{"list":"other","total":58,"rows":[{"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":"2101.00027","title":"The Pile: An 800GB Dataset of Diverse Text for Language Modeling","created":"2020-12-31","cited_by_count":2411},{"id":"1311.2901","title":"Visualizing and Understanding Convolutional Networks","created":"2013-11-12","cited_by_count":2290},{"id":"2012.07805","title":"Extracting Training Data from Large Language Models","created":"2020-12-14","cited_by_count":2189},{"id":"2212.04089","title":"Editing Models with Task Arithmetic","created":"2022-12-08","cited_by_count":1120},{"id":"2312.06681","title":"Steering Llama 2 via Contrastive Activation Addition","created":"2023-12-09","cited_by_count":1085},{"id":"1912.03817","title":"Machine Unlearning","created":"2019-12-09","cited_by_count":1061},{"id":"2210.07229","title":"Mass-Editing Memory in a Transformer","created":"2022-10-13","cited_by_count":1001},{"id":"2308.10248","title":"Steering Language Models With Activation Engineering","created":"2023-08-20","cited_by_count":922},{"id":"1802.08232","title":"The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks","created":"2018-02-22","cited_by_count":864},{"id":"2305.14233","title":"Enhancing Chat Language Models by Scaling High-quality Instructional Conversations","created":"2023-05-23","cited_by_count":839},{"id":"2202.07646","title":"Quantifying Memorization Across Neural Language Models","created":"2022-02-15","cited_by_count":763},{"id":"2107.06499","title":"Deduplicating Training Data Makes Language Models Better","created":"2021-07-14","cited_by_count":714},{"id":"2310.06824","title":"The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets","created":"2023-10-10","cited_by_count":712},{"id":"2404.05868","title":"Negative Preference Optimization: From Catastrophic Collapse to Effective Unlearning","created":"2024-04-08","cited_by_count":504},{"id":"2206.06520","title":"Memory-Based Model Editing at Scale","created":"2022-06-13","cited_by_count":447},{"id":"2210.01504","title":"Knowledge Unlearning for Mitigating Privacy Risks in Language Models","created":"2022-10-04","cited_by_count":437},{"id":"2010.10981","title":"Amnesiac Machine Learning","created":"2020-10-21","cited_by_count":319},{"id":"2209.02299","title":"A Survey of Machine Unlearning","created":"2022-09-06","cited_by_count":312},{"id":"2501.17148","title":"AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders","created":"2025-01-28","cited_by_count":218},{"id":"2111.08947","title":"Fast Yet Effective Machine Unlearning","created":"2021-11-17","cited_by_count":217},{"id":"2409.05907","title":"Programming Refusal with Conditional Activation Steering","created":"2024-09-06","cited_by_count":206},{"id":"1811.08737","title":"SpotTune: Transfer Learning through Adaptive Fine-tuning","created":"2018-11-21","cited_by_count":168},{"id":"2402.15159","title":"Machine Unlearning of Pre-trained Large Language Models","created":"2024-02-23","cited_by_count":119},{"id":"2410.23123","title":"On Memorization of Large Language Models in Logical Reasoning","created":"2024-10-30","cited_by_count":117},{"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":"2502.05628","title":"AnyEdit: Edit Any Knowledge Encoded in Language Models","created":"2025-02-08","cited_by_count":76},{"id":"2310.12560","title":"Fast Model Debias with Machine Unlearning","created":"2023-10-19","cited_by_count":72},{"id":"2505.24832","title":"How much do language models memorize?","created":"2025-05-30","cited_by_count":61},{"id":"2412.17686","title":"Large Language Model Safety: A Holistic Survey","created":"2024-12-23","cited_by_count":59},{"id":"2407.17817","title":"Demystifying Verbatim Memorization in Large Language Models","created":"2024-07-25","cited_by_count":56},{"id":"2311.17391","title":"Unveiling the Implicit Toxicity in Large Language