{"total":33,"rows":[{"id":"2211.05100","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","created":"2022-11-09","cited_by_count":1984,"area":null},{"id":"2405.01535","title":"Prometheus 2: An Open Source Language Model Specialized in Evaluating Other Language Models","created":"2024-05-02","cited_by_count":446,"area":null},{"id":"2207.13332","title":"RealTime QA: What's the Answer Right Now?","created":"2022-07-27","cited_by_count":244,"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":"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":"2406.05761","title":"The BiGGen Bench: A Principled Benchmark for Fine-grained Evaluation of Language Models with Language Models","created":"2024-06-09","cited_by_count":93,"area":null},{"id":"2212.09746","title":"Evaluating Human-Language Model Interaction","created":"2022-12-19","cited_by_count":92,"area":null},{"id":"2209.01188","title":"Petals: Collaborative Inference and Fine-tuning of Large Models","created":"2022-09-02","cited_by_count":87,"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":"2404.06228","title":"Understanding Cross-Lingual Alignment -- A Survey","created":"2024-04-09","cited_by_count":34,"area":null},{"id":"2310.16379","title":"Evaluating General-Purpose AI with Psychometrics","created":"2023-10-25","cited_by_count":23,"area":null},{"id":"2212.09577","title":"CiteBench: A benchmark for Scientific Citation Text Generation","created":"2022-12-19","cited_by_count":22,"area":null},{"id":"2305.14989","title":"Dolphin: A Challenging and Diverse Benchmark for Arabic NLG","created":"2023-05-24","cited_by_count":22,"area":null},{"id":"2305.13627","title":"InstructAlign: High-and-Low Resource Language Alignment via Continual Crosslingual Instruction Tuning","created":"2023-05-23","cited_by_count":21,"area":null},{"id":"2410.20245","title":"Improving Model Evaluation using SMART Filtering of Benchmark Datasets","created":"2024-10-26","cited_by_count":21,"area":null},{"id":"2310.14424","title":"Which Prompts Make The Difference? Data Prioritization For Efficient Human LLM Evaluation","created":"2023-10-22","cited_by_count":18,"area":null},{"id":"2210.05109","title":"BanglaParaphrase: A High-Quality Bangla Paraphrase Dataset","created":"2022-10-11","cited_by_count":15,"area":null},{"id":"2401.01053","title":"Cheetah: Natural Language Generation for 517 African Languages","created":"2024-01-02","cited_by_count":15,"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":"2406.15948","title":"Teaching LLMs to Abstain across Languages via Multilingual Feedback","created":"2024-06-22","cited_by_count":14,"area":null},{"id":"2210.12929","title":"Finding Memo: Extractive Memorization in Constrained Sequence Generation Tasks","created":"2022-10-24","cited_by_count":12,"area":null},{"id":"2211.16259","title":"Measuring the Measuring Tools: An Automatic Evaluation of Semantic Metrics for Text Corpora","created":"2022-11-29","cited_by_count":11,"area":null},{"id":"2312.13871","title":"Evaluating Task-oriented Dialogue Systems: A Systematic Review of Measures, Constructs and their Operationalisations","created":"2023-12-21","cited_by_count":9,"area":null},{"id":"2503.07920","title":"Crowdsource, Crawl, or Generate? Creating SEA-VL, a Multicultural Vision-Language Dataset for Southeast Asia","created":"2025-03-10","cited_by_count":9,"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":"2410.09527","title":"LexSumm and LexT5: Benchmarking and Modeling Legal Summarization Tasks in English","created":"2024-10-12","cited_by_count":8,"area":null},{"id":"2309.10661","title":"NusaWrites: Constructing High-Quality Corpora for Underrepresented and Extremely Low-Resource Languages","created":"2023-09-19","cited_by_count":5,"area":null},{"id":"2601.02669","title":"Towards Comprehensive Stage-wise Benchmarking of Large Language Models in Fact-Checking","created":"2026-01-06","cited_by_count":3,"area":null},{"id":"2211.02423","title":"CLSE: Corpus of Linguistically Significant Entities","created":"2022-11-04","cited_by_count":2,"area":null},{"id":"2211.16858","title":"A Major Obstacle for NLP Research: Let's Talk about Time Allocation!","created":"2022-11-30","cited_by_count":1,"area":null},{"id":"2212.00006","title":"Operationalizing Specifications, In Addition to Test Sets for Evaluating Constrained Generative Models","created":"2022-11-19","cited_by_count":1,"area":null},{"id":"2507.20419","title":"Survey of NLU Benchmarks Diagnosing Linguistic Phenomena: Why not Standardize Diagnostics Benchmarks?","created":"2025-07-27","cited_by_count":1,"area":null},{"id":"2212.11670","title":"Evaluation for Change","created":"2022-12-20","cited_by_count":0,"area":null}],"next_cursor":null}