{"list":"other","total":74,"rows":[{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"2109.07958","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","created":"2021-09-08","cited_by_count":2975},{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"id":"2101.00027","title":"The Pile: An 800GB Dataset of Diverse Text for Language Modeling","created":"2020-12-31","cited_by_count":2411},{"id":"1706.08840","title":"Gradient Episodic Memory for Continual Learning","created":"2017-06-26","cited_by_count":1898},{"id":"2210.09261","title":"Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them","created":"2022-10-17","cited_by_count":1807},{"id":"2304.01373","title":"Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling","created":"2023-04-03","cited_by_count":1786},{"id":"1703.04730","title":"Understanding Black-box Predictions via Influence Functions","created":"2017-03-14","cited_by_count":1741},{"id":"1711.09601","title":"Memory Aware Synapses: Learning what (not) to forget","created":"2017-11-27","cited_by_count":1105},{"id":"1812.00420","title":"Efficient Lifelong Learning with A-GEM","created":"2018-12-02","cited_by_count":1058},{"id":"2004.07211","title":"Dark Experience for General Continual Learning: a Strong, Simple Baseline","created":"2020-04-15","cited_by_count":911},{"id":"2301.13688","title":"The Flan Collection: Designing Data and Methods for Effective Instruction Tuning","created":"2023-01-31","cited_by_count":739},{"id":"1902.06720","title":"Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent","created":"2019-02-18","cited_by_count":738},{"id":"2304.14997","title":"Towards Automated Circuit Discovery for Mechanistic Interpretability","created":"2023-04-28","cited_by_count":724},{"id":"1312.6211","title":"An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networks","created":"2013-12-21","cited_by_count":722},{"id":"1812.05159","title":"An Empirical Study of Example Forgetting during Deep Neural Network Learning","created":"2018-12-12","cited_by_count":678},{"id":"2204.04799","title":"DualPrompt: Complementary Prompting for Rehearsal-free Continual Learning","created":"2022-04-10","cited_by_count":642},{"id":"2402.00838","title":"OLMo: Accelerating the Science of Language Models","created":"2024-02-01","cited_by_count":613},{"id":"1903.08671","title":"Gradient based sample selection for online continual learning","created":"2019-03-20","cited_by_count":571},{"id":"2402.04333","title":"LESS: Selecting Influential Data for Targeted Instruction Tuning","created":"2024-02-06","cited_by_count":532},{"id":"2008.03703","title":"What Neural Networks Memorize and Why: Discovering the Long Tail via Influence Estimation","created":"2020-08-09","cited_by_count":497},{"id":"2402.00159","title":"Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research","created":"2024-01-31","cited_by_count":483},{"id":"2211.13218","title":"CODA-Prompt: COntinual Decomposed Attention-based Prompting for Rehearsal-Free Continual Learning","created":"2022-11-23","cited_by_count":450},{"id":"2009.10795","title":"Dataset Cartography: Mapping and Diagnosing Datasets with Training Dynamics","created":"2020-09-22","cited_by_count":425},{"id":"2310.01377","title":"UltraFeedback: Boosting Language Models with Scaled AI Feedback","created":"2023-10-02","cited_by_count":406},{"id":"2406.11794","title":"DataComp-LM: In search of the next generation of training sets for language models","created":"2024-06-17","cited_by_count":398},{"id":"1908.04742","title":"Online Continual Learning with Maximally Interfered Retrieval","created":"2019-08-11","cited_by_count":379},{"id":"2305.13172","title":"Editing Large Language Models: Problems, Methods, and Opportunities","created":"2023-05-22","cited_by_count":372},{"id":"2405.09673","title":"LoRA Learns Less and Forgets Less","created":"2024-05-15","cited_by_count":328},{"id":"2209.02299","title":"A Survey of Machine Unlearning","created":"2022-09-06","cited_by_count":312},{"id":"2303.14186","title":"TRAK: Attributing Model Behavior at Scale","created":"2023-03-24","cited_by_count":283},{"id":"2404.16789","title":"Continual Learning of Large Language Models: A Comprehensive Survey","created":"2024-04-25","cited_by_count":234},{"id":"2311.10702","title":"Camels in a Changing Climate: Enhancing LM Adaptation with Tulu 2","created":"2023-11-17","cited_by_count":229},{"id":"2205.10770","title":"Memorization Without Overfitting: Analyzing the Training Dynamics of Large Language Models","created":"2022-05-22","cited_by_count":220},{"id":"2202.07785","title":"Predictability and Surprise in Large Generative Models","created":"2022-02-15","cited_by_count":210},{"id":"2301.12314","title":"Progressive Prompts: Continual Learning for Language Models","created":"2023-01-29","cited_by_count":197},{"id":"2202.00622","title":"Datamodels: Predicting Predictions from Training Data","created":"2022-02-01","cited_by_count":189},{"id":"1906.01076","title":"Episodic