{"total":124,"rows":[{"id":"2109.07958","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","created":"2021-09-08","cited_by_count":2975,"area":null},{"id":"2202.03629","title":"Survey of Hallucination in Natural Language Generation","created":"2022-02-08","cited_by_count":2075,"area":null},{"id":"2305.14627","title":"Enabling Large Language Models to Generate Text with Citations","created":"2023-05-24","cited_by_count":595,"area":null},{"id":"2109.02846","title":"Datasets: A Community Library for Natural Language Processing","created":"2021-09-07","cited_by_count":530,"area":null},{"id":"2109.05052","title":"Entity-Based Knowledge Conflicts in Question Answering","created":"2021-09-10","cited_by_count":356,"area":null},{"id":"2210.08726","title":"RARR: Researching and Revising What Language Models Say, Using Language Models","created":"2022-10-17","cited_by_count":287,"area":null},{"id":"2204.06092","title":"ASQA: Factoid Questions Meet Long-Form Answers","created":"2022-04-12","cited_by_count":234,"area":null},{"id":"2104.00369","title":"FeTaQA: Free-form Table Question Answering","created":"2021-04-01","cited_by_count":175,"area":null},{"id":"2306.04181","title":"Benchmarking Foundation Models with Language-Model-as-an-Examiner","created":"2023-06-07","cited_by_count":172,"area":null},{"id":"2306.10193","title":"Conformal Language Modeling","created":"2023-06-16","cited_by_count":170,"area":null},{"id":"2401.01301","title":"Large Legal Fictions: Profiling Legal Hallucinations in Large Language Models","created":"2024-01-02","cited_by_count":150,"area":null},{"id":"2210.13701","title":"Rich Knowledge Sources Bring Complex Knowledge Conflicts: Recalibrating Models to Reflect Conflicting Evidence","created":"2022-10-25","cited_by_count":144,"area":null},{"id":"2305.15852","title":"Self-contradictory Hallucinations of Large Language Models: Evaluation, Detection and Mitigation","created":"2023-05-25","cited_by_count":124,"area":null},{"id":"2307.02762","title":"PRD: Peer Rank and Discussion Improve Large Language Model based Evaluations","created":"2023-07-06","cited_by_count":114,"area":null},{"id":"2305.18201","title":"A Critical Evaluation of Evaluations for Long-form Question Answering","created":"2023-05-29","cited_by_count":111,"area":null},{"id":"2202.12299","title":"Capturing Failures of Large Language Models via Human Cognitive Biases","created":"2022-02-24","cited_by_count":98,"area":null},{"id":"2309.07852","title":"ExpertQA: Expert-Curated Questions and Attributed Answers","created":"2023-09-14","cited_by_count":97,"area":null},{"id":"2301.13298","title":"LongEval: Guidelines for Human Evaluation of Faithfulness in Long-form Summarization","created":"2023-01-30","cited_by_count":96,"area":null},{"id":"2305.06849","title":"WebCPM: Interactive Web Search for Chinese Long-form Question Answering","created":"2023-05-11","cited_by_count":93,"area":null},{"id":"2109.09115","title":"Do Long-Range Language Models Actually Use Long-Range Context?","created":"2021-09-19","cited_by_count":92,"area":null},{"id":"2107.12708","title":"QA Dataset Explosion: A Taxonomy of NLP Resources for Question Answering and Reading Comprehension","created":"2021-07-27","cited_by_count":91,"area":null},{"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":"2205.09726","title":"RankGen: Improving Text Generation with Large Ranking Models","created":"2022-05-19","cited_by_count":72,"area":null},{"id":"2211.17257","title":"CREPE: Open-Domain Question Answering with False Presuppositions","created":"2022-11-30","cited_by_count":72,"area":null},{"id":"2112.09924","title":"The Web Is Your Oyster - Knowledge-Intensive NLP against a Very Large Web Corpus","created":"2021-12-18","cited_by_count":60,"area":null},{"id":"2104.08727","title":"GooAQ: Open Question Answering with Diverse Answer Types","created":"2021-04-18","cited_by_count":53,"area":null},{"id":"2305.14908","title":"PURR: Efficiently Editing Language Model Hallucinations by Denoising Language Model Corruptions","created":"2023-05-24","cited_by_count":53,"area":null},{"id":"2502.14127","title":"Which of These Best Describes Multiple Choice Evaluation with LLMs? A) Forced B) Flawed C) Fixable D) All of the Above","created":"2025-02-19","cited_by_count":52,"area":null},{"id":"2205.11465","title":"SQuALITY: Building a Long-Document Summarization Dataset the Hard Way","created":"2022-05-23","cited_by_count":50,"area":null},{"id":"2509.00496","title":"ResearchQA: Evaluating Scholarly Question Answering at Scale Across 75 Fields with Survey-Mined Questions and Rubrics","created":"2025-08-30","cited_by_count":49,"area":null},{"id":"2307.02394","title":"Won't Get Fooled Again: Answering Questions with False Premises","created":"2023-07-05","cited_by_count":48,"area":null},{"id":"2203.00343","title":"Read before Generate! Faithful Long Form Question Answering with Machine Reading","created":"2022-03-01","cited_by_count":47,"area":null},{"id":"2310.12150","title":"Understanding Retrieval Augmentation for Long-Form Question Answering","created":"2023-10-18","cited_by_count":45,"area":null},{"id":"2204.03508","title":"A Survey of Multi-task Learning in Natural Language Processing: Regarding Task Relatedness and Training Methods","created":"2022-04-07","cited_by_count":42,"area":null},{"id":"2305.11541","title":"Empower Large Language Model to Perform Better on Industrial Domain-Specific Question Answering","created":"2023-05-19","cited_by_count":41,"area":null},{"id":"2109.00087","title":"It's not Rocket Science : Interpreting Figurative Language in Narratives","created":"2021-08-31","cited_by_count":39,"area":null},{"id":"2112.08634","title":"FRUIT: Faithfully Reflecting Updated Information in Text","created":"2021-12-16","cited_by_count":39,"area":null},{"id":"2105.00816","title":"What's in a Summary? Laying the Groundwork for Advances in Hospital-Course Summarization","created":"2021-04-12","cited_by_count":35,"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":"2406.17761","title":"CaLMQA: Exploring culturally specific long-form question answering across 23 languages","created":"2024-06-25","cited_by_count":31,"area":null},{"id":"2109.01156","title":"Challenges in Generalization in Open Domain Question Answering","created":"2021-09-02","cited_by_count":30,"area":null},{"id":"2210.04186","title":"Analogy Generation by Prompting Large Language Models: A Case Study of InstructGPT","created":"2022-10-09","cited_by_count":27,"area":null},{"id":"2501.14956","title":"ExPerT: Effective and Explainable Evaluation of Personalized Long-Form Text Generation","created":"2025-01-24","cited_by_count":26,"area":null},{"id":"2401.15042","title":"PROXYQA: An Alternative Framework for Evaluating Long-Form Text Generation with Large Language Models","created":"2024-01-26","cited_by_count":24,"area":null},{"id":"2402.12869","title":"Exploring the Impact of Table-to-Text Methods on Augmenting LLM-based Question Answering with Domain Hybrid Data","created":"2024-02-20","cited_by_count":24,"area":null},{"id":"2405.00982","title":"On the Evaluation of Machine-Generated Reports","created":"2024-05-02","cited_by_count":23,"area":null},{"id":"2409.00509","title":"LongRecipe: Recipe for Efficient Long Context Generalization in Large Language Models","created":"2024-08-31","cited_by_count":23,"area":null},{"id":"2502.13668","title":"PeerQA: A Scientific Question Answering Dataset from Peer Reviews","created":"2025-02-19","cited_by_count":22,"area":null},{"id":"2305.15099","title":"Fourier Transformer: Fast Long Range Modeling by Removing Sequence Redundancy with FFT Operator","created":"2023-05-24","cited_by_count":20,"area":null},{"id":"2405.12701","title":"OLAPH: Improving Factuality in Biomedical Long-form Question