{"total":45,"rows":[{"id":"2210.07229","title":"Mass-Editing Memory in a Transformer","created":"2022-10-13","cited_by_count":1001,"area":null},{"id":"2305.13169","title":"A Pretrainer's Guide to Training Data: Measuring the Effects of Data Age, Domain Coverage, Quality, & Toxicity","created":"2023-05-22","cited_by_count":182,"area":null},{"id":"2202.03829","title":"TimeLMs: Diachronic Language Models from Twitter","created":"2022-02-08","cited_by_count":131,"area":null},{"id":"2204.14211","title":"TemporalWiki: A Lifelong Benchmark for Training and Evaluating Ever-Evolving Language Models","created":"2022-04-29","cited_by_count":119,"area":null},{"id":"2306.04618","title":"Revisiting Out-of-distribution Robustness in NLP: Benchmark, Analysis, and LLMs Evaluations","created":"2023-06-07","cited_by_count":97,"area":null},{"id":"2310.14820","title":"ALCUNA: Large Language Models Meet New Knowledge","created":"2023-10-23","cited_by_count":35,"area":null},{"id":"2210.03797","title":"Named Entity Recognition in Twitter: A Dataset and Analysis on Short-Term Temporal Shifts","created":"2022-10-07","cited_by_count":28,"area":null},{"id":"2402.16797","title":"Set the Clock: Temporal Alignment of Pretrained Language Models","created":"2024-02-26","cited_by_count":25,"area":null},{"id":"2202.02093","title":"Temporal Attention for Language Models","created":"2022-02-04","cited_by_count":21,"area":null},{"id":"2302.12297","title":"Dynamic Benchmarking of Masked Language Models on Temporal Concept Drift with Multiple Views","created":"2023-02-23","cited_by_count":21,"area":null},{"id":"2402.12261","title":"NEO-BENCH: Evaluating Robustness of Large Language Models with Neologisms","created":"2024-02-19","cited_by_count":20,"area":null},{"id":"2209.07216","title":"TempoWiC: An Evaluation Benchmark for Detecting Meaning Shift in Social Media","created":"2022-09-15","cited_by_count":19,"area":null},{"id":"2411.08324","title":"Are LLMs Prescient? A Continuous Evaluation using Daily News as the Oracle","created":"2024-11-13","cited_by_count":19,"area":null},{"id":"2302.03147","title":"It's about Time: Rethinking Evaluation on Rumor Detection Benchmarks using Chronological Splits","created":"2023-02-06","cited_by_count":15,"area":null},{"id":"2305.14489","title":"Are Large Language Models Robust Coreference Resolvers?","created":"2023-05-23","cited_by_count":15,"area":null},{"id":"2504.02107","title":"TiC-LM: A Web-Scale Benchmark for Time-Continual LLM Pretraining","created":"2025-04-02","cited_by_count":15,"area":null},{"id":"2210.09197","title":"On the Impact of Temporal Concept Drift on Model Explanations","created":"2022-10-17","cited_by_count":14,"area":null},{"id":"2302.02500","title":"TempEL: Linking Dynamically Evolving and Newly Emerging Entities","created":"2023-02-05","cited_by_count":14,"area":null},{"id":"2405.14211","title":"ChronosLex: Time-aware Incremental Training for Temporal Generalization of Legal Classification Tasks","created":"2024-05-23","cited_by_count":11,"area":null},{"id":"2211.02162","title":"Time-aware Prompting for Text Generation","created":"2022-11-03","cited_by_count":10,"area":null},{"id":"2212.09747","title":"Do CoNLL-2003 Named Entity Taggers Still Work Well in 2023?","created":"2022-12-19","cited_by_count":9,"area":null},{"id":"2305.01951","title":"Can LMs Generalize to Future Data? An Empirical Analysis on Text Summarization","created":"2023-05-03","cited_by_count":9,"area":null},{"id":"2310.14757","title":"SuperTweetEval: A Challenging, Unified and Heterogeneous Benchmark for Social Media NLP