{"total":140,"rows":[{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028,"area":null},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326,"area":null},{"id":"2211.05100","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","created":"2022-11-09","cited_by_count":1984,"area":null},{"id":"2303.17564","title":"BloombergGPT: A Large Language Model for Finance","created":"2023-03-30","cited_by_count":939,"area":null},{"id":"2209.12356","title":"News Summarization and Evaluation in the Era of GPT-3","created":"2022-09-26","cited_by_count":327,"area":null},{"id":"2205.05131","title":"UL2: Unifying Language Learning Paradigms","created":"2022-05-10","cited_by_count":295,"area":null},{"id":"2210.07197","title":"Towards a Unified Multi-Dimensional Evaluator for Text Generation","created":"2022-10-13","cited_by_count":264,"area":null},{"id":"2309.05196","title":"Does Writing with Language Models Reduce Content Diversity?","created":"2023-09-11","cited_by_count":192,"area":null},{"id":"2402.06619","title":"Aya Dataset: An Open-Access Collection for Multilingual Instruction Tuning","created":"2024-02-09","cited_by_count":177,"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":"2212.07981","title":"Revisiting the Gold Standard: Grounding Summarization Evaluation with Robust Human Evaluation","created":"2022-12-15","cited_by_count":142,"area":null},{"id":"2306.01941","title":"AI Transparency in the Age of LLMs: A Human-Centered Research Roadmap","created":"2023-06-02","cited_by_count":123,"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":"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":"2304.03245","title":"Large language models effectively leverage document-level context for literary translation, but critical errors persist","created":"2023-04-06","cited_by_count":80,"area":null},{"id":"2311.16822","title":"Large Language Models Suffer From Their Own Output: An Analysis of the Self-Consuming Training Loop","created":"2023-11-28","cited_by_count":79,"area":null},{"id":"2309.13633","title":"EvalLM: Interactive Evaluation of Large Language Model Prompts on User-Defined Criteria","created":"2023-09-24","cited_by_count":74,"area":null},{"id":"2402.01383","title":"LLM-based NLG Evaluation: Current Status and Challenges","created":"2024-02-02","cited_by_count":73,"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":"2307.15703","title":"Uncertainty in Natural Language Generation: From Theory to Applications","created":"2023-07-28","cited_by_count":61,"area":null},{"id":"2502.06559","title":"Can We Trust AI Benchmarks? An Interdisciplinary Review of Current Issues in AI Evaluation","created":"2025-02-10","cited_by_count":60,"area":null},{"id":"2211.07634","title":"Follow the Wisdom of the Crowd: Effective Text Generation via Minimum Bayes Risk Decoding","created":"2022-11-14","cited_by_count":54,"area":null},{"id":"2406.10229","title":"Quantifying Variance in Evaluation Benchmarks","created":"2024-06-14","cited_by_count":54,"area":null},{"id":"2305.11707","title":"What Comes Next? Evaluating Uncertainty in Neural Text Generators Against Human Production Variability","created":"2023-05-19","cited_by_count":51,"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":"2211.15914","title":"Prompted Opinion Summarization with GPT-3.5","created":"2022-11-29","cited_by_count":44,"area":null},{"id":"2305.14889","title":"Evaluating Evaluation Metrics: A Framework for Analyzing NLG Evaluation Metrics using Measurement Theory","created":"2023-05-24","cited_by_count":43,"area":null},{"id":"2212.10622","title":"mFACE: Multilingual Summarization with Factual Consistency Evaluation","created":"2022-12-20","cited_by_count":42,"area":null},{"id":"2305.13194","title":"SEAHORSE: A Multilingual, Multifaceted Dataset for Summarization Evaluation","created":"2023-05-22","cited_by_count":42,"area":null},{"id":"2210.10045","title":"SafeText: A Benchmark for Exploring Physical Safety in Language Models","created":"2022-10-18","cited_by_count":41,"area":null},{"id":"2206.11249","title":"GEMv2: Multilingual NLG Benchmarking in a Single Line of Code","created":"2022-06-22","cited_by_count":36,"area":null},{"id":"2210.13746","title":"DEMETR: Diagnosing Evaluation Metrics for Translation","created":"2022-10-25","cited_by_count":36,"area":null},{"id":"2401.06796","title":"AI Hallucinations: A Misnomer Worth Clarifying","created":"2024-01-09","cited_by_count":34,"area":null},{"id":"2401.14493","title":"K-QA: A Real-World Medical Q&A Benchmark","created":"2024-01-25","cited_by_count":31,"area":null},{"id":"2208.09770","title":"Z-Code++: A Pre-trained Language Model Optimized for Abstractive Summarization","created":"2022-08-21","cited_by_count":29,"area":null},{"id":"2306.16793","title":"Benchmarking Large Language Model Capabilities for Conditional Generation","created":"2023-06-29","cited_by_count":29,"area":null},{"id":"2204.06815","title":"deep-significance - Easy and Meaningful Statistical Significance Testing in the Age of Neural Networks","created":"2022-04-14","cited_by_count":28,"area":null},{"id":"2311.08788","title":"X-Eval: Generalizable Multi-aspect Text Evaluation via Augmented Instruction Tuning with Auxiliary Evaluation Aspects","created":"2023-11-15","cited_by_count":28,"area":null},{"id":"2401.02458","title":"Data-Centric Foundation Models in Computational Healthcare: A Survey","created":"2024-01-04","cited_by_count":27,"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":"2405.17974","title":"Recent Trends in Personalized Dialogue Generation: A Review of Datasets, Methodologies, and Evaluations","created":"2024-05-28","cited_by_count":20,"area":null},{"id":"2407.12858","title":"Grounding and Evaluation for Large Language Models: Practical Challenges and Lessons Learned (Survey)","created":"2024-07-10","cited_by_count":20,"area":null},{"id":"2408.09169","title":"Automatic Metrics in Natural Language Generation: A Survey of Current Evaluation Practices","created":"2024-08-17","cited_by_count":20,"area":null},{"id":"2303.04729","title":"Stealing the Decoding Algorithms of Language Models","created":"2023-03-08","cited_by_count":19,"area":null},{"id":"2312.03631","title":"Mitigating Open-Vocabulary Caption Hallucinations","created":"2023-12-06","cited_by_count":19,"area":null},{"id":"2310.08394","title":"Towards Better Evaluation of Instruction-Following: A Case-Study in Summarization","created":"2023-10-12","cited_by_count":18,"area":null},{"id":"2401.10186","title":"Beyond Traditional Benchmarks: Analyzing Behaviors of Open LLMs on Data-to-Text Generation","created":"2024-01-18","cited_by_count":16,"area":null},{"id":"2203.11131","title":"Towards Explainable Evaluation Metrics for Natural Language Generation","created":"2022-03-21","cited_by_count":15,"area":null},{"id":"2306.13041","title":"Towards Explainable Evaluation Metrics for Machine Translation","created":"2023-06-22","cited_by_count":15,"area":null},{"id":"2211.00922","title":"Dialect-robust Evaluation of Generated Text","created":"2022-11-02","cited_by_count":14,"area":null},{"id":"2303.16166","title":"When Good and Reproducible Results are a Giant with Feet of Clay: The Importance of Software Quality in NLP","created":"2023-03-28","cited_by_count":14,"area":null},{"id":"2305.10284","title":"Towards More Robust NLP System Evaluation: Handling Missing Scores in Benchmarks","created":"2023-05-17","cited_by_count":14,"area":null},{"id":"2404.01474","title":"Finding