{"total":73,"rows":[{"id":"2406.15877","title":"BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions","created":"2024-06-22","cited_by_count":546,"area":null},{"id":"2402.07827","title":"Aya Model: An Instruction Finetuned Open-Access Multilingual Language Model","created":"2024-02-12","cited_by_count":295,"area":null},{"id":"2402.09906","title":"Generative Representational Instruction Tuning","created":"2024-02-15","cited_by_count":233,"area":null},{"id":"2308.07124","title":"OctoPack: Instruction Tuning Code Large Language Models","created":"2023-08-14","cited_by_count":189,"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":"2210.14868","title":"Multi-lingual Evaluation of Code Generation Models","created":"2022-10-26","cited_by_count":159,"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":"2303.16104","title":"Hallucinations in Large Multilingual Translation Models","created":"2023-03-28","cited_by_count":129,"area":null},{"id":"2406.06443","title":"LLM Dataset Inference: Did you train on my dataset?","created":"2024-06-10","cited_by_count":110,"area":"safety"},{"id":"2112.08313","title":"Measure and Improve Robustness in NLP Models: A Survey","created":"2021-12-15","cited_by_count":107,"area":null},{"id":"2212.10264","title":"ReCode: Robustness Evaluation of Code Generation Models","created":"2022-12-20","cited_by_count":103,"area":null},{"id":"2306.01943","title":"NLPositionality: Characterizing Design Biases of Datasets and Models","created":"2023-06-02","cited_by_count":94,"area":null},{"id":"2301.12867","title":"Red teaming ChatGPT via Jailbreaking: Bias, Robustness, Reliability and Toxicity","created":"2023-01-30","cited_by_count":89,"area":"safety"},{"id":"2311.05640","title":"FinGPT: Large Generative Models for a Small Language","created":"2023-11-03","cited_by_count":49,"area":null},{"id":"2406.11036","title":"garak: A Framework for Security Probing Large Language Models","created":"2024-06-16","cited_by_count":49,"area":"safety"},{"id":"2212.10758","title":"ORCA: A Challenging Benchmark for Arabic Language Understanding","created":"2022-12-21","cited_by_count":47,"area":null},{"id":"2211.00768","title":"Why is Winoground Hard? Investigating Failures in Visuolinguistic Compositionality","created":"2022-11-01","cited_by_count":44,"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":"2206.11249","title":"GEMv2: Multilingual NLG Benchmarking in a Single Line of Code","created":"2022-06-22","cited_by_count":36,"area":null},{"id":"2401.11943","title":"Benchmarking Large Multimodal Models against Common Corruptions","created":"2024-01-22","cited_by_count":24,"area":"lr"},{"id":"2207.02159","title":"Robustness Analysis of Video-Language Models Against Visual and Language Perturbations","created":"2022-07-05","cited_by_count":23,"area":null},{"id":"2403.03894","title":"IRCoder: Intermediate Representations Make Language Models Robust Multilingual Code Generators","created":"2024-03-06","cited_by_count":23,"area":null},{"id":"2404.03746","title":"GenQREnsemble: Zero-Shot LLM Ensemble Prompting for Generative Query Reformulation","created":"2024-04-04","cited_by_count":23,"area":null},{"id":"2503.17181","title":"A Study of LLMs' Preferences for Libraries and Programming Languages","created":"2025-03-21","cited_by_count":20,"area":null},{"id":"2207.03586","title":"CausalAgents: A Robustness Benchmark for Motion Forecasting using Causal Relationships","created":"2022-07-07","cited_by_count":18,"area":null},{"id":"2403.03893","title":"From One to Many: Expanding the Scope of Toxicity Mitigation in Language Models","created":"2024-03-06","cited_by_count":18,"area":null},{"id":"2306.13651","title":"Bring Your Own Data! Self-Supervised Evaluation for Large Language Models","created":"2023-06-23","cited_by_count":17,"area":null},{"id":"2203.09161","title":"How Many Data Samples is an Additional Instruction Worth?","created":"2022-03-17","cited_by_count":16,"area":null},{"id":"2211.02738","title":"Intriguing Properties of Compression on Multilingual Models","created":"2022-11-04","cited_by_count":15,"area":null},{"id":"2205.03589","title":"Learning Disentangled Textual Representations via Statistical Measures of Similarity","created":"2022-05-07","cited_by_count":14,"area":null},{"id":"2308.04813","title":"CLEVA: Chinese Language Models EVAluation Platform","created":"2023-08-09","cited_by_count":13,"area":null},{"id":"2304.03543","title":"HyperTab: Hypernetwork Approach for Deep Learning on Small Tabular Datasets","created":"2023-04-07","cited_by_count":10,"area":null},{"id":"2205.09178","title":"PreQuEL: Quality Estimation of Machine Translation Outputs in Advance","created":"2022-05-18","cited_by_count":9,"area":null},{"id":"2310.09668","title":"Beyond Testers' Biases: Guiding Model Testing with Knowledge Bases using LLMs","created":"2023-10-14","cited_by_count":9,"area":null},{"id":"2403.08688","title":"Token Alignment via Character Matching for Subword Completion","created":"2024-03-13","cited_by_count":9,"area":null},{"id":"2202.12875","title":"DataLab: A Platform for Data Analysis and Intervention","created":"2022-02-25","cited_by_count":8,"area":null},{"id":"2204.06239","title":"Can Question Rewriting Help Conversational Question Answering?","created":"2022-04-13","cited_by_count":8,"area":null},{"id":"2502.14445","title":"PredictaBoard: Benchmarking LLM Score Predictability","created":"2025-02-20","cited_by_count":7,"area":null},{"id":"2311.11226","title":"An Interactive Query