","title":"RepLiQA: A Question-Answering Dataset for Benchmarking LLMs on Unseen Reference Content","created":"2024-06-17","cited_by_count":26,"area":null},{"id":"2406.15718","title":"Beyond the Turn-Based Game: Enabling Real-Time Conversations with Duplex Models","created":"2024-06-22","cited_by_count":26,"area":null},{"id":"2401.07348","title":"Generative AI in EU Law: Liability, Privacy, Intellectual Property, and Cybersecurity","created":"2024-01-14","cited_by_count":21,"area":null},{"id":"2404.12447","title":"AmbigDocs: Reasoning across Documents on Different Entities under the Same Name","created":"2024-04-18","cited_by_count":21,"area":null},{"id":"2403.17848","title":"ArabicaQA: A Comprehensive Dataset for Arabic Question Answering","created":"2024-03-26","cited_by_count":20,"area":null},{"id":"2504.07863","title":"Robust Hallucination Detection in LLMs via Adaptive Token Selection","created":"2025-04-10","cited_by_count":19,"area":null},{"id":"2312.11518","title":"User Modeling in the Era of Large Language Models: Current Research and Future Directions","created":"2023-12-11","cited_by_count":18,"area":null},{"id":"2406.05213","title":"On Subjective Uncertainty Quantification and Calibration in Natural Language Generation","created":"2024-06-07","cited_by_count":16,"area":null},{"id":"2403.07556","title":"Truth-Aware Context Selection: Mitigating Hallucinations of Large Language Models Being Misled by Untruthful Contexts","created":"2024-03-12","cited_by_count":15,"area":null},{"id":"2406.05494","title":"Investigating and Addressing Hallucinations of LLMs in Tasks Involving Negation","created":"2024-06-08","cited_by_count":15,"area":null},{"id":"2411.13173","title":"Writing Style Matters: An Examination of Bias and Fairness in Information Retrieval Systems","created":"2024-11-20","cited_by_count":15,"area":null},{"id":"2311.10395","title":"Bias A-head? Analyzing Bias in Transformer-Based Language Model Attention Heads","created":"2023-11-17","cited_by_count":14,"area":null},{"id":"2405.20441","title":"SECURE: Benchmarking Large Language Models for Cybersecurity","created":"2024-05-30","cited_by_count":14,"area":null},{"id":"2407.06071","title":"From Loops to Oops: Fallback Behaviors of Language Models Under Uncertainty","created":"2024-07-08","cited_by_count":14,"area":null},{"id":"2504.11972","title":"Reassessing Extractive QA Datasets at Scale: LLM-as-a-Judge and In-Depth Analyses","created":"2025-04-16","cited_by_count":14,"area":null},{"id":"2402.15400","title":"Faithful Temporal Question Answering over Heterogeneous Sources","created":"2024-02-23","cited_by_count":13,"area":null},{"id":"2312.08800","title":"Evaluating Large Language Models for Health-related Queries with Presuppositions","created":"2023-12-14","cited_by_count":12,"area":null},{"id":"2402.14833","title":"CliqueParcel: An Approach For Batching LLM Prompts That Jointly Optimizes Efficiency And Faithfulness","created":"2024-02-17","cited_by_count":12,"area":null},{"id":"2411.00489","title":"Human-inspired Perspectives: A Survey on AI Long-term Memory","created":"2024-11-01","cited_by_count":12,"area":null},{"id":"2406.06458","title":"Evaluating the Retrieval Component in LLM-Based Question Answering Systems","created":"2024-06-10","cited_by_count":11,"area":null},{"id":"2503.17073","title":"A Study into Investigating Temporal Robustness of LLMs","created":"2025-03-21","cited_by_count":11,"area":null},{"id":"2505.15807","title":"The Atlas of In-Context Learning: How Attention Heads Shape In-Context Retrieval Augmentation","created":"2025-05-21","cited_by_count":11,"area":null},{"id":"2410.10796","title":"Context-Parametric Inversion: Why Instruction Finetuning Can Worsen Context Reliance","created":"2024-10-14","cited_by_count":10,"area":null},{"id":"2509.04492","title":"Learned Hallucination Detection in Black-Box LLMs using Token-level Entropy Production Rate","created":"2025-09-01","cited_by_count":10,"area":null},{"id":"2311.09800","title":"$\\textit{Dial BeInfo for Faithfulness}$: Improving Factuality of Information-Seeking Dialogue via Behavioural Fine-Tuning","created":"2023-11-16","cited_by_count":9,"area":null},{"id":"2403.00827","title":"Self-Refinement of Language Models from External Proxy Metrics Feedback","created":"2024-02-27","cited_by_count":9,"area":null},{"id":"2501.00269","title":"A review of faithfulness metrics for hallucination assessment in Large Language Models","created":"2024-12-31","cited_by_count":9,"area":null},{"id":"2409.18216","title":"MMMT-IF: