{"list":"other","total":51,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2202.05262","title":"Locating and Editing Factual Associations in GPT","created":"2022-02-10","cited_by_count":2691},{"id":"2202.03629","title":"Survey of Hallucination in Natural Language Generation","created":"2022-02-08","cited_by_count":2075},{"id":"2311.05232","title":"A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions","created":"2023-11-09","cited_by_count":1601},{"id":"2012.14913","title":"Transformer Feed-Forward Layers Are Key-Value Memories","created":"2020-12-29","cited_by_count":1336},{"id":"2210.07229","title":"Mass-Editing Memory in a Transformer","created":"2022-10-13","cited_by_count":1001},{"id":"1704.00051","title":"Reading Wikipedia to Answer Open-Domain Questions","created":"2017-03-31","cited_by_count":777},{"id":"2309.01219","title":"Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models","created":"2023-09-03","cited_by_count":698},{"id":"1906.00300","title":"Latent Retrieval for Weakly Supervised Open Domain Question Answering","created":"2019-06-01","cited_by_count":695},{"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":"2303.07345","title":"Erasing Concepts from Diffusion Models","created":"2023-03-13","cited_by_count":539},{"id":"1911.12237","title":"SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarization","created":"2019-11-27","cited_by_count":535},{"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":"1706.04115","title":"Zero-Shot Relation Extraction via Reading Comprehension","created":"2017-06-13","cited_by_count":426},{"id":"2305.13172","title":"Editing Large Language Models: Problems, Methods, and Opportunities","created":"2023-05-22","cited_by_count":372},{"id":"2306.03078","title":"SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compression","created":"2023-06-05","cited_by_count":367},{"id":"2302.12813","title":"Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedback","created":"2023-02-24","cited_by_count":353},{"id":"2305.14795","title":"MQuAKE: Assessing Knowledge Editing in Language Models via Multi-Hop Questions","created":"2023-05-24","cited_by_count":300},{"id":"1301.2300","title":"Direct and Indirect Effects","created":"2013-01-10","cited_by_count":280},{"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":"2401.01286","title":"A Comprehensive Study of Knowledge Editing for Large Language Models","created":"2024-01-02","cited_by_count":163},{"id":"2401.18018","title":"On Prompt-Driven Safeguarding for Large Language Models","created":"2024-01-31","cited_by_count":116},{"id":"2402.01761","title":"Rethinking Interpretability in the Era of Large Language Models","created":"2024-01-30","cited_by_count":111},{"id":"2401.04700","title":"Model Editing Harms General Abilities of Large Language Models: Regularization to the Rescue","created":"2024-01-09","cited_by_count":103},{"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":"2401.07453","title":"Model Editing at Scale leads to Gradual and Catastrophic Forgetting","created":"2024-01-15","cited_by_count":93},{"id":"2312.11795","title":"MELO: Enhancing Model Editing with Neuron-Indexed Dynamic LoRA","created":"2023-12-19","cited_by_count":80},{"id":"2403.14236","title":"A Unified Framework for Model Editing","created":"2024-03-21","cited_by_count":57},{"id":"2402.09656","title":"The Butterfly Effect of Model Editing: Few Edits Can Trigger Large Language Models Collapse","created":"2024-02-15","cited_by_count":54},{"id":"2309.05516","title":"Optimize Weight Rounding via Signed Gradient Descent for the Quantization of LLMs","created":"2023-09-11","cited_by_count":50},{"id":"2403.07175","title":"Rebuilding ROME : Resolving Model Collapse during Sequential Model Editing","created":"2024-03-11","cited_by_count":50},{"id":"2310.02129","title":"Unveiling the Pitfalls of Knowledge Editing for Large Language Models","created":"2023-10-03","cited_by_count":43},{"id":"2402.10987","title":"WilKE: Wise-Layer Knowledge Editor for Lifelong Knowledge Editing","created":"2024-02-16","cited_by_count":40},{"id":"2101.00297","title":"Analyzing Commonsense Emergence in Few-shot Knowledge Models","created":"2021-01-01","cited_by_count":34},{"id":"2310.10322","title":"Evaluating the Reversal Curse in Model Editing","created":"2023-10-16","cited_by_count":34},{"id":"2306.02080","title":"Benchmarking Robustness of Adaptation Methods on Pre-trained Vision-Language Models","created":"2023-06-03","cited_by_count":31},{"id":"1906.02004","title":"Interpretable and Differentially Private Predictions","created":"2019-06-05","cited_by_count":28},{"id":"2308.09954","title":"DocTER: Evaluating Document-based Knowledge Editing","created":"2023-08-19","cited_by_count":26},{"id":"2312.15184","title":"ZO-AdaMU Optimizer: Adapting Perturbation by the Momentum and Uncertainty in Zeroth-order Optimization","created":"2023-12-23","cited_by_count":25},{"id":"2403.06408","title":"What Makes Quantization for Large Language Models Hard? An Empirical Study from the Lens of Perturbation","created":"2024-03-11","cited_by_count":23},{"id":"2403.06259","title":"Editing Conceptual Knowledge for Large Language Models","created":"2024-03-10","cited_by_count":21},{"id":"2401.17623","title":"Neighboring Perturbations of Knowledge Editing on Large Language Models","created":"2024-01-31","cited_by_count":10},{"id":"2402.11122","title":"Navigating the Dual Facets: A Comprehensive Evaluation of Sequential Memory Editing in Large Language Models","created":"2024-02-16","cited_by_count":10},{"id":"2404.00828","title":"PID Control-Based Self-Healing to Improve the Robustness of Large Language Models","created":"2024-03-31","cited_by_count":3}],"next_cursor":null}