{"total":97,"rows":[{"id":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576,"area":null},{"id":"2202.03629","title":"Survey of Hallucination in Natural Language Generation","created":"2022-02-08","cited_by_count":2075,"area":null},{"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":"2111.09525","title":"SummaC: Re-Visiting NLI-based Models for Inconsistency Detection in Summarization","created":"2021-11-18","cited_by_count":407,"area":null},{"id":"2401.11817","title":"Hallucination is Inevitable: An Innate Limitation of Large Language Models","created":"2024-01-22","cited_by_count":332,"area":null},{"id":"2104.13346","title":"Understanding Factuality in Abstractive Summarization with FRANK: A Benchmark for Factuality Metrics","created":"2021-04-27","cited_by_count":287,"area":null},{"id":"2303.04226","title":"A Comprehensive Survey of AI-Generated Content (AIGC): A History of Generative AI from GAN to ChatGPT","created":"2023-03-07","cited_by_count":224,"area":null},{"id":"2206.04624","title":"Factuality Enhanced Language Models for Open-Ended Text Generation","created":"2022-06-09","cited_by_count":202,"area":null},{"id":"2209.15558","title":"Out-of-Distribution Detection and Selective Generation for Conditional Language Models","created":"2022-09-30","cited_by_count":197,"area":null},{"id":"2104.08704","title":"A Token-level Reference-free Hallucination Detection Benchmark for Free-form Text Generation","created":"2021-04-18","cited_by_count":138,"area":null},{"id":"2104.08202","title":"$Q^{2}$: Evaluating Factual Consistency in Knowledge-Grounded Dialogues via Question Generation and Question Answering","created":"2021-04-16","cited_by_count":132,"area":null},{"id":"2211.08412","title":"Evaluating the Factual Consistency of Large Language Models Through News Summarization","created":"2022-11-15","cited_by_count":92,"area":null},{"id":"2305.11171","title":"TrueTeacher: Learning Factual Consistency Evaluation with Large Language Models","created":"2023-05-18","cited_by_count":83,"area":null},{"id":"2104.14839","title":"The Factual Inconsistency Problem in Abstractive Text Summarization: A Survey","created":"2021-04-30","cited_by_count":79,"area":null},{"id":"2303.15621","title":"ChatGPT as a Factual Inconsistency Evaluator for Text Summarization","created":"2023-03-27","cited_by_count":75,"area":null},{"id":"2207.00939","title":"An Empirical Survey on Long Document Summarization: Datasets, Models and Metrics","created":"2022-07-03","cited_by_count":74,"area":null},{"id":"2305.14292","title":"WikiChat: Stopping the Hallucination of Large Language Model Chatbots by Few-Shot Grounding on Wikipedia","created":"2023-05-23","cited_by_count":67,"area":null},{"id":"2401.05778","title":"Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems","created":"2024-01-11","cited_by_count":66,"area":null},{"id":"2510.06265","title":"Large Language Models Hallucination: A Comprehensive Survey","created":"2025-10-05","cited_by_count":49,"area":null},{"id":"2407.06089","title":"Merge, Ensemble, and Cooperate! A Survey on Collaborative Strategies in the Era of Large Language Models","created":"2024-07-08","cited_by_count":44,"area":null},{"id":"2308.02312","title":"Is Stack Overflow Obsolete? An Empirical Study of the Characteristics of ChatGPT Answers to Stack Overflow Questions","created":"2023-08-04","cited_by_count":42,"area":null},{"id":"2204.06508","title":"FactGraph: Evaluating Factuality in Summarization with Semantic Graph Representations","created":"2022-04-13","cited_by_count":41,"area":null},{"id":"2403.11903","title":"A Closer Look at Claim Decomposition","created":"2024-03-18","cited_by_count":41,"area":null},{"id":"2210.12378","title":"Correcting Diverse Factual Errors in Abstractive Summarization via Post-Editing and Language Model