{"list":"other","total":51,"rows":[{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"2204.05862","title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","created":"2022-04-12","cited_by_count":3720},{"id":"2109.07958","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","created":"2021-09-08","cited_by_count":2975},{"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},{"id":"2207.04672","title":"No Language Left Behind: Scaling Human-Centered Machine Translation","created":"2022-07-11","cited_by_count":1312},{"id":"2305.14251","title":"FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation","created":"2023-05-23","cited_by_count":1282},{"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},{"id":"2306.08302","title":"Unifying Large Language Models and Knowledge Graphs: A Roadmap","created":"2023-06-14","cited_by_count":668},{"id":"1910.09700","title":"Quantifying the Carbon Emissions of Machine Learning","created":"2019-10-21","cited_by_count":521},{"id":"2411.16594","title":"From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judge","created":"2024-11-25","cited_by_count":494},{"id":"2411.04368","title":"Measuring short-form factuality in large language models","created":"2024-11-07","cited_by_count":373},{"id":"2402.05672","title":"Multilingual E5 Text Embeddings: A Technical Report","created":"2024-02-08","cited_by_count":372},{"id":"2402.19473","title":"Retrieval-Augmented Generation for AI-Generated Content: A Survey","created":"2024-02-29","cited_by_count":354},{"id":"2305.11747","title":"HaluEval: A Large-Scale Hallucination Evaluation Benchmark for Large Language Models","created":"2023-05-19","cited_by_count":341},{"id":"2310.01061","title":"Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning","created":"2023-10-02","cited_by_count":328},{"id":"2408.08921","title":"Graph Retrieval-Augmented Generation: A Survey","created":"2024-08-15","cited_by_count":324},{"id":"2401.00595","title":"State of What Art? A Call for Multi-Prompt LLM Evaluation","created":"2023-12-31","cited_by_count":310},{"id":"2401.00396","title":"RAGTruth: A Hallucination Corpus for Developing Trustworthy Retrieval-Augmented Language Models","created":"2023-12-31","cited_by_count":283},{"id":"2407.02485","title":"RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMs","created":"2024-07-02","cited_by_count":202},{"id":"2007.15207","title":"MKQA: A Linguistically Diverse Benchmark for Multilingual Open Domain Question Answering","created":"2020-07-30","cited_by_count":153},{"id":"2310.05189","title":"Factuality Challenges in the Era of Large Language Models","created":"2023-10-08","cited_by_count":126},{"id":"2502.13595","title":"MMTEB: Massive Multilingual Text Embedding Benchmark","created":"2025-02-19","cited_by_count":125},{"id":"2310.10378","title":"Cross-Lingual Consistency of Factual Knowledge in Multilingual Language Models","created":"2023-10-16","cited_by_count":118},{"id":"2504.17550","title":"HalluLens: LLM Hallucination Benchmark","created":"2025-04-24","cited_by_count":92},{"id":"2302.11529","title":"Modular Deep Learning","created":"2023-02-22","cited_by_count":83},{"id":"2405.17202","title":"Efficient multi-prompt evaluation of LLMs","created":"2024-05-27","cited_by_count":73},{"id":"2210.01613","title":"Mintaka: A Complex, Natural, and Multilingual Dataset for End-to-End Question Answering","created":"2022-10-04","cited_by_count":72},{"id":"2308.06374","title":"Large Language Models and Knowledge Graphs: Opportunities and Challenges","created":"2023-08-11","cited_by_count":71},{"id":"2311.13314","title":"Mitigating Large Language Model Hallucinations via Autonomous Knowledge Graph-based Retrofitting","created":"2023-11-22","cited_by_count":70},{"id":"2404.14741","title":"Generate-on-Graph: Treat LLM as both Agent and KG in Incomplete Knowledge Graph Question Answering","created":"2024-04-23","cited_by_count":60},{"id":"2305.06590","title":"FactKG: Fact Verification via Reasoning on Knowledge Graphs","created":"2023-05-11","cited_by_count":57},{"id":"2407.08488","title":"Lynx: An Open Source Hallucination Evaluation Model","created":"2024-07-11","cited_by_count":57},{"id":"2405.12035","title":"KG-RAG: Bridging the Gap Between Knowledge and Creativity","created":"2024-05-20","cited_by_count":56},{"id":"2204.06508","title":"FactGraph: Evaluating Factuality in Summarization with Semantic Graph Representations","created":"2022-04-13","cited_by_count":41},{"id":"2005.04308","title":"Building a PubMed knowledge graph","created":"2020-05-08","cited_by_count":38},{"id":"2402.06647","title":"A Survey on Large Language Model Hallucination via a Creativity Perspective","created":"2024-02-02","cited_by_count":38},{"id":"2407.10793","title":"GraphEval: A Knowledge-Graph Based LLM Hallucination Evaluation Framework","created":"2024-07-15","cited_by_count":30},{"id":"2411.14258","title":"Knowledge Graphs, Large Language Models, and Hallucinations: An NLP Perspective","created":"2024-11-21","cited_by_count":29},{"id":"2408.11832","title":"OpenFactCheck: A Unified Framework for Factuality Evaluation of LLMs","created":"2024-08-06","cited_by_count":28},{"id":"2310.17119","title":"FLEEK: Factual Error Detection and Correction with Evidence Retrieved from External Knowledge","created":"2023-10-26","cited_by_count":25},{"id":"2403.07726","title":"SemEval-2024 Shared Task 6: SHROOM, a Shared-task on Hallucinations and Related Observable Overgeneration Mistakes","created":"2024-03-12","cited_by_count":24},{"id":"2402.17630","title":"Fine-Grained Natural Language Inference Based Faithfulness Evaluation for Diverse Summarisation Tasks","created":"2024-02-27","cited_by_count":23},{"id":"1912.11270","title":"Falcon 2.0: An Entity and Relation Linking Tool over Wikidata","created":"2019-12-24","cited_by_count":21},{"id":"2503.00353","title":"U-NIAH: Unified RAG and LLM Evaluation for Long Context Needle-In-A-Haystack","created":"2025-03-01","cited_by_count":20},{"id":"2407.06564","title":"Combining Knowledge Graphs and Large Language Models","created":"2024-07-09","cited_by_count":16},{"id":"2406.12128","title":"AI \"News\" Content Farms Are Easy to Make and Hard to Detect: A Case Study in Italian","created":"2024-06-17","cited_by_count":12},{"id":"2408.08688","title":"The Fellowship of the LLMs: Multi-Model Workflows for Synthetic Preference Optimization Dataset Generation","created":"2024-08-16","cited_by_count":11},{"id":"2410.18270","title":"Multilingual Hallucination Gaps in Large Language Models","created":"2024-10-23","cited_by_count":7},{"id":"2406.09155","title":"DefAn: Definitive Answer Dataset for LLMs Hallucination Evaluation","created":"2024-06-13","cited_by_count":6},{"id":"2407.06041","title":"MST5 -- Multilingual Question Answering over Knowledge Graphs","created":"2024-07-08","cited_by_count":5},{"id":"2501.13824","title":"Can Hallucinations Help? Boosting LLMs for Drug Discovery","created":"2025-01-23","cited_by_count":2}],"next_cursor":null}