Replicable Human Evaluations via Stable Ranking Probability","created":"2024-04-01","cited_by_count":13,"area":null},{"id":"2211.08371","title":"Pragmatics in Language Grounding: Phenomena, Tasks, and Modeling Approaches","created":"2022-11-15","cited_by_count":12,"area":null},{"id":"2503.23339","title":"A Scalable Framework for Evaluating Health Language Models","created":"2025-03-30","cited_by_count":11,"area":null},{"id":"2204.05307","title":"Toward More Effective Human Evaluation for Machine Translation","created":"2022-04-11","cited_by_count":10,"area":null},{"id":"2204.06251","title":"Experimental Standards for Deep Learning in Natural Language Processing Research","created":"2022-04-13","cited_by_count":10,"area":null},{"id":"2211.00142","title":"TaTa: A Multilingual Table-to-Text Dataset for African Languages","created":"2022-10-31","cited_by_count":10,"area":null},{"id":"2212.10397","title":"Needle in a Haystack: An Analysis of High-Agreement Workers on MTurk for Summarization","created":"2022-12-20","cited_by_count":10,"area":null},{"id":"2306.12719","title":"Natural Language Generation for Advertising: A Survey","created":"2023-06-22","cited_by_count":10,"area":null},{"id":"2402.18005","title":"A Sentiment Consolidation Framework for Meta-Review Generation","created":"2024-02-28","cited_by_count":10,"area":null},{"id":"2204.00004","title":"Reproducibility Issues for BERT-based Evaluation Metrics","created":"2022-03-30","cited_by_count":9,"area":null},{"id":"2210.17378","title":"Questioning the Validity of Summarization Datasets and Improving Their Factual Consistency","created":"2022-10-31","cited_by_count":9,"area":null},{"id":"2305.17779","title":"Generating EDU Extracts for Plan-Guided Summary Re-Ranking","created":"2023-05-28","cited_by_count":9,"area":null},{"id":"2504.07971","title":"SPHERE: An Evaluation Card for Human-AI Systems","created":"2025-03-24","cited_by_count":9,"area":null},{"id":"2205.12467","title":"R2D2: Robust Data-to-Text with Replacement Detection","created":"2022-05-25","cited_by_count":8,"area":null},{"id":"2211.09455","title":"Consultation Checklists: Standardising the Human Evaluation of Medical Note Generation","created":"2022-11-17","cited_by_count":8,"area":null},{"id":"2305.07615","title":"What are the Desired Characteristics of Calibration Sets? Identifying Correlates on Long Form Scientific Summarization","created":"2023-05-12","cited_by_count":8,"area":null},{"id":"2402.14880","title":"Automatic Histograms: Leveraging Language Models for Text Dataset Exploration","created":"2024-02-21","cited_by_count":8,"area":null},{"id":"2407.04046","title":"Systematic Task Exploration with LLMs: A Study in Citation Text Generation","created":"2024-07-04","cited_by_count":8,"area":null},{"id":"2509.04373","title":"Measuring Bias or Measuring the Task: Understanding the Brittle Nature of LLM Gender Biases","created":"2025-09-04","cited_by_count":8,"area":null},{"id":"2302.14169","title":"TabGenie: A Toolkit for Table-to-Text Generation","created":"2023-02-27","cited_by_count":7,"area":null},{"id":"2307.06869","title":"DecompEval: Evaluating Generated Texts as Unsupervised Decomposed Question Answering","created":"2023-07-13","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":"2404.11960","title":"MCRanker: Generating Diverse Criteria On-the-Fly to Improve Point-wise LLM Rankers","created":"2024-04-18","cited_by_count":7,"area":null},{"id":"2504.08697","title":"LLMs as Span Annotators: A Comparative Study of LLMs and Humans","created":"2025-04-11","cited_by_count":7,"area":null},{"id":"2210.07373","title":"Mind the Labels: Describing Relations in Knowledge Graphs With Pretrained