Infilling","created":"2022-10-22","cited_by_count":38,"area":null},{"id":"2108.13134","title":"Factual Consistency Evaluation for Text Summarization via Counterfactual Estimation","created":"2021-08-30","cited_by_count":37,"area":null},{"id":"2103.08545","title":"A Study of Automatic Metrics for the Evaluation of Natural Language Explanations","created":"2021-03-15","cited_by_count":34,"area":null},{"id":"2205.06009","title":"Falsesum: Generating Document-level NLI Examples for Recognizing Factual Inconsistency in Summarization","created":"2022-05-12","cited_by_count":34,"area":null},{"id":"2405.02134","title":"Optimising Calls to Large Language Models with Uncertainty-Based Two-Tier Selection","created":"2024-05-03","cited_by_count":33,"area":null},{"id":"2402.10412","title":"Measuring and Reducing LLM Hallucination without Gold-Standard Answers","created":"2024-02-16","cited_by_count":31,"area":null},{"id":"2301.12307","title":"MQAG: Multiple-choice Question Answering and Generation for Assessing Information Consistency in Summarization","created":"2023-01-28","cited_by_count":30,"area":null},{"id":"2304.04358","title":"WebBrain: Learning to Generate Factually Correct Articles for Queries by Grounding on Large Web Corpus","created":"2023-04-10","cited_by_count":29,"area":null},{"id":"2203.05227","title":"Faithfulness in Natural Language Generation: A Systematic Survey of Analysis, Evaluation and Optimization Methods","created":"2022-03-10","cited_by_count":27,"area":null},{"id":"2210.16732","title":"How Far are We from Robust Long Abstractive Summarization?","created":"2022-10-30","cited_by_count":25,"area":null},{"id":"2102.08585","title":"Towards Faithfulness in Open Domain Table-to-text Generation from an Entity-centric View","created":"2021-02-17","cited_by_count":24,"area":null},{"id":"2310.11648","title":"Zero-shot Faithfulness Evaluation for Text Summarization with Foundation Language Model","created":"2023-10-18","cited_by_count":21,"area":null},{"id":"2110.12680","title":"TODSum: Task-Oriented Dialogue Summarization with State Tracking","created":"2021-10-25","cited_by_count":19,"area":null},{"id":"2502.10855","title":"Towards Effective Extraction and Evaluation of Factual Claims","created":"2025-02-15","cited_by_count":19,"area":null},{"id":"2405.15604","title":"Text Generation: A Systematic Literature Review of Tasks, Evaluation, and Challenges","created":"2024-05-24","cited_by_count":18,"area":null},{"id":"2411.05375","title":"Ev2R: Evaluating Evidence Retrieval in Automated Fact-Checking","created":"2024-11-08","cited_by_count":18,"area":null},{"id":"2404.11588","title":"Related Work and Citation Text Generation: A Survey","created":"2024-04-17","cited_by_count":17,"area":null},{"id":"2108.02859","title":"Evaluating the Tradeoff Between Abstractiveness and Factuality in Abstractive Summarization","created":"2021-08-05","cited_by_count":16,"area":null},{"id":"2306.06264","title":"Measuring and Modifying Factual Knowledge in Large Language Models","created":"2023-06-09","cited_by_count":16,"area":null},{"id":"2404.11184","title":"FIZZ: Factual Inconsistency Detection by Zoom-in Summary and Zoom-out Document","created":"2024-04-17","cited_by_count":15,"area":null},{"id":"2303.03948","title":"A Meta-Evaluation of Faithfulness Metrics for Long-Form Hospital-Course Summarization","created":"2023-03-07","cited_by_count":14,"area":null},{"id":"2306.00419","title":"Challenges and Remedies to Privacy and Security in AIGC: Exploring the Potential of Privacy Computing, Blockchain, and Beyond","created":"2023-06-01","cited_by_count":14,"area":null},{"id":"2306.06199","title":"Reliability Check: An Analysis of GPT-3's Response to Sensitive Topics and Prompt Wording","created":"2023-06-09","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":"2106.00219","title":"Question-aware Transformer Models for