{"total":70,"rows":[{"id":"2211.11501","title":"DS-1000: A Natural and Reliable Benchmark for Data Science Code Generation","created":"2022-11-18","cited_by_count":452,"area":null},{"id":"2310.18018","title":"NLP Evaluation in trouble: On the Need to Measure LLM Data Contamination for each Benchmark","created":"2023-10-27","cited_by_count":348,"area":null},{"id":"2304.04675","title":"Multilingual Machine Translation with Large Language Models: Empirical Results and Analysis","created":"2023-04-10","cited_by_count":160,"area":null},{"id":"2406.04244","title":"Benchmark Data Contamination of Large Language Models: A Survey","created":"2024-06-06","cited_by_count":147,"area":null},{"id":"2202.07206","title":"Impact of Pretraining Term Frequencies on Few-Shot Reasoning","created":"2022-02-15","cited_by_count":142,"area":"lr"},{"id":"2305.00118","title":"Speak, Memory: An Archaeology of Books Known to ChatGPT/GPT-4","created":"2023-04-28","cited_by_count":125,"area":"safety"},{"id":"2502.01534","title":"Preference Leakage: A Contamination Problem in LLM-as-a-judge","created":"2025-02-03","cited_by_count":125,"area":null},{"id":"2406.14991","title":"SpreadsheetBench: Towards Challenging Real World Spreadsheet Manipulation","created":"2024-06-21","cited_by_count":111,"area":null},{"id":"2310.13771","title":"Copyright Violations and Large Language Models","created":"2023-10-20","cited_by_count":108,"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":"2310.11501","title":"CoMPosT: Characterizing and Evaluating Caricature in LLM Simulations","created":"2023-10-17","cited_by_count":97,"area":null},{"id":"2310.16787","title":"The Data Provenance Initiative: A Large Scale Audit of Dataset Licensing & Attribution in AI","created":"2023-10-25","cited_by_count":73,"area":null},{"id":"2409.09788","title":"Reasoning Paths with Reference Objects Elicit Quantitative Spatial Reasoning in Large Vision-Language Models","created":"2024-09-15","cited_by_count":54,"area":"lr"},{"id":"2407.14933","title":"Consent in Crisis: The Rapid Decline of the AI Data Commons","created":"2024-07-20","cited_by_count":46,"area":null},{"id":"2205.14704","title":"Decoupling Knowledge from Memorization: Retrieval-augmented Prompt Learning","created":"2022-05-29","cited_by_count":36,"area":"rag"},{"id":"2206.15076","title":"BigBIO: A Framework for Data-Centric Biomedical Natural Language Processing","created":"2022-06-30","cited_by_count":36,"area":null},{"id":"2310.14820","title":"ALCUNA: Large Language Models Meet New Knowledge","created":"2023-10-23","cited_by_count":35,"area":null},{"id":"2502.14425","title":"A Survey on Data Contamination for Large Language Models","created":"2025-02-20","cited_by_count":35,"area":null},{"id":"2407.09777","title":"Graph Transformers: A Survey","created":"2024-07-13","cited_by_count":32,"area":null},{"id":"2410.02650","title":"Undesirable Memorization in Large Language Models: A Survey","created":"2024-10-03","cited_by_count":29,"area":null},{"id":"2410.18966","title":"Does Data Contamination Detection Work (Well) for LLMs? A Survey and Evaluation on Detection Assumptions","created":"2024-10-24","cited_by_count":26,"area":null},{"id":"2401.04531","title":"MERA: A Comprehensive LLM Evaluation in Russian","created":"2024-01-09","cited_by_count":22,"area":null},{"id":"2203.12171","title":"An Empirical Study of Memorization in NLP","created":"2022-03-23","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":"2405.16391","title":"When does compositional structure yield compositional generalization? A kernel theory","created":"2024-05-26","cited_by_count":20,"area":null},{"id":"2106.08704","title":"Memorization and Generalization in Neural Code Intelligence Models","created":"2021-06-16","cited_by_count":19,"area":null},{"id":"2306.14583","title":"Exploring