{"total":154,"rows":[{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326,"area":null},{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780,"area":null},{"id":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576,"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":"2305.10403","title":"PaLM 2 Technical Report","created":"2023-05-17","cited_by_count":1162,"area":"lr"},{"id":"2305.16264","title":"Scaling Data-Constrained Language Models","created":"2023-05-25","cited_by_count":403,"area":null},{"id":"2308.16884","title":"The Belebele Benchmark: a Parallel Reading Comprehension Dataset in 122 Language Variants","created":"2023-08-31","cited_by_count":311,"area":null},{"id":"2102.01672","title":"The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics","created":"2021-02-02","cited_by_count":239,"area":null},{"id":"2110.07904","title":"SPoT: Better Frozen Model Adaptation through Soft Prompt Transfer","created":"2021-10-15","cited_by_count":235,"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":"2111.10952","title":"ExT5: Towards Extreme Multi-Task Scaling for Transfer Learning","created":"2021-11-22","cited_by_count":161,"area":null},{"id":"2202.06935","title":"Repairing the Cracked Foundation: A Survey of Obstacles in Evaluation Practices for Generated Text","created":"2022-02-14","cited_by_count":155,"area":null},{"id":"2403.02901","title":"A Comprehensive Survey on Process-Oriented Automatic Text Summarization with Exploration of LLM-Based Methods","created":"2024-03-05","cited_by_count":102,"area":null},{"id":"2210.03050","title":"State-of-the-art generalisation research in NLP: A taxonomy and review","created":"2022-10-06","cited_by_count":98,"area":null},{"id":"2402.12840","title":"ArabicMMLU: Assessing Massive Multitask Language Understanding in Arabic","created":"2024-02-20","cited_by_count":88,"area":"lr"},{"id":"2305.11171","title":"TrueTeacher: Learning Factual Consistency Evaluation with Large Language Models","created":"2023-05-18","cited_by_count":83,"area":null},{"id":"2109.10465","title":"Scalable and Efficient MoE Training for Multitask Multilingual Models","created":"2021-09-22","cited_by_count":76,"area":"moe"},{"id":"2109.12068","title":"AraT5: Text-to-Text Transformers for Arabic Language Generation","created":"2021-08-31","cited_by_count":63,"area":null},{"id":"2205.12647","title":"Overcoming Catastrophic Forgetting in Zero-Shot Cross-Lingual Generation","created":"2022-05-25","cited_by_count":62,"area":null},{"id":"2108.13684","title":"Faithful or Extractive? On Mitigating the Faithfulness-Abstractiveness Trade-off in Abstractive Summarization","created":"2021-08-31","cited_by_count":51,"area":null},{"id":"2106.13736","title":"DeltaLM: Encoder-Decoder Pre-training for Language Generation and Translation by Augmenting Pretrained Multilingual Encoders","created":"2021-06-25","cited_by_count":50,"area":null},{"id":"2203.05437","title":"IndicNLG Benchmark: Multilingual Datasets for Diverse NLG Tasks in Indic Languages","created":"2022-03-10","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":"2104.08692","title":"MT6: Multilingual Pretrained Text-to-Text Transformer with Translation Pairs","created":"2021-04-18","cited_by_count":41,"area":null},{"id":"2211.00635","title":"Two-stage LLM Fine-tuning with Less Specialization and More Generalization","created":"2022-11-01","cited_by_count":41,"area":null},{"id":"2210.13448","title":"EUR-Lex-Sum: A Multi- and Cross-lingual Dataset for Long-form Summarization in the Legal Domain","created":"2022-10-24","cited_by_count":40,"area":null},{"id":"2112.08804","title":"CrossSum: Beyond English-Centric Cross-Lingual Summarization for 1,500+ Language Pairs","created":"2021-12-16","cited_by_count":39,"area":null},{"id":"2203.12515","title":"A