Answering","created":"2024-05-21","cited_by_count":20,"area":null},{"id":"2111.00701","title":"Discourse Comprehension: A Question Answering Framework to Represent Sentence Connections","created":"2021-11-01","cited_by_count":19,"area":null},{"id":"2203.11048","title":"How Do We Answer Complex Questions: Discourse Structure of Long-form Answers","created":"2022-03-21","cited_by_count":19,"area":null},{"id":"2302.09170","title":"KILM: Knowledge Injection into Encoder-Decoder Language Models","created":"2023-02-17","cited_by_count":19,"area":null},{"id":"2501.15595","title":"SedarEval: Automated Evaluation using Self-Adaptive Rubrics","created":"2025-01-26","cited_by_count":19,"area":null},{"id":"2203.10053","title":"RELIC: Retrieving Evidence for Literary Claims","created":"2022-03-18","cited_by_count":18,"area":null},{"id":"2404.05411","title":"Know When To Stop: A Study of Semantic Drift in Text Generation","created":"2024-04-08","cited_by_count":18,"area":null},{"id":"2505.14279","title":"YESciEval: Robust LLM-as-a-Judge for Scientific Question Answering","created":"2025-05-20","cited_by_count":16,"area":null},{"id":"2406.13375","title":"ALiiCE: Evaluating Positional Fine-grained Citation Generation","created":"2024-06-19","cited_by_count":15,"area":null},{"id":"2207.06366","title":"N-Grammer: Augmenting Transformers with latent n-grams","created":"2022-07-13","cited_by_count":14,"area":null},{"id":"2311.09585","title":"LifeTox: Unveiling Implicit Toxicity in Life Advice","created":"2023-11-16","cited_by_count":14,"area":null},{"id":"2406.13124","title":"Learning to Generate Answers with Citations via Factual Consistency Models","created":"2024-06-19","cited_by_count":13,"area":null},{"id":"2204.03084","title":"Knowledge Infused Decoding","created":"2022-04-06","cited_by_count":12,"area":null},{"id":"2404.11826","title":"AdvisorQA: Towards Helpful and Harmless Advice-seeking Question Answering with Collective Intelligence","created":"2024-04-18","cited_by_count":12,"area":null},{"id":"2405.15329","title":"DnA-Eval: Enhancing Large Language Model Evaluation through Decomposition and Aggregation","created":"2024-05-24","cited_by_count":12,"area":null},{"id":"2402.11176","title":"KnowTuning: Knowledge-aware Fine-tuning for Large Language Models","created":"2024-02-17","cited_by_count":11,"area":null},{"id":"2409.08435","title":"When Context Leads but Parametric Memory Follows in Large Language Models","created":"2024-09-13","cited_by_count":11,"area":null},{"id":"2111.14232","title":"Long-range and hierarchical language predictions in brains and algorithms","created":"2021-11-28","cited_by_count":10,"area":null},{"id":"2502.16612","title":"MemeIntel: Explainable Detection of Propagandistic and Hateful Memes","created":"2025-02-23","cited_by_count":10,"area":null},{"id":"2405.05938","title":"DOLOMITES: Domain-Specific Long-Form Methodical Tasks","created":"2024-05-09","cited_by_count":8,"area":null},{"id":"2205.09278","title":"Modeling Exemplification in Long-form Question Answering via Retrieval","created":"2022-05-19","cited_by_count":7,"area":null},{"id":"2210.06349","title":"Context Generation Improves Open Domain Question Answering","created":"2022-10-12","cited_by_count":7,"area":null},{"id":"2305.19271","title":"Concise Answers to Complex Questions: Summarization of Long-form Answers","created":"2023-05-30","cited_by_count":7,"area":null},{"id":"2403.01774","title":"WebCiteS: Attributed Query-Focused Summarization on Chinese Web Search Results with Citations","created":"2024-03-04","cited_by_count":7,"area":null},{"id":"2410.06203","title":"Integrating Planning into Single-Turn Long-Form Text Generation","created":"2024-10-08","cited_by_count":7,"area":null},{"id":"2210.11536","title":"CONSISTENT: Open-Ended Question Generation From News Articles","created":"2022-10-20","cited_by_count":6,"area":null},{"id":"2207.05875","title":"A Novel DeBERTa-based