the Robustness of Large Language Models for Solving Programming Problems","created":"2023-06-26","cited_by_count":16,"area":null},{"id":"2410.08385","title":"Language model developers should report train-test overlap","created":"2024-10-10","cited_by_count":16,"area":null},{"id":"2210.05769","title":"Vote'n'Rank: Revision of Benchmarking with Social Choice Theory","created":"2022-10-11","cited_by_count":15,"area":null},{"id":"2412.06745","title":"ONEBench to Test Them All: Sample-Level Benchmarking Over Open-Ended Capabilities","created":"2024-12-09","cited_by_count":15,"area":null},{"id":"2110.03111","title":"Cut the CARP: Fishing for zero-shot story evaluation","created":"2021-10-06","cited_by_count":14,"area":null},{"id":"2403.11395","title":"Automated data processing and feature engineering for deep learning and big data applications: a survey","created":"2024-03-18","cited_by_count":14,"area":null},{"id":"2404.00699","title":"A Comprehensive Survey of Contamination Detection Methods in Large Language Models","created":"2024-03-31","cited_by_count":12,"area":null},{"id":"2210.12813","title":"TAPE: Assessing Few-shot Russian Language Understanding","created":"2022-10-23","cited_by_count":11,"area":null},{"id":"2406.04197","title":"DICE: Detecting In-distribution Contamination in LLM's Fine-tuning Phase for Math Reasoning","created":"2024-06-06","cited_by_count":11,"area":"lr"},{"id":"2112.01342","title":"How not to Lie with a Benchmark: Rearranging NLP Leaderboards","created":"2021-12-02","cited_by_count":9,"area":null},{"id":"2407.17631","title":"BLAZE: Cross-Language and Cross-Project Bug Localization via Dynamic Chunking and Hard Example Learning","created":"2024-07-24","cited_by_count":7,"area":null},{"id":"2310.10190","title":"Battle of the Large Language Models: Dolly vs LLaMA vs Vicuna vs Guanaco vs Bard vs ChatGPT -- A Text-to-SQL Parsing Comparison","created":"2023-10-16","cited_by_count":6,"area":null},{"id":"2407.04065","title":"On the Workflows and Smells of Leaderboard Operations (LBOps): An Exploratory Study of Foundation Model Leaderboards","created":"2024-07-04","cited_by_count":6,"area":null},{"id":"2111.09612","title":"How Emotionally Stable is ALBERT? Testing Robustness with Stochastic Weight Averaging on a Sentiment Analysis Task","created":"2021-11-18","cited_by_count":5,"area":null},{"id":"2205.15951","title":"Hollywood Identity Bias Dataset: A Context Oriented Bias Analysis of Movie Dialogues","created":"2022-05-31","cited_by_count":5,"area":null},{"id":"2306.12550","title":"On Evaluation of Document Classification using RVL-CDIP","created":"2023-06-21","cited_by_count":5,"area":null},{"id":"2402.14482","title":"SpanSeq: Similarity-based sequence data splitting method for improved development and assessment of deep learning projects","created":"2024-02-22","cited_by_count":5,"area":null},{"id":"2503.22948","title":"SUV: Scalable Large Language Model Copyright Compliance with Regularized Selective Unlearning","created":"2025-03-29","cited_by_count":5,"area":"alignment"},{"id":"2509.08604","title":"Memorization in Large Language Models in Medicine: Prevalence, Characteristics, and Implications","created":"2025-09-10","cited_by_count":5,"area":null},{"id":"2311.03663","title":"Principles from Clinical Research for NLP Model Generalization","created":"2023-11-07","cited_by_count":4,"area":null},{"id":"2503.14900","title":"Deep Contrastive Unlearning for Language Models","created":"2025-03-19","cited_by_count":4,"area":"safety"},{"id":"2505.22945","title":"OWL: Probing Cross-Lingual Recall of Memorized Texts via World Literature","created":"2025-05-28","cited_by_count":4,"area":null},{"id":"2310.08008","title":"Effects of Human Adversarial and Affable Samples on BERT Generalization","created":"2023-10-12","cited_by_count":3,"area":null},{"id":"2407.09311","title":"Scalability