Survey on Cross-Lingual Summarization","created":"2022-03-23","cited_by_count":38,"area":null},{"id":"2212.09648","title":"NusaCrowd: Open Source Initiative for Indonesian NLP Resources","created":"2022-12-19","cited_by_count":38,"area":null},{"id":"2205.06457","title":"ViT5: Pretrained Text-to-Text Transformer for Vietnamese Language Generation","created":"2022-05-13","cited_by_count":37,"area":null},{"id":"2202.09583","title":"Models and Datasets for Cross-Lingual Summarisation","created":"2022-02-19","cited_by_count":36,"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":"2107.13189","title":"Goal-Oriented Script Construction","created":"2021-07-28","cited_by_count":30,"area":null},{"id":"2402.11597","title":"Multi-Task Inference: Can Large Language Models Follow Multiple Instructions at Once?","created":"2024-02-18","cited_by_count":30,"area":null},{"id":"2505.12201","title":"How Reliable is Multilingual LLM-as-a-Judge?","created":"2025-05-18","cited_by_count":30,"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":"2311.05741","title":"Efficiently Adapting Pretrained Language Models To New Languages","created":"2023-11-09","cited_by_count":28,"area":null},{"id":"2305.15678","title":"Revisiting non-English Text Simplification: A Unified Multilingual Benchmark","created":"2023-05-25","cited_by_count":27,"area":null},{"id":"2404.12318","title":"Reuse Your Rewards: Reward Model Transfer for Zero-Shot Cross-Lingual Alignment","created":"2024-04-18","cited_by_count":26,"area":"alignment"},{"id":"2202.05599","title":"ClidSum: A Benchmark Dataset for Cross-Lingual Dialogue Summarization","created":"2022-02-11","cited_by_count":25,"area":null},{"id":"2410.05873","title":"MEXA: Multilingual Evaluation of English-Centric LLMs via Cross-Lingual Alignment","created":"2024-10-08","cited_by_count":25,"area":null},{"id":"2106.01597","title":"ZmBART: An Unsupervised Cross-lingual Transfer Framework for Language Generation","created":"2021-06-03","cited_by_count":23,"area":null},{"id":"2108.07140","title":"MTG: A Benchmark Suite for Multilingual Text Generation","created":"2021-08-13","cited_by_count":22,"area":null},{"id":"2112.03473","title":"Improving Neural Cross-Lingual Summarization via Employing Optimal Transport Distance for Knowledge Distillation","created":"2021-12-07","cited_by_count":22,"area":"distill"},{"id":"2305.17325","title":"Why Does Zero-Shot Cross-Lingual Generation Fail? An Explanation and a Solution","created":"2023-05-27","cited_by_count":22,"area":null},{"id":"2106.02171","title":"nmT5 -- Is parallel data still relevant for pre-training massively multilingual language models?","created":"2021-06-03","cited_by_count":21,"area":null},{"id":"2212.10218","title":"GanLM: Encoder-Decoder Pre-training with an Auxiliary Discriminator","created":"2022-12-20","cited_by_count":20,"area":null},{"id":"2407.21530","title":"Data Contamination Report from the 2024 CONDA Shared Task","created":"2024-07-31","cited_by_count":20,"area":null},{"id":"2106.09069","title":"Automatic Construction of Evaluation Suites for Natural Language Generation Datasets","created":"2021-06-16","cited_by_count":18,"area":null},{"id":"2109.04319","title":"Translate & Fill: Improving Zero-Shot Multilingual Semantic Parsing with Synthetic Data","created":"2021-09-09","cited_by_count":17,"area":"synth"},{"id":"2203.03820","title":"A Variational Hierarchical Model for Neural Cross-Lingual Summarization","created":"2022-03-08","cited_by_count":17,"area":null},{"id":"2206.12131","title":"MVP: Multi-task Supervised Pre-training for Natural Language Generation","created":"2022-06-24","cited_by_count":16,"area":null},{"id":"2302.14229","title":"Zero-Shot Cross-Lingual Summarization via Large Language