Research","created":"2023-10-23","cited_by_count":9,"area":null},{"id":"2502.08825","title":"Examining and Adapting Time for Multilingual Classification via Mixture of Temporal Experts","created":"2025-02-12","cited_by_count":9,"area":null},{"id":"2407.17638","title":"Time Matters: Examine Temporal Effects on Biomedical Language Models","created":"2024-07-24","cited_by_count":7,"area":null},{"id":"2505.19572","title":"DocMEdit: Towards Document-Level Model Editing","created":"2025-05-26","cited_by_count":6,"area":null},{"id":"2205.12570","title":"EDIN: An End-to-end Benchmark and Pipeline for Unknown Entity Discovery and Indexing","created":"2022-05-25","cited_by_count":5,"area":null},{"id":"2401.07544","title":"See the Unseen: Better Context-Consistent Knowledge-Editing by Noises","created":"2024-01-15","cited_by_count":5,"area":null},{"id":"2206.11155","title":"Then and Now: Quantifying the Longitudinal Validity of Self-Disclosed Depression Diagnoses","created":"2022-06-22","cited_by_count":4,"area":null},{"id":"2410.10859","title":"FAME: Towards Factual Multi-Task Model Editing","created":"2024-10-07","cited_by_count":3,"area":null},{"id":"2208.10734","title":"Learning Dynamic Contextualised Word Embeddings via Template-based Temporal Adaptation","created":"2022-08-23","cited_by_count":2,"area":null},{"id":"2602.17234","title":"All Leaks Count, Some Count More: Interpretable Temporal Contamination Detection and Mitigation in LLM Backtesting","created":"2026-02-19","cited_by_count":2,"area":null},{"id":"2305.17127","title":"Characterizing and Measuring Linguistic Dataset Drift","created":"2023-05-26","cited_by_count":1,"area":null},{"id":"2406.19116","title":"CHEW: A Dataset of CHanging Events in Wikipedia","created":"2024-06-27","cited_by_count":1,"area":null},{"id":"2604.17650","title":"Measuring Distribution Shift in User Prompts and Its Effects on LLM Performance","created":"2026-04-19","cited_by_count":1,"area":null},{"id":"2604.22098","title":"Knowledge-driven Augmentation and Retrieval for Integrative Temporal Adaptation","created":"2026-04-23","cited_by_count":1,"area":null},{"id":"2301.07981","title":"Continuously Reliable Detection of New-Normal Misinformation: Semantic Masking and Contrastive Smoothing in High-Density Latent Regions","created":"2023-01-19","cited_by_count":0,"area":null},{"id":"2302.10016","title":"Boosting classification reliability of NLP transformer models in the long run","created":"2023-02-20","cited_by_count":0,"area":null},{"id":"2308.03582","title":"WIKITIDE: A Wikipedia-Based Timestamped Definition Pairs Dataset","created":"2023-08-07","cited_by_count":0,"area":null},{"id":"2309.13562","title":"Keeping in Time: Adding Temporal Context to Sentiment Analysis Models","created":"2023-09-24","cited_by_count":0,"area":null},{"id":"2404.10297","title":"Future Language Modeling from Temporal Document History","created":"2024-04-16","cited_by_count":0,"area":null},{"id":"2405.13017","title":"A Systematic Analysis on the Temporal Generalization of Language Models in Social Media","created":"2024-05-15","cited_by_count":0,"area":null},{"id":"2502.14897","title":"Market-Derived Financial Sentiment Analysis: Context-Aware Language Models for Crypto Forecasting","created":"2025-02-17","cited_by_count":0,"area":null},{"id":"2511.23056","title":"Decoding the Past: Explainable Machine Learning Models for Dating Historical Texts","created":"2025-11-28","cited_by_count":0,"area":null},{"id":"2609.19916","title":"KoNeoBench: A Curated Evaluation Dataset for LLM Understanding of Korean Neologisms","created":"2026-09-17","cited_by_count":0,"area":null}],"next_cursor":null}