Models","created":"2022-10-13","cited_by_count":6,"area":null},{"id":"2311.00739","title":"Can Large Language Models Design Accurate Label Functions?","created":"2023-11-01","cited_by_count":6,"area":null},{"id":"2403.14275","title":"Is Reference Necessary in the Evaluation of NLG Systems? When and Where?","created":"2024-03-21","cited_by_count":6,"area":null},{"id":"2404.19563","title":"RepEval: Effective Text Evaluation with LLM Representation","created":"2024-04-30","cited_by_count":6,"area":null},{"id":"2504.16677","title":"A Post-trainer's Guide to Multilingual Training Data: Uncovering Cross-lingual Transfer Dynamics","created":"2025-04-23","cited_by_count":6,"area":null},{"id":"2506.02945","title":"Quantitative LLM Judges","created":"2025-06-03","cited_by_count":6,"area":null},{"id":"2508.07955","title":"Expert Preference-based Evaluation of Automated Related Work Generation","created":"2025-08-11","cited_by_count":6,"area":null},{"id":"2306.01169","title":"Hybrid Long Document Summarization using C2F-FAR and ChatGPT: A Practical Study","created":"2023-06-01","cited_by_count":5,"area":null},{"id":"2310.01917","title":"Hierarchical Evaluation Framework: Best Practices for Human Evaluation","created":"2023-10-03","cited_by_count":5,"area":null},{"id":"2404.01701","title":"On the Role of Summary Content Units in Text Summarization Evaluation","created":"2024-04-02","cited_by_count":5,"area":null},{"id":"2408.15409","title":"Awes, Laws, and Flaws From Today's LLM Research","created":"2024-08-27","cited_by_count":5,"area":null},{"id":"2507.01936","title":"The Thin Line Between Comprehension and Persuasion in LLMs","created":"2025-07-02","cited_by_count":5,"area":null},{"id":"2510.22581","title":"Pedagogy-driven Evaluation of Generative AI-powered Intelligent Tutoring Systems","created":"2025-10-26","cited_by_count":5,"area":null},{"id":"2311.05020","title":"First Tragedy, then Parse: History Repeats Itself in the New Era of Large Language Models","created":"2023-11-08","cited_by_count":4,"area":null},{"id":"2403.18697","title":"The Invalsi Benchmarks: measuring Linguistic and Mathematical understanding of Large Language Models in Italian","created":"2024-03-27","cited_by_count":4,"area":null},{"id":"2407.01878","title":"Compare without Despair: Reliable Preference Evaluation with Generation Separability","created":"2024-07-02","cited_by_count":4,"area":null},{"id":"2509.17559","title":"Specification-Aware Machine Translation and Evaluation for Purpose Alignment","created":"2025-09-22","cited_by_count":4,"area":null},{"id":"2304.14104","title":"Learning Human-Human Interactions in Images from Weak Textual Supervision","created":"2023-04-27","cited_by_count":3,"area":null},{"id":"2307.08189","title":"Mini-Giants: \"Small\" Language Models and Open Source Win-Win","created":"2023-07-17","cited_by_count":3,"area":null},{"id":"2402.13709","title":"SaGE: Evaluating Moral Consistency in Large Language Models","created":"2024-02-21","cited_by_count":3,"area":null},{"id":"2402.18756","title":"How Much Annotation is Needed to Compare Summarization Models?","created":"2024-02-28","cited_by_count":3,"area":null},{"id":"2407.21072","title":"Beyond Metrics: A Critical Analysis of the Variability in Large Language Model Evaluation Frameworks","created":"2024-07-29","cited_by_count":3,"area":null},{"id":"2412.17321","title":"Assessing Human Editing Effort on LLM-Generated Texts via Compression-Based Edit Distance","created":"2024-12-23","cited_by_count":3,"area":null},{"id":"2502.18339","title":"Correlating and Predicting Human Evaluations of Language Models from Natural Language Processing Benchmarks","created":"2025-02-24","cited_by_count":3,"area":null}],"next_cursor":"100"}