Models","created":"2023-02-28","cited_by_count":16,"area":null},{"id":"2305.09220","title":"Towards Unifying Multi-Lingual and Cross-Lingual Summarization","created":"2023-05-16","cited_by_count":15,"area":null},{"id":"2404.01667","title":"METAL: Towards Multilingual Meta-Evaluation","created":"2024-04-02","cited_by_count":15,"area":null},{"id":"2410.18779","title":"A Little Help Goes a Long Way: Efficient LLM Training by Leveraging Small LMs","created":"2024-10-24","cited_by_count":15,"area":null},{"id":"2106.01478","title":"Evaluating the Efficacy of Summarization Evaluation across Languages","created":"2021-06-02","cited_by_count":14,"area":null},{"id":"2212.07220","title":"Understanding Translationese in Cross-Lingual Summarization","created":"2022-12-14","cited_by_count":14,"area":null},{"id":"2305.14926","title":"Universal Self-Adaptive Prompting","created":"2023-05-24","cited_by_count":14,"area":null},{"id":"2311.09033","title":"MELA: Multilingual Evaluation of Linguistic Acceptability","created":"2023-11-15","cited_by_count":14,"area":null},{"id":"2110.12199","title":"PhoMT: A High-Quality and Large-Scale Benchmark Dataset for Vietnamese-English Machine Translation","created":"2021-10-23","cited_by_count":12,"area":null},{"id":"2205.15051","title":"X-SCITLDR: Cross-Lingual Extreme Summarization of Scholarly Documents","created":"2022-05-30","cited_by_count":12,"area":null},{"id":"2302.06560","title":"Large Scale Multi-Lingual Multi-Modal Summarization Dataset","created":"2023-02-13","cited_by_count":12,"area":null},{"id":"2407.14885","title":"Falcon2-11B Technical Report","created":"2024-07-20","cited_by_count":12,"area":null},{"id":"2409.12958","title":"MURI: High-Quality Instruction Tuning Datasets for Low-Resource Languages via Reverse Instructions","created":"2024-09-19","cited_by_count":12,"area":null},{"id":"2409.18314","title":"Realistic Evaluation of Model Merging for Compositional Generalization","created":"2024-09-26","cited_by_count":12,"area":null},{"id":"2502.19737","title":"XCOMPS: A Multilingual Benchmark of Conceptual Minimal Pairs","created":"2025-02-27","cited_by_count":12,"area":null},{"id":"2212.10755","title":"JASMINE: Arabic GPT Models for Few-Shot Learning","created":"2022-12-21","cited_by_count":11,"area":null},{"id":"2305.08828","title":"PMIndiaSum: Multilingual and Cross-lingual Headline Summarization for Languages in India","created":"2023-05-15","cited_by_count":11,"area":null},{"id":"2109.13664","title":"Multilingual Counter Narrative Type Classification","created":"2021-09-28","cited_by_count":10,"area":null},{"id":"2205.06356","title":"Beyond Static Models and Test Sets: Benchmarking the Potential of Pre-trained Models Across Tasks and Languages","created":"2022-05-12","cited_by_count":10,"area":null},{"id":"2305.11129","title":"mLongT5: A Multilingual and Efficient Text-To-Text Transformer for Longer Sequences","created":"2023-05-18","cited_by_count":10,"area":null},{"id":"2306.16322","title":"Taqyim: Evaluating Arabic NLP Tasks Using ChatGPT Models","created":"2023-06-28","cited_by_count":10,"area":null},{"id":"2310.18600","title":"MILDSum: A Novel Benchmark Dataset for Multilingual Summarization of Indian Legal Case Judgments","created":"2023-10-28","cited_by_count":10,"area":null},{"id":"2402.11532","title":"Chain-of-Instructions: Compositional Instruction Tuning on Large Language Models","created":"2024-02-18","cited_by_count":9,"area":null},{"id":"2410.04087","title":"GlobeSumm: A Challenging Benchmark Towards Unifying Multi-lingual, Cross-lingual and Multi-document News Summarization","created":"2024-10-05","cited_by_count":9,"area":null},{"id":"2205.00379","title":"The Cross-lingual Conversation Summarization Challenge","created":"2022-05-01","cited_by_count":8,"area":null},{"id":"2205.07455","title":"Reasoning