{"list":"other","total":55,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2202.05262","title":"Locating and Editing Factual Associations in GPT","created":"2022-02-10","cited_by_count":2691},{"id":"2012.14913","title":"Transformer Feed-Forward Layers Are Key-Value Memories","created":"2020-12-29","cited_by_count":1336},{"id":"2212.04089","title":"Editing Models with Task Arithmetic","created":"2022-12-08","cited_by_count":1120},{"id":"2210.07229","title":"Mass-Editing Memory in a Transformer","created":"2022-10-13","cited_by_count":1001},{"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":"2203.14680","title":"Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space","created":"2022-03-28","cited_by_count":532},{"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":"2304.08467","title":"Learning to Compress Prompts with Gist Tokens","created":"2023-04-17","cited_by_count":390},{"id":"2305.14795","title":"MQuAKE: Assessing Knowledge Editing in Language Models via Multi-Hop Questions","created":"2023-05-24","cited_by_count":300},{"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":"2306.03819","title":"LEACE: Perfect linear concept erasure in closed form","created":"2023-06-06","cited_by_count":267},{"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":"2301.09785","title":"Transformer-Patcher: One Mistake worth One Neuron","created":"2023-01-24","cited_by_count":197},{"id":"2308.08742","title":"PMET: Precise Model Editing in a Transformer","created":"2023-08-17","cited_by_count":173},{"id":"2211.05110","title":"Large Language Models with Controllable Working Memory","created":"2022-11-09","cited_by_count":169},{"id":"2110.07814","title":"Meta-learning via Language Model In-context Tuning","created":"2021-10-15","cited_by_count":164},{"id":"2401.01286","title":"A Comprehensive Study of Knowledge Editing for Large Language Models","created":"2024-01-02","cited_by_count":163},{"id":"2004.00345","title":"Editable Neural Networks","created":"2020-04-01","cited_by_count":155},{"id":"2209.15189","title":"Learning by Distilling Context","created":"2022-09-30","cited_by_count":138},{"id":"1809.05972","title":"Generating Informative and Diverse Conversational Responses via Adversarial Information Maximization","created":"2018-09-16","cited_by_count":116},{"id":"2402.04624","title":"MEMORYLLM: Towards Self-Updatable Large Language Models","created":"2024-02-07","cited_by_count":93},{"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":"2403.14472","title":"Detoxifying Large Language Models via Knowledge Editing","created":"2024-03-21","cited_by_count":87},{"id":"2312.11795","title":"MELO: Enhancing Model Editing with Neuron-Indexed Dynamic LoRA","created":"2023-12-19","cited_by_count":80},{"id":"2111.13654","title":"Do Language Models Have Beliefs? Methods for Detecting, Updating, and Visualizing Model Beliefs","created":"2021-11-26","cited_by_count":79},{"id":"2310.20138","title":"DEPN: Detecting and Editing Privacy Neurons in Pretrained Language Models","created":"2023-10-31","cited_by_count":79},{"id":"2305.01651","title":"Can LMs Learn New Entities from Descriptions? Challenges in Propagating Injected Knowledge","created":"2023-05-02","cited_by_count":67},{"id":"2112.01008","title":"Editing a classifier by rewriting its prediction rules","created":"2021-12-02","cited_by_count":65},{"id":"2311.04661","title":"Massive Editing for Large Language Models via Meta Learning","created":"2023-11-08","cited_by_count":63},{"id":"2305.17553","title":"Detecting Edit Failures In Large Language Models: An Improved Specificity Benchmark","created":"2023-05-27","cited_by_count":62},{"id":"2403.14236","title":"A Unified Framework for Model Editing","created":"2024-03-21","cited_by_count":57},{"id":"2402.11905","title":"Learning to Edit: Aligning LLMs with Knowledge Editing","created":"2024-02-19","cited_by_count":43},{"id":"2212.10670","title":"In-context Learning Distillation: Transferring Few-shot Learning Ability of Pre-trained Language Models","created":"2022-12-20","cited_by_count":37},{"id":"2404.03646","title":"Locating and Editing Factual Associations in Mamba","created":"2024-04-04","cited_by_count":37},{"id":"2310.10322","title":"Evaluating the Reversal Curse in Model Editing","created":"2023-10-16","cited_by_count":34},{"id":"2211.03318","title":"Fixing Model Bugs with Natural Language Patches","created":"2022-11-07","cited_by_count":33},{"id":"2401.10471","title":"DeepEdit: Knowledge Editing as Decoding with Constraints","created":"2024-01-19","cited_by_count":33},{"id":"2305.14956","title":"Editing Common Sense in Transformers","created":"2023-05-24","cited_by_count":28},{"id":"2207.04806","title":"Repairing Neural Networks by Leaving the Right Past Behind","created":"2022-07-11","cited_by_count":27},{"id":"2205.12677","title":"Language Anisotropic Cross-Lingual Model Editing","created":"2022-05-25","cited_by_count":26},{"id":"2301.10405","title":"Editing Language Model-based Knowledge Graph Embeddings","created":"2023-01-25","cited_by_count":23},{"id":"2204.12785","title":"Plug-and-Play Adaptation for Continuously-updated QA","created":"2022-04-27","cited_by_count":21},{"id":"2406.09920","title":"Knowledge Editing in Language Models via Adapted Direct Preference Optimization","created":"2024-06-14","cited_by_count":17},{"id":"2311.08011","title":"Forgetting before Learning: Utilizing Parametric Arithmetic for Knowledge Updating in Large Language Models","created":"2023-11-14","cited_by_count":15},{"id":"2211.13317","title":"Rank-One Editing of Encoder-Decoder Models","created":"2022-11-23","cited_by_count":7},{"id":"2401.07544","title":"See the Unseen: Better Context-Consistent Knowledge-Editing by Noises","created":"2024-01-15","cited_by_count":5},{"id":"2403.17431","title":"Robust and Scalable Model Editing for Large Language Models","created":"2024-03-26","cited_by_count":2}],"next_cursor":null}