{"list":"other","total":53,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"1910.13461","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","created":"2019-10-29","cited_by_count":5893},{"id":"2205.11916","title":"Large Language Models are Zero-Shot Reasoners","created":"2022-05-24","cited_by_count":4374},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"1701.06538","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","created":"2017-01-23","cited_by_count":3509},{"id":"2101.03961","title":"Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity","created":"2021-01-11","cited_by_count":3073},{"id":"1911.11641","title":"PIQA: Reasoning about Physical Commonsense in Natural Language","created":"2019-11-26","cited_by_count":2883},{"id":"2202.05262","title":"Locating and Editing Factual Associations in GPT","created":"2022-02-10","cited_by_count":2691},{"id":"2303.12712","title":"Sparks of Artificial General Intelligence: Early experiments with GPT-4","created":"2023-03-22","cited_by_count":2592},{"id":"2312.10997","title":"Retrieval-Augmented Generation for Large Language Models: A Survey","created":"2023-12-18","cited_by_count":2212},{"id":"2202.03629","title":"Survey of Hallucination in Natural Language Generation","created":"2022-02-08","cited_by_count":2075},{"id":"2210.07229","title":"Mass-Editing Memory in a Transformer","created":"2022-10-13","cited_by_count":1001},{"id":"2302.00487","title":"A Comprehensive Survey of Continual Learning: Theory, Method and Application","created":"2023-01-31","cited_by_count":872},{"id":"2311.03658","title":"The Linear Representation Hypothesis and the Geometry of Large Language Models","created":"2023-11-07","cited_by_count":716},{"id":"2104.08696","title":"Knowledge Neurons in Pretrained Transformers","created":"2021-04-18","cited_by_count":601},{"id":"2104.08164","title":"Editing Factual Knowledge in Language Models","created":"2021-04-16","cited_by_count":553},{"id":"2110.11309","title":"Fast Model Editing at Scale","created":"2021-10-21","cited_by_count":498},{"id":"2206.06520","title":"Memory-Based Model Editing at Scale","created":"2022-06-13","cited_by_count":447},{"id":"2203.09509","title":"ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detection","created":"2022-03-17","cited_by_count":422},{"id":"2305.13172","title":"Editing Large Language Models: Problems, Methods, and Opportunities","created":"2023-05-22","cited_by_count":372},{"id":"2302.09419","title":"A Comprehensive Survey on Pretrained Foundation Models: A History from BERT to ChatGPT","created":"2023-02-18","cited_by_count":368},{"id":"2305.12740","title":"Can We Edit Factual Knowledge by In-Context Learning?","created":"2023-05-22","cited_by_count":285},{"id":"2211.11031","title":"Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptors","created":"2022-11-20","cited_by_count":271},{"id":"2301.04213","title":"Does Localization Inform Editing? Surprising Differences in Causality-Based Localization vs. Knowledge Editing in Language Models","created":"2023-01-10","cited_by_count":243},{"id":"2307.12976","title":"Evaluating the Ripple Effects of Knowledge Editing in Language Models","created":"2023-07-24","cited_by_count":242},{"id":"2012.00363","title":"Modifying Memories in Transformer Models","created":"2020-12-01","cited_by_count":224},{"id":"1610.09038","title":"Professor Forcing: A New Algorithm for Training Recurrent Networks","created":"2016-10-27","cited_by_count":216},{"id":"2407.02485","title":"RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMs","created":"2024-07-02","cited_by_count":202},{"id":"2301.09785","title":"Transformer-Patcher: One Mistake worth One Neuron","created":"2023-01-24","cited_by_count":197},{"id":"2404.03592","title":"ReFT: Representation Finetuning for Language Models","created":"2024-04-04","cited_by_count":197},{"id":"2310.16218","title":"Knowledge Editing for Large Language Models: A Survey","created":"2023-10-24","cited_by_count":194},{"id":"2401.01286","title":"A Comprehensive Study of Knowledge Editing for Large Language Models","created":"2024-01-02","cited_by_count":163},{"id":"2304.00740","title":"Inspecting and Editing Knowledge Representations in Language Models","created":"2023-04-03","cited_by_count":141},{"id":"2308.07269","title":"EasyEdit: An Easy-to-use Knowledge Editing Framework for Large Language Models","created":"2023-08-14","cited_by_count":98},{"id":"2210.03329","title":"Calibrating Factual Knowledge in Pretrained Language Models","created":"2022-10-07","cited_by_count":92},{"id":"2405.14768","title":"WISE: Rethinking the Knowledge Memory for Lifelong Model Editing of Large Language Models","created":"2024-05-23","cited_by_count":92},{"id":"1909.10705","title":"Do Massively Pretrained Language Models Make Better Storytellers?","created":"2019-09-24","cited_by_count":90},{"id":"2312.11795","title":"MELO: Enhancing Model Editing with Neuron-Indexed Dynamic LoRA","created":"2023-12-19","cited_by_count":80},{"id":"2402.11905","title":"Learning to Edit: Aligning LLMs with Knowledge Editing","created":"2024-02-19","cited_by_count":43},{"id":"2402.11129","title":"BlendFilter: Advancing Retrieval-Augmented Large Language Models via Query Generation Blending and Knowledge Filtering","created":"2024-02-16","cited_by_count":29},{"id":"2410.17952","title":"SimRAG: Self-Improving Retrieval-Augmented Generation for Adapting Large Language Models to Specialized Domains","created":"2024-10-23","cited_by_count":28},{"id":"2308.09954","title":"DocTER: Evaluating Document-based Knowledge Editing","created":"2023-08-19","cited_by_count":26},{"id":"2406.10777","title":"RoseLoRA: Row and Column-wise Sparse Low-rank Adaptation of Pre-trained Language Model for Knowledge Editing and Fine-tuning","created":"2024-06-16","cited_by_count":21},{"id":"2402.16123","title":"InstructEdit: Instruction-based Knowledge Editing for Large Language Models","created":"2024-02-25","cited_by_count":17},{"id":"2402.13048","title":"Stable Knowledge Editing in Large Language Models","created":"2024-02-20","cited_by_count":13},{"id":"2502.10993","title":"RoseRAG: Robust Retrieval-augmented Generation with Small-scale LLMs via Margin-aware Preference Optimization","created":"2025-02-16","cited_by_count":9},{"id":"2502.00602","title":"Mitigating Heterogeneous Token Overfitting in LLM Knowledge Editing","created":"2025-02-02","cited_by_count":8}],"next_cursor":null}