Model for Financial Question Answering Task","created":"2022-07-12","cited_by_count":5,"area":null},{"id":"2209.12617","title":"Evaluation of Question Answering Systems: Complexity of judging a natural language","created":"2022-09-10","cited_by_count":5,"area":null},{"id":"2310.18794","title":"Sequence-Level Certainty Reduces Hallucination In Knowledge-Grounded Dialogue Generation","created":"2023-10-28","cited_by_count":5,"area":null},{"id":"2409.14744","title":"LINKAGE: Listwise Ranking among Varied-Quality References for Non-Factoid QA Evaluation via LLMs","created":"2024-09-23","cited_by_count":5,"area":null},{"id":"2112.07536","title":"Tackling Query-Focused Summarization as A Knowledge-Intensive Task: A Pilot Study","created":"2021-12-14","cited_by_count":4,"area":null},{"id":"2201.09651","title":"Artefact Retrieval: Overview of NLP Models with Knowledge Base Access","created":"2022-01-24","cited_by_count":4,"area":null},{"id":"2201.11094","title":"SCAI-QReCC Shared Task on Conversational Question Answering","created":"2022-01-26","cited_by_count":4,"area":null},{"id":"2308.06488","title":"Generating Faithful Text From a Knowledge Graph with Noisy Reference Text","created":"2023-08-12","cited_by_count":4,"area":null},{"id":"2310.16147","title":"PreWoMe: Exploiting Presuppositions as Working Memory for Long Form Question Answering","created":"2023-10-24","cited_by_count":4,"area":null},{"id":"2311.09383","title":"Long-form Question Answering: An Iterative Planning-Retrieval-Generation Approach","created":"2023-11-15","cited_by_count":4,"area":null},{"id":"2407.11930","title":"Localizing and Mitigating Errors in Long-form Question Answering","created":"2024-07-16","cited_by_count":4,"area":null},{"id":"2409.09844","title":"A Benchmark Dataset with Larger Context for Non-Factoid Question Answering over Islamic Text","created":"2024-09-15","cited_by_count":4,"area":null},{"id":"2507.19995","title":"VLQA: The First Comprehensive, Large, and High-Quality Vietnamese Dataset for Legal Question Answering","created":"2025-07-26","cited_by_count":4,"area":null},{"id":"2305.13669","title":"The Knowledge Alignment Problem: Bridging Human and External Knowledge for Large Language Models","created":"2023-05-23","cited_by_count":3,"area":null},{"id":"2407.04969","title":"EVA-Score: Evaluating Abstractive Long-form Summarization on Informativeness through Extraction and Validation","created":"2024-07-06","cited_by_count":3,"area":null},{"id":"2410.01945","title":"LFQA-E: Carefully Benchmarking Long-form QA Evaluation","created":"2024-10-02","cited_by_count":3,"area":null},{"id":"2507.08459","title":"Diagnosing Failures in Large Language Models' Answers: Integrating Error Attribution into Evaluation Framework","created":"2025-07-11","cited_by_count":3,"area":null},{"id":"2112.13432","title":"New Methods & Metrics for LFQA tasks","created":"2021-12-26","cited_by_count":2,"area":null},{"id":"2210.14260","title":"Universal Evasion Attacks on Summarization Scoring","created":"2022-10-25","cited_by_count":2,"area":null},{"id":"2211.05452","title":"Towards Human-Centred Explainability Benchmarks For Text Classification","created":"2022-11-10","cited_by_count":2,"area":null},{"id":"2305.11991","title":"Evaluation of medium-large Language Models at zero-shot closed book generative question answering","created":"2023-05-19","cited_by_count":2,"area":null},{"id":"2305.12483","title":"Model Analysis & Evaluation for Ambiguous Question Answering","created":"2023-05-21","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":"2508.01401","title":"MedSynth: Realistic, Synthetic Medical Dialogue-Note Pairs","created":"2025-08-02","cited_by_count":2,"area":null},{"id":"2608.00005","title":"RubricReviewer: From Direct Critique to Objective and Comprehensive Rubric-Driven Peer Review","created":"2026-06-04","cited_by_count":2,"area":null}],"next_cursor":"100"}