about Procedures with Natural Language Processing: A Tutorial","created":"2022-05-16","cited_by_count":8,"area":null},{"id":"2303.04092","title":"CroCoSum: A Benchmark Dataset for Cross-Lingual Code-Switched Summarization","created":"2023-03-07","cited_by_count":8,"area":null},{"id":"2305.11778","title":"Cross-Lingual Supervision improves Large Language Models Pre-training","created":"2023-05-19","cited_by_count":8,"area":null},{"id":"2306.12916","title":"Cross-lingual Cross-temporal Summarization: Dataset, Models, Evaluation","created":"2023-06-22","cited_by_count":8,"area":null},{"id":"2508.16431","title":"Cetvel: A Unified Benchmark for Evaluating Language Understanding, Generation and Cultural Capacity of LLMs for Turkish","created":"2025-08-22","cited_by_count":8,"area":null},{"id":"2305.14205","title":"$\\mu$PLAN: Summarizing using a Content Plan as Cross-Lingual Bridge","created":"2023-05-23","cited_by_count":7,"area":null},{"id":"2306.06800","title":"AraMUS: Pushing the Limits of Data and Model Scale for Arabic Natural Language Processing","created":"2023-06-11","cited_by_count":7,"area":null},{"id":"2307.04018","title":"Revisiting Cross-Lingual Summarization: A Corpus-based Study and A New Benchmark with Improved Annotation","created":"2023-07-08","cited_by_count":7,"area":null},{"id":"2309.10706","title":"OpenBA: An Open-sourced 15B Bilingual Asymmetric seq2seq Model Pre-trained from Scratch","created":"2023-09-19","cited_by_count":7,"area":null},{"id":"2110.09147","title":"BEAMetrics: A Benchmark for Language Generation Evaluation Evaluation","created":"2021-10-18","cited_by_count":6,"area":null},{"id":"2204.05042","title":"Resources for Turkish Natural Language Processing: A critical survey","created":"2022-04-11","cited_by_count":6,"area":null},{"id":"2211.02580","title":"Evaluating and Improving Factuality in Multimodal Abstractive Summarization","created":"2022-11-04","cited_by_count":6,"area":null},{"id":"2212.00586","title":"Long-Document Cross-Lingual Summarization","created":"2022-12-01","cited_by_count":6,"area":null},{"id":"2403.02715","title":"Crossing Linguistic Horizons: Finetuning and Comprehensive Evaluation of Vietnamese Large Language Models","created":"2024-03-05","cited_by_count":6,"area":null},{"id":"2507.03373","title":"WETBench: A Benchmark for Detecting Task-Specific Machine-Generated Text on Wikipedia","created":"2025-07-04","cited_by_count":6,"area":null},{"id":"2509.14814","title":"ReCoVeR the Target Language: Language Steering without Sacrificing Task Performance","created":"2025-09-18","cited_by_count":6,"area":null},{"id":"2110.07936","title":"Unifying Cross-lingual Summarization and Machine Translation with Compression Rate","created":"2021-10-15","cited_by_count":5,"area":null},{"id":"2210.05610","title":"MTet: Multi-domain Translation for English and Vietnamese","created":"2022-10-11","cited_by_count":5,"area":null},{"id":"2309.06698","title":"Benchmarking Procedural Language Understanding for Low-Resource Languages: A Case Study on Turkish","created":"2023-09-13","cited_by_count":5,"area":null},{"id":"2510.13366","title":"Document Intelligence in the Era of Large Language Models: A Survey","created":"2025-10-15","cited_by_count":5,"area":null},{"id":"2203.10250","title":"Meta-X$_{NLG}$: A Meta-Learning Approach Based on Language Clustering for Zero-Shot Cross-Lingual Transfer and Generation","created":"2022-03-19","cited_by_count":4,"area":null},{"id":"2403.01308","title":"VBART: The Turkish LLM","created":"2024-03-02","cited_by_count":4,"area":null},{"id":"2406.04630","title":"Low-Resource Cross-Lingual Summarization through Few-Shot Learning with Large Language Models","created":"2024-06-07","cited_by_count":4,"area":null}],"next_cursor":"100"}