{"total":37,"rows":[{"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":"2305.08281","title":"FactKB: Generalizable Factuality Evaluation using Language Models Enhanced with Factual Knowledge","created":"2023-05-14","cited_by_count":55,"area":null},{"id":"2501.05435","title":"Neuro-Symbolic AI in 2024: A Systematic Review","created":"2025-01-09","cited_by_count":38,"area":null},{"id":"2303.03278","title":"Faithfulness-Aware Decoding Strategies for Abstractive Summarization","created":"2023-03-06","cited_by_count":31,"area":null},{"id":"2407.10793","title":"GraphEval: A Knowledge-Graph Based LLM Hallucination Evaluation Framework","created":"2024-07-15","cited_by_count":30,"area":null},{"id":"2411.14258","title":"Knowledge Graphs, Large Language Models, and Hallucinations: An NLP Perspective","created":"2024-11-21","cited_by_count":29,"area":null},{"id":"2403.02270","title":"FENICE: Factuality Evaluation of summarization based on Natural language Inference and Claim Extraction","created":"2024-03-04","cited_by_count":28,"area":null},{"id":"2305.07982","title":"Zero-shot Faithful Factual Error Correction","created":"2023-05-13","cited_by_count":26,"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":"2402.17630","title":"Fine-Grained Natural Language Inference Based Faithfulness Evaluation for Diverse Summarisation Tasks","created":"2024-02-27","cited_by_count":23,"area":null},{"id":"2404.05904","title":"The Hallucinations Leaderboard -- An Open Effort to Measure Hallucinations in Large Language Models","created":"2024-04-08","cited_by_count":17,"area":null},{"id":"2403.00896","title":"DiaHalu: A Dialogue-level Hallucination Evaluation Benchmark for Large Language Models","created":"2024-03-01","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":"2410.07473","title":"Localizing Factual Inconsistencies in Attributable Text Generation","created":"2024-10-09","cited_by_count":14,"area":null},{"id":"2502.16514","title":"GraphCheck: Breaking Long-Term Text Barriers with Extracted Knowledge Graph-Powered Fact-Checking","created":"2025-02-23","cited_by_count":12,"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":"2210.06461","title":"Better Smatch = Better Parser? AMR evaluation is not so simple anymore","created":"2022-10-12","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":"2404.12041","title":"A Survey of Automatic Hallucination Evaluation on Natural Language Generation","created":"2024-04-18","cited_by_count":7,"area":null},{"id":"2305.14548","title":"Interpretable Automatic Fine-grained Inconsistency Detection in Text Summarization","created":"2023-05-23","cited_by_count":6,"area":null},{"id":"2503.01670","title":"Evaluating LLMs' Assessment of Mixed-Context Hallucination Through the Lens of Summarization","created":"2025-03-03","cited_by_count":6,"area":null},{"id":"2310.14909","title":"Linking Surface Facts to Large-Scale Knowledge Graphs","created":"2023-10-23","cited_by_count":5,"area":null},{"id":"2404.01588","title":"Hallucination Diversity-Aware Active Learning for Text Summarization","created":"2024-04-02","cited_by_count":5,"area":null},{"id":"2305.14163","title":"Leveraging Open Information Extraction for More Robust Domain Transfer of Event Trigger Detection","created":"2023-05-23","cited_by_count":4,"area":null},{"id":"2406.06589","title":"PatentEval: Understanding Errors in Patent Generation","created":"2024-06-05","cited_by_count":3,"area":null},{"id":"2507.19586","title":"Mitigating Geospatial Knowledge Hallucination in Large Language Models: Benchmarking and Dynamic Factuality Aligning","created":"2025-07-25","cited_by_count":3,"area":null},{"id":"2204.07551","title":"Summarization with Graphical Elements","created":"2022-04-15","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":"2305.10736","title":"Counterfactual Debiasing for Generating Factually Consistent Text Summaries","created":"2023-05-18","cited_by_count":1,"area":null},{"id":"2404.02126","title":"Rematch: Robust and Efficient Matching of Local Knowledge Graphs to Improve Structural and Semantic Similarity","created":"2024-04-02","cited_by_count":1,"area":null},{"id":"2405.09153","title":"Adapting Abstract Meaning Representation Parsing to the Clinical Narrative -- the SPRING THYME parser","created":"2024-05-15","cited_by_count":1,"area":null},{"id":"2505.17855","title":"Explaining Sources of Uncertainty in Automated Fact-Checking","created":"2025-05-23","cited_by_count":1,"area":null},{"id":"2601.06666","title":"InFi-Check: Interpretable and Fine-Grained Fact-Checking of LLMs","created":"2026-01-10","cited_by_count":1,"area":null},{"id":"2306.00936","title":"AMR4NLI: Interpretable and robust NLI measures from semantic graphs","created":"2023-06-01","cited_by_count":0,"area":null},{"id":"2403.15407","title":"X-AMR Annotation Tool","created":"2024-02-29","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":"2603.06135","title":"A Counterfactual Graph Approach to Oppositional Narrative Analysis","created":"2026-03-06","cited_by_count":0,"area":null}],"next_cursor":null}