Consumer Health Question Summarization","created":"2021-06-01","cited_by_count":11,"area":null},{"id":"2109.11020","title":"Exploring Decomposition for Table-based Fact Verification","created":"2021-09-22","cited_by_count":11,"area":null},{"id":"2305.12191","title":"Pointwise Mutual Information Based Metric and Decoding Strategy for Faithful Generation in Document Grounded Dialogs","created":"2023-05-20","cited_by_count":11,"area":null},{"id":"2311.09521","title":"AMRFact: Enhancing Summarization Factuality Evaluation with AMR-Driven Negative Samples Generation","created":"2023-11-16","cited_by_count":11,"area":null},{"id":"2305.14069","title":"Evaluating Factual Consistency of Summaries with Large Language Models","created":"2023-05-23","cited_by_count":10,"area":null},{"id":"2112.01147","title":"CO2Sum:Contrastive Learning for Factual-Consistent Abstractive Summarization","created":"2021-12-02","cited_by_count":9,"area":null},{"id":"2310.19626","title":"Transformation vs Tradition: Artificial General Intelligence (AGI) for Arts and Humanities","created":"2023-10-30","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":"2305.03276","title":"Expository Text Generation: Imitate, Retrieve, Paraphrase","created":"2023-05-05","cited_by_count":8,"area":null},{"id":"2203.10133","title":"Probing Factually Grounded Content Transfer with Factual Ablation","created":"2022-03-18","cited_by_count":7,"area":null},{"id":"2204.05879","title":"Generating Full Length Wikipedia Biographies: The Impact of Gender Bias on the Retrieval-Based Generation of Women Biographies","created":"2022-04-12","cited_by_count":7,"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":"2406.01855","title":"TruthEval: A Dataset to Evaluate LLM Truthfulness and Reliability","created":"2024-06-04","cited_by_count":7,"area":null},{"id":"2408.10645","title":"CoRA: Collaborative Information Perception by Large Language Model's Weights for Recommendation","created":"2024-08-20","cited_by_count":7,"area":null},{"id":"2503.16541","title":"Poly-FEVER: A Multilingual Fact Verification Benchmark for Hallucination Detection in Large Language Models","created":"2025-03-19","cited_by_count":7,"area":null},{"id":"2102.09681","title":"WebRED: Effective Pretraining And Finetuning For Relation Extraction On The Web","created":"2021-02-18","cited_by_count":5,"area":null},{"id":"2307.00963","title":"Challenges in Domain-Specific Abstractive Summarization and How to Overcome them","created":"2023-07-03","cited_by_count":5,"area":null},{"id":"2402.02547","title":"Integration of cognitive tasks into artificial general intelligence test for large models","created":"2024-02-04","cited_by_count":5,"area":null},{"id":"2208.13265","title":"Podcast Summary Assessment: A Resource for Evaluating Summary Assessment Methods","created":"2022-08-28","cited_by_count":4,"area":null},{"id":"2212.01611","title":"CoP: Factual Inconsistency Detection by Controlling the Preference","created":"2022-12-03","cited_by_count":4,"area":null},{"id":"2305.13309","title":"Evaluating Factual Consistency of Texts with Semantic Role Labeling","created":"2023-05-22","cited_by_count":4,"area":null},{"id":"2203.15959","title":"Entity-driven Fact-aware Abstractive Summarization of Biomedical Literature","created":"2022-03-30","cited_by_count":3,"area":null},{"id":"2510.06107","title":"Distributional Semantics Tracing: A Framework for Explaining Hallucinations in Large Language Models","created":"2025-10-07","cited_by_count":3,"area":null},{"id":"2204.00797","title":"Improving the Factual Accuracy of Abstractive Clinical Text Summarization using Multi-Objective Optimization","created":"2022-04-02","cited_by_count":2,"area":null},{"id":"2308.15711","title":"Optimizing Factual Accuracy in Text Generation through Dynamic Knowledge