A Challenging Multimodal Multi-Turn Instruction Following Benchmark","created":"2024-09-26","cited_by_count":8,"area":null},{"id":"2405.20315","title":"ANAH: Analytical Annotation of Hallucinations in Large Language Models","created":"2024-05-30","cited_by_count":7,"area":null},{"id":"2409.11500","title":"Multi-Document Grounded Multi-Turn Synthetic Dialog Generation","created":"2024-09-17","cited_by_count":7,"area":null},{"id":"2311.08117","title":"Insights into Classifying and Mitigating LLMs' Hallucinations","created":"2023-11-14","cited_by_count":6,"area":null},{"id":"2406.09155","title":"DefAn: Definitive Answer Dataset for LLMs Hallucination Evaluation","created":"2024-06-13","cited_by_count":6,"area":null},{"id":"2409.11727","title":"Enabling Real-Time Conversations with Minimal Training Costs","created":"2024-09-18","cited_by_count":6,"area":null},{"id":"2410.10724","title":"Large Language Models Are Active Critics in NLG Evaluation","created":"2024-10-14","cited_by_count":6,"area":null},{"id":"2503.08542","title":"CLEV: LLM-Based Evaluation Through Lightweight Efficient Voting for Free-Form Question-Answering","created":"2025-03-11","cited_by_count":6,"area":null},{"id":"2504.18114","title":"Evaluating Evaluation Metrics -- The Mirage of Hallucination Detection","created":"2025-04-25","cited_by_count":6,"area":null},{"id":"2505.22630","title":"Stochastic Chameleons: Irrelevant Context Hallucinations Reveal Class-Based (Mis)Generalization in LLMs","created":"2025-05-28","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":"2403.14443","title":"Language Models Can Reduce Asymmetry in Information Markets","created":"2024-03-21","cited_by_count":5,"area":null},{"id":"2501.14733","title":"LLM as HPC Expert: Extending RAG Architecture for HPC Data","created":"2024-12-09","cited_by_count":5,"area":null},{"id":"2505.24040","title":"MedPAIR: Measuring Physicians and AI Relevance Alignment in Medical Question Answering","created":"2025-05-29","cited_by_count":5,"area":null},{"id":"2507.21914","title":"Rote Learning Considered Useful: Generalizing over Memorized Data in LLMs","created":"2025-07-29","cited_by_count":5,"area":null},{"id":"2601.07506","title":"Judging Against the Reference: Uncovering Knowledge-Driven Failures in LLM-Judges on QA Evaluation","created":"2026-01-12","cited_by_count":5,"area":null},{"id":"2503.22693","title":"Bridging Language Models and Financial Analysis","created":"2025-03-14","cited_by_count":4,"area":null},{"id":"2508.19475","title":"Automatic Question & Answer Generation Using Generative Large Language Model (LLM)","created":"2025-08-26","cited_by_count":4,"area":null},{"id":"2509.04304","title":"Facts Fade Fast: Evaluating Memorization of Outdated Medical Knowledge in Large Language Models","created":"2025-09-04","cited_by_count":4,"area":null},{"id":"2509.17445","title":"Semantic Reformulation Entropy for Robust Hallucination Detection in QA Tasks","created":"2025-09-22","cited_by_count":4,"area":null},{"id":"2601.16766","title":"Do LLM hallucination detectors suffer from low-resource effect?","created":"2026-01-23","cited_by_count":4,"area":null},{"id":"2412.12632","title":"What External Knowledge is Preferred by LLMs? Characterizing and Exploring Chain of Evidence in Imperfect Context for Multi-Hop QA","created":"2024-12-17","cited_by_count":3,"area":null},{"id":"2508.05283","title":"Decision-Making with Deliberation: Meta-reviewing as a Document-grounded Dialogue","created":"2025-08-07","cited_by_count":3,"area":null},{"id":"2508.15418","title":"LLaSO: A Foundational Framework for Reproducible Research in Large Language and Speech Model","created":"2025-08-21","cited_by_count":3,"area":null},{"id":"2509.24120","title":"EduVidQA: Generating and Evaluating Long-form Answers to Student Questions based on Lecture Videos","created":"2025-09-28","cited_by_count":3,"area":null},{"id":"2404.15650","title":"Return of EM: Entity-driven Answer Set Expansion for QA Evaluation","created":"2024-04-24","cited_by_count":2,"area":null},{"id":"2406.03428","title":"HelloFresh: LLM Evaluations on Streams of Real-World Human Editorial Actions across X Community Notes and Wikipedia edits","created":"2024-06-05","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":"2502.15723","title":"Balancing Content Size in RAG-Text2SQL System","created":"2025-01-28","cited_by_count":2,"area":null},{"id":"2509.11687","title":"A Dynamic Knowledge Update-Driven Model with Large Language Models for Fake News