of Bayesian Network Structure Elicitation with Large Language Models: a Novel Methodology and Comparative Analysis","created":"2024-07-12","cited_by_count":3,"area":null},{"id":"2506.09093","title":"Merging Smarter, Generalizing Better: Enhancing Model Merging on OOD Data","created":"2025-06-10","cited_by_count":3,"area":null},{"id":"2601.20858","title":"When Flores Bloomz Wrong: Cross-Direction Contamination in Machine Translation Evaluation","created":"2026-01-28","cited_by_count":3,"area":null},{"id":"2201.02229","title":"Large-scale protein-protein post-translational modification extraction with distant supervision and confidence calibrated BioBERT","created":"2022-01-06","cited_by_count":2,"area":null},{"id":"2404.05632","title":"Fighting crime with Transformers: Empirical analysis of address parsing methods in payment data","created":"2024-04-08","cited_by_count":2,"area":null},{"id":"2412.18497","title":"Neuron-Level Differentiation of Memorization and Generalization in Large Language Models","created":"2024-12-24","cited_by_count":2,"area":null},{"id":"2512.22633","title":"Rethinking the Capability of Fine-Tuned Language Models for Automated Vulnerability Repair","created":"2025-12-27","cited_by_count":2,"area":"lr"},{"id":"2602.00628","title":"From Associations to Activations: Comparing Behavioral and Hidden-State Semantic Geometry in LLMs","created":"2026-01-31","cited_by_count":2,"area":null},{"id":"2407.18738","title":"Towards Generalized Offensive Language Identification","created":"2024-07-26","cited_by_count":1,"area":null},{"id":"2502.16701","title":"Beyond Release: Access Considerations for Generative AI Systems","created":"2025-02-23","cited_by_count":1,"area":null},{"id":"2506.14474","title":"LexiMark: Robust Watermarking via Lexical Substitutions to Enhance Membership Verification of an LLM's Textual Training Data","created":"2025-06-17","cited_by_count":1,"area":"safety"},{"id":"2310.12135","title":"Pseudointelligence: A Unifying Framework for Language Model Evaluation","created":"2023-10-18","cited_by_count":0,"area":null},{"id":"2311.10236","title":"Latent Feature-based Data Splits to Improve Generalisation Evaluation: A Hate Speech Detection Case Study","created":"2023-11-16","cited_by_count":0,"area":"safety"},{"id":"2311.12337","title":"Do Smaller Language Models Answer Contextualised Questions Through Memorisation Or Generalisation?","created":"2023-11-21","cited_by_count":0,"area":null},{"id":"2512.20145","title":"Retrieval-augmented Prompt Learning for Pre-trained Foundation Models","created":"2025-12-23","cited_by_count":0,"area":"rag"},{"id":"2601.05500","title":"The Illusion of AI Expertise Under Uncertainty: A Probabilistic Paradigm to Interpret Results Under Ground Truth Variation","created":"2026-01-09","cited_by_count":0,"area":null},{"id":"2601.05713","title":"Visualising Information Flow in Word Embeddings with Diffusion Tensor Imaging","created":"2026-01-09","cited_by_count":0,"area":null},{"id":"2604.20256","title":"RADS: Reinforcement Learning-Based Sample Selection Improves Transfer Learning in Low-resource and Imbalanced Clinical Settings","created":"2026-04-22","cited_by_count":0,"area":"deeprl"},{"id":"2607.19718","title":"Lightweight Person-Place Relation Extraction from Historical Newspapers with Dependency Graphs and Proximity Features","created":"2026-07-22","cited_by_count":0,"area":null},{"id":"2609.07965","title":"Rethinking Sign Language Translation: The Impact of Signer Dependence on Model Evaluation","created":"2026-09-07","cited_by_count":0,"area":null},{"id":"2610.17654","title":"Decouple to Forget: Semantic Mediation for Sensitive Unlearning in Large Language Models","created":"2026-10-13","cited_by_count":0,"area":"safety"}],"next_cursor":null}