Memory in Lifelong Language Learning","created":"2019-06-03","cited_by_count":188},{"id":"2403.16952","title":"Data Mixing Laws: Optimizing Data Mixtures by Predicting Language Modeling Performance","created":"2024-03-25","cited_by_count":184},{"id":"2401.01286","title":"A Comprehensive Study of Knowledge Editing for Large Language Models","created":"2024-01-02","cited_by_count":163},{"id":"2007.07400","title":"Anatomy of Catastrophic Forgetting: Hidden Representations and Task Semantics","created":"2020-07-14","cited_by_count":161},{"id":"1909.03329","title":"LAMOL: LAnguage MOdeling for Lifelong Language Learning","created":"2019-09-07","cited_by_count":160},{"id":"2205.12393","title":"Fine-tuned Language Models are Continual Learners","created":"2022-05-24","cited_by_count":156},{"id":"2304.11158","title":"Emergent and Predictable Memorization in Large Language Models","created":"2023-04-21","cited_by_count":148},{"id":"2402.01364","title":"Continual Learning for Large Language Models: A Survey","created":"2024-02-02","cited_by_count":147},{"id":"2309.10105","title":"Understanding Catastrophic Forgetting in Language Models via Implicit Inference","created":"2023-09-18","cited_by_count":144},{"id":"2112.09153","title":"An Empirical Investigation of the Role of Pre-training in Lifelong Learning","created":"2021-12-16","cited_by_count":134},{"id":"2403.08763","title":"Simple and Scalable Strategies to Continually Pre-train Large Language Models","created":"2024-03-13","cited_by_count":127},{"id":"2403.01244","title":"Mitigating Catastrophic Forgetting in Large Language Models with Self-Synthesized Rehearsal","created":"2024-03-02","cited_by_count":118},{"id":"2010.04003","title":"A Theoretical Analysis of Catastrophic Forgetting through the NTK Overlap Matrix","created":"2020-10-07","cited_by_count":103},{"id":"2406.04836","title":"Revisiting Catastrophic Forgetting in Large Language Model Tuning","created":"2024-06-07","cited_by_count":99},{"id":"2107.04384","title":"Continual Learning in the Teacher-Student Setup: Impact of Task Similarity","created":"2021-07-09","cited_by_count":88},{"id":"2205.09588","title":"How catastrophic can catastrophic forgetting be in linear regression?","created":"2022-05-19","cited_by_count":81},{"id":"2307.09218","title":"A Comprehensive Survey of Forgetting in Deep Learning Beyond Continual Learning","created":"2023-07-16","cited_by_count":69},{"id":"2110.11526","title":"Wide Neural Networks Forget Less Catastrophically","created":"2021-10-21","cited_by_count":64},{"id":"2205.00329","title":"Continual Learning with Foundation Models: An Empirical Study of Latent Replay","created":"2022-04-30","cited_by_count":61},{"id":"2403.11435","title":"InsCL: A Data-efficient Continual Learning Paradigm for Fine-tuning Large Language Models with Instructions","created":"2024-03-18","cited_by_count":58},{"id":"2005.00870","title":"Predicting Performance for Natural Language Processing Tasks","created":"2020-05-02","cited_by_count":49},{"id":"2307.01163","title":"Improving Language Plasticity via Pretraining with Active Forgetting","created":"2023-07-03","cited_by_count":43},{"id":"2406.01375","title":"D-CPT Law: Domain-specific Continual Pre-Training Scaling Law for Large Language Models","created":"2024-06-03","cited_by_count":41},{"id":"2404.02062","title":"Digital Forgetting in Large Language Models: A Survey of Unlearning Methods","created":"2024-04-02","cited_by_count":40},{"id":"2401.05605","title":"Scaling Laws for Forgetting When Fine-Tuning Large Language Models","created":"2024-01-11","cited_by_count":38},{"id":"2210.15031","title":"Characterizing Datapoints via Second-Split Forgetting","created":"2022-10-26","cited_by_count":37},{"id":"2305.14947","title":"How Predictable Are Large Language Model Capabilities? A Case Study on BIG-bench","created":"2023-05-24","cited_by_count":34},{"id":"2405.17583","title":"Understanding Forgetting in Continual Learning with Linear Regression","created":"2024-05-27","cited_by_count":30},{"id":"2305.16252","title":"Overcoming Catastrophic Forgetting in Massively Multilingual Continual Learning","created":"2023-05-25","cited_by_count":27},{"id":"2401.12617","title":"The Joint Effect of Task Similarity and Overparameterization on Catastrophic Forgetting -- An Analytical Model","created":"2024-01-23","cited_by_count":26},{"id":"2207.04543","title":"Challenging Common Assumptions about Catastrophic Forgetting","created":"2022-07-10","cited_by_count":20},{"id":"2304.04158","title":"Does Continual Learning Equally Forget All Parameters?","created":"2023-04-09","cited_by_count":18},{"id":"2303.01081","title":"Can BERT Refrain from Forgetting on Sequential Tasks? A Probing Study","created":"2023-03-02","cited_by_count":11},{"id":"2402.01865","title":"What Will My Model Forget? Forecasting Forgotten Examples in Language Model Refinement","created":"2024-02-02","cited_by_count":9}],"next_cursor":null}