Detection","created":"2025-09-15","cited_by_count":2,"area":null},{"id":"2402.02077","title":"Investigating Content Planning for Navigating Trade-offs in Knowledge-Grounded Dialogue","created":"2024-02-03","cited_by_count":1,"area":null},{"id":"2407.00488","title":"PFME: A Modular Approach for Fine-grained Hallucination Detection and Editing of Large Language Models","created":"2024-06-29","cited_by_count":1,"area":null},{"id":"2410.10030","title":"A Step Towards Mixture of Grader: Statistical Analysis of Existing Automatic Evaluation Metrics","created":"2024-10-13","cited_by_count":1,"area":null},{"id":"2503.05857","title":"SYMBIOSIS: Systems Thinking and Machine Intelligence for Better Outcomes in Society","created":"2025-03-07","cited_by_count":1,"area":null},{"id":"2504.00584","title":"Semantic Adapter for Universal Text Embeddings: Diagnosing and Mitigating Negation Blindness to Enhance Universality","created":"2025-04-01","cited_by_count":1,"area":null},{"id":"2505.12265","title":"Learning Auxiliary Tasks Improves Reference-Free Hallucination Detection in Open-Domain Long-Form Generation","created":"2025-05-18","cited_by_count":1,"area":null},{"id":"2505.16178","title":"Understanding Fact Recall in Language Models: Why Two-Stage Training Encourages Memorization but Mixed Training Teaches Knowledge","created":"2025-05-22","cited_by_count":1,"area":null},{"id":"2508.11163","title":"MobQA: A Benchmark Dataset for Semantic Understanding of Human Mobility Data through Question Answering","created":"2025-08-15","cited_by_count":1,"area":null},{"id":"2605.25831","title":"Clarify, Abstain or Answer? Strategising in Conversation with Belief-Augmented Generation","created":"2026-05-25","cited_by_count":1,"area":null},{"id":"2607.02235","title":"Challenges and Recommendations for LLM-as-a-Judge in Multilingual Settings and for Low-Resource Languages","created":"2026-07-02","cited_by_count":1,"area":null},{"id":"2405.10745","title":"Empowering Small-Scale Knowledge Graphs: A Strategy of Leveraging General-Purpose Knowledge Graphs for Enriched Embeddings","created":"2024-05-17","cited_by_count":0,"area":null},{"id":"2407.12812","title":"Building Understandable Messaging for Policy and Evidence Review (BUMPER) with AI","created":"2024-06-27","cited_by_count":0,"area":null},{"id":"2409.17173","title":"A Multiple-Fill-in-the-Blank Exam Approach for Enhancing Zero-Resource Hallucination Detection in Large Language Models","created":"2024-09-20","cited_by_count":0,"area":null},{"id":"2506.17692","title":"Resource-Friendly Dynamic Enhancement Chain for Multi-Hop Question Answering","created":"2025-06-21","cited_by_count":0,"area":null},{"id":"2512.05700","title":"Faithfulness metric fusion: Improving the evaluation of LLM trustworthiness across domains","created":"2025-12-05","cited_by_count":0,"area":null},{"id":"2601.00641","title":"Probabilistic Guarantees for Reducing Contextual Hallucinations in LLMs","created":"2026-01-02","cited_by_count":0,"area":null},{"id":"2601.04524","title":"BioPIE: A Biomedical Protocol Information Extraction Dataset for Experiment Understanding","created":"2026-01-08","cited_by_count":0,"area":null},{"id":"2602.20300","title":"What Makes a Good Query? Measuring the Impact of Human-Confusing Linguistic Features on LLM Performance","created":"2026-02-23","cited_by_count":0,"area":null},{"id":"2603.29221","title":"SiPaKosa: A Comprehensive Corpus of Canonical and Classical Buddhist Texts in Sinhala and Pali","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2606.11945","title":"uva-irlab-conv at SemEval-2026 Task 8: Multi-Turn RAG with Learned Sparse Retrieval and Listwise Reranking","created":"2026-06-10","cited_by_count":0,"area":null},{"id":"2607.21961","title":"On Improving Faithfulness of Podcasts from Documents","created":"2026-07-24","cited_by_count":0,"area":null},{"id":"2608.26131","title":"Evaluating Language Models in Realistic Conversational Contexts","created":"2026-06-24","cited_by_count":0,"area":null},{"id":"2608.26168","title":"Hallucinations in LLMs: A Lifecycle-Based Survey of Causes, Detection, Mitigation, and Prevention","created":"2026-07-20","cited_by_count":0,"area":null},{"id":"2609.01369","title":"How Correct Is Your Answer? A Semantic Correctness Framework for Open QA Evaluation","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.24885","title":"The Copy Ceiling: An Input-Exposure Control for Ontology-Grounded Generation over Curated Corpora","created":"2026-09-21","cited_by_count":0,"area":null}],"next_cursor":null}