Models","created":"2023-11-29","cited_by_count":51},{"id":"2506.07022","title":"AlphaSteer: Learning Refusal Steering with Principled Null-Space Constraint","created":"2025-06-08","cited_by_count":49},{"id":"2411.16721","title":"Steering Away from Harm: An Adaptive Approach to Defending Vision Language Model Against Jailbreaks","created":"2024-11-23","cited_by_count":48},{"id":"2402.11905","title":"Learning to Edit: Aligning LLMs with Knowledge Editing","created":"2024-02-19","cited_by_count":43},{"id":"2405.03097","title":"To Each (Textual Sequence) Its Own: Improving Memorized-Data Unlearning in Large Language Models","created":"2024-05-06","cited_by_count":43},{"id":"2505.16831","title":"Unlearning Isn't Deletion: Investigating Reversibility of Machine Unlearning in LLMs","created":"2025-05-22","cited_by_count":42},{"id":"2502.07218","title":"LLM Unlearning via Neural Activation Redirection","created":"2025-02-11","cited_by_count":41},{"id":"2402.10987","title":"WilKE: Wise-Layer Knowledge Editor for Lifelong Knowledge Editing","created":"2024-02-16","cited_by_count":40},{"id":"2402.05813","title":"Selective Forgetting: Advancing Machine Unlearning Techniques and Evaluation in Language Models","created":"2024-02-08","cited_by_count":39},{"id":"2504.09466","title":"AdaSteer: Your Aligned LLM is Inherently an Adaptive Jailbreak Defender","created":"2025-04-13","cited_by_count":38},{"id":"2410.04962","title":"Activation Scaling for Steering and Interpreting Language Models","created":"2024-10-07","cited_by_count":35},{"id":"2502.11051","title":"MMUnlearner: Reformulating Multimodal Machine Unlearning in the Era of Multimodal Large Language Models","created":"2025-02-16","cited_by_count":30},{"id":"2311.09060","title":"Do Localization Methods Actually Localize Memorized Data in LLMs? A Tale of Two Benchmarks","created":"2023-11-15","cited_by_count":29},{"id":"2412.07684","title":"The Pitfalls of Memorization: When Memorization Hurts Generalization","created":"2024-12-10","cited_by_count":19},{"id":"2410.02159","title":"Mitigating Memorization In Language Models","created":"2024-10-03","cited_by_count":12},{"id":"2507.05578","title":"The Landscape of Memorization in LLMs: Mechanisms, Measurement, and Mitigation","created":"2025-07-08","cited_by_count":10},{"id":"2405.11577","title":"A Multi-Perspective Analysis of Memorization in Large Language Models","created":"2024-05-19","cited_by_count":8},{"id":"2503.06040","title":"Mitigating Memorization in LLMs using Activation Steering","created":"2025-03-08","cited_by_count":8},{"id":"2505.20309","title":"Guiding Giants: Lightweight Controllers for Weighted Activation Steering in LLMs","created":"2025-05-22","cited_by_count":8},{"id":"2506.10024","title":"Private Memorization Editing: Turning Memorization into a Defense to Strengthen Data Privacy in Large Language Models","created":"2025-06-09","cited_by_count":7},{"id":"2502.19953","title":"GeoEdit: Geometric Knowledge Editing for Large Language Models","created":"2025-02-27","cited_by_count":6},{"id":"2408.04983","title":"Get Confused Cautiously: Textual Sequence Memorization Erasure with Selective Entropy Maximization","created":"2024-08-09","cited_by_count":4},{"id":"2502.15796","title":"Pruning as a Defense: Reducing Memorization in Large Language Models","created":"2025-02-18","cited_by_count":3},{"id":"2506.05198","title":"Quantifying Cross-Modality Memorization in Vision-Language Models","created":"2025-06-05","cited_by_count":3},{"id":"2509.00072","title":"Test of Time: Rethinking Temporal Signal of Benchmark Contamination","created":"2025-08-26","cited_by_count":3},{"id":"2511.20799","title":"Memories Retrieved from Many Paths: A Multi-Prefix Framework for Robust Detection of Training Data Leakage in Large Language Models","created":"2025-11-25","cited_by_count":2}],"next_cursor":null}