Selection","created":"2023-08-30","cited_by_count":2,"area":null},{"id":"2310.10495","title":"Metric Ensembles For Hallucination Detection","created":"2023-10-16","cited_by_count":2,"area":null},{"id":"2402.18264","title":"WIKIGENBENCH: Exploring Full-length Wikipedia Generation under Real-World Scenario","created":"2024-02-28","cited_by_count":2,"area":null},{"id":"2502.20647","title":"Consistency Evaluation of News Article Summaries Generated by Large (and Small) Language Models","created":"2025-02-28","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":"2505.16392","title":"Resource for Error Analysis in Text Simplification: New Taxonomy and Test Collection","created":"2025-05-22","cited_by_count":2,"area":null},{"id":"2605.17007","title":"HalluScore: Large Language Model Hallucination Question Answering Benchmark","created":"2026-05-16","cited_by_count":2,"area":null},{"id":"2102.05924","title":"Toward Improving Coherence and Diversity of Slogan Generation","created":"2021-02-11","cited_by_count":1,"area":null},{"id":"2305.10736","title":"Counterfactual Debiasing for Generating Factually Consistent Text Summaries","created":"2023-05-18","cited_by_count":1,"area":null},{"id":"2311.13273","title":"Comparative Experimentation of Accuracy Metrics in Automated Medical Reporting: The Case of Otitis Consultations","created":"2023-11-22","cited_by_count":1,"area":null},{"id":"2402.13758","title":"Factual consistency evaluation of summarization in the Era of large language models","created":"2024-02-21","cited_by_count":1,"area":null},{"id":"2503.01921","title":"NCL-UoR at SemEval-2025 Task 3: Detecting Multilingual Hallucination and Related Observable Overgeneration Text Spans with Modified RefChecker and Modified SeflCheckGPT","created":"2025-03-02","cited_by_count":1,"area":null},{"id":"2102.10956","title":"Few Shot Learning for Information Verification","created":"2021-02-22","cited_by_count":0,"area":null},{"id":"2204.04869","title":"Evaluation of Automatic Text Summarization using Synthetic Facts","created":"2022-04-11","cited_by_count":0,"area":null},{"id":"2210.00667","title":"Probing of Quantitative Values in Abstractive Summarization Models","created":"2022-10-03","cited_by_count":0,"area":null},{"id":"2211.13883","title":"Learning with Silver Standard Data for Zero-shot Relation Extraction","created":"2022-11-25","cited_by_count":0,"area":null},{"id":"2303.06002","title":"Is In-hospital Meta-information Useful for Abstractive Discharge Summary Generation?","created":"2023-03-10","cited_by_count":0,"area":null},{"id":"2403.04964","title":"Tell me the truth: A system to measure the trustworthiness of Large Language Models","created":"2024-03-08","cited_by_count":0,"area":null},{"id":"2403.07557","title":"SIFiD: Reassess Summary Factual Inconsistency Detection with LLM","created":"2024-03-12","cited_by_count":0,"area":null},{"id":"2406.02943","title":"The Task-oriented Queries Benchmark (ToQB)","created":"2024-06-05","cited_by_count":0,"area":null},{"id":"2502.11113","title":"Valuable Hallucinations: Realizable Non-realistic Propositions","created":"2025-02-16","cited_by_count":0,"area":null},{"id":"2510.16783","title":"LC-Eval: A Bilingual Multi-Task Evaluation Benchmark for Long-Context Understanding","created":"2025-10-19","cited_by_count":0,"area":null},{"id":"2512.03634","title":"AlignCheck: a Semantic Open-Domain Metric for Factual Consistency Assessment","created":"2025-12-03","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":"2602.08709","title":"FactSim: Fact-Checking for Opinion Summarization","created":"2026-02-09","cited_by_count":0,"area":null},{"id":"2604.19281","title":"Beyond Semantic Similarity: A Component-Wise Evaluation Framework for Medical Question Answering Systems with Health Equity Implications","created":"2026-04-21","cited_by_count":0,"area":null}],"next_cursor":null}