Generation Assistant using LLM-based Prompt Modification and User Feedback","created":"2023-11-19","cited_by_count":6,"area":null},{"id":"2409.18023","title":"DARE: Diverse Visual Question Answering with Robustness Evaluation","created":"2024-09-26","cited_by_count":6,"area":"mllm"},{"id":"2209.01638","title":"Every picture tells a story: Image-grounded controllable stylistic story generation","created":"2022-09-04","cited_by_count":5,"area":null},{"id":"2210.06442","title":"Can Pretrained Language Models (Yet) Reason Deductively?","created":"2022-10-12","cited_by_count":5,"area":"lr"},{"id":"2210.12846","title":"EUREKA: EUphemism Recognition Enhanced through Knn-based methods and Augmentation","created":"2022-10-23","cited_by_count":5,"area":null},{"id":"2210.13749","title":"AugCSE: Contrastive Sentence Embedding with Diverse Augmentations","created":"2022-10-20","cited_by_count":5,"area":null},{"id":"2301.05133","title":"Is AI Art Another Industrial Revolution in the Making?","created":"2023-01-12","cited_by_count":5,"area":null},{"id":"2308.09435","title":"A Methodology for Generative Spelling Correction via Natural Spelling Errors Emulation across Multiple Domains and Languages","created":"2023-08-18","cited_by_count":5,"area":null},{"id":"2311.12405","title":"IndoRobusta: Towards Robustness Against Diverse Code-Mixed Indonesian Local Languages","created":"2023-11-21","cited_by_count":5,"area":null},{"id":"2405.17658","title":"Generative Query Reformulation Using Ensemble Prompting, Document Fusion, and Relevance Feedback","created":"2024-05-27","cited_by_count":5,"area":null},{"id":"2212.07473","title":"MABSplit: Faster Forest Training Using Multi-Armed Bandits","created":"2022-12-14","cited_by_count":4,"area":null},{"id":"2303.05378","title":"Greener yet Powerful: Taming Large Code Generation Models with Quantization","created":"2023-03-09","cited_by_count":4,"area":null},{"id":"2401.16454","title":"KAUCUS: Knowledge Augmented User Simulators for Training Language Model Assistants","created":"2024-01-29","cited_by_count":4,"area":null},{"id":"2211.06409","title":"Capabilities for Better ML Engineering","created":"2022-11-11","cited_by_count":3,"area":null},{"id":"2305.19915","title":"Source Code Data Augmentation for Deep Learning: A Survey","created":"2023-05-31","cited_by_count":3,"area":null},{"id":"2306.12907","title":"xSIM++: An Improved Proxy to Bitext Mining Performance for Low-Resource Languages","created":"2023-06-22","cited_by_count":3,"area":null},{"id":"2407.12872","title":"Evaluating Large Language Models with fmeval","created":"2024-07-15","cited_by_count":3,"area":null},{"id":"2508.07180","title":"Code2Bench: Scaling Source and Rigor for Dynamic Benchmark Construction","created":"2025-08-10","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":"2302.11412","title":"Data Augmentation for Neural NLP","created":"2023-02-22","cited_by_count":2,"area":null},{"id":"2404.07501","title":"Leveraging Data Augmentation for Process Information Extraction","created":"2024-04-11","cited_by_count":2,"area":null},{"id":"2408.15915","title":"Leveraging Open Knowledge for Advancing Task Expertise in Large Language Models","created":"2024-08-28","cited_by_count":2,"area":"moe"},{"id":"2209.07752","title":"PINEAPPLE: Personifying INanimate Entities by Acquiring Parallel Personification data for Learning Enhanced generation","created":"2022-09-16","cited_by_count":1,"area":null},{"id":"2304.11679","title":"Domain Mastery Benchmark: An Ever-Updating Benchmark for Evaluating Holistic Domain Knowledge of Large Language Model--A Preliminary Release","created":"2023-04-23","cited_by_count":1,"area":null},{"id":"2403.17220","title":"Making Sentence Embeddings Robust to User-Generated Content","created":"2024-03-25","cited_by_count":1,"area":null},{"id":"2507.16410","title":"GG-BBQ: German Gender Bias Benchmark for Question Answering","created":"2025-07-22","cited_by_count":1,"area":null},{"id":"2509.09714","title":"How Small Transformation Expose the Weakness of Semantic Similarity Measures","created":"2025-09-08","cited_by_count":1,"area":null},{"id":"2509.22202","title":"Library Hallucinations in LLM-Generated Code: A Risk Analysis Grounded in Developer Queries","created":"2025-09-26","cited_by_count":1,"area":null},{"id":"2202.03799","title":"What are the best systems? New perspectives on NLP Benchmarking","created":"2022-02-08","cited_by_count":0,"area":null},{"id":"2310.16251","title":"Speakerly: A Voice-based Writing Assistant for Text Composition","created":"2023-10-24","cited_by_count":0,"area":null},{"id":"2401.05871","title":"Enhancing Personality Recognition in Dialogue by Data Augmentation and Heterogeneous Conversational Graph Networks","created":"2024-01-11","cited_by_count":0,"area":null},{"id":"2603.13640","title":"SemRep: Generative Code Representation Learning with Code Transformations","created":"2026-03-13","cited_by_count":0,"area":null},{"id":"2603.17017","title":"LLM NL2SQL Robustness: Surface Noise vs. Linguistic Variation in Traditional and Agentic Settings","created":"2026-03-17","cited_by_count":0,"area":"agents"},{"id":"2605.19066","title":"The Annotation Scarcity Paradox in Low-Resource NLP Evaluation: A Decade of Acceleration and Emerging Constraints","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2610.12667","title":"perturber: A Stateless Service for Semantics-Preserving Text Perturbations","created":"2026-10-08","cited_by_count":0,"area":null}],"next_cursor":null}