{"total":79,"rows":[{"id":"2202.05262","title":"Locating and Editing Factual Associations in GPT","created":"2022-02-10","cited_by_count":2691,"area":null},{"id":"2210.07229","title":"Mass-Editing Memory in a Transformer","created":"2022-10-13","cited_by_count":1001,"area":null},{"id":"2210.02414","title":"GLM-130B: An Open Bilingual Pre-trained Model","created":"2022-10-05","cited_by_count":843,"area":null},{"id":"2206.06520","title":"Memory-Based Model Editing at Scale","created":"2022-06-13","cited_by_count":447,"area":null},{"id":"2305.14795","title":"MQuAKE: Assessing Knowledge Editing in Language Models via Multi-Hop Questions","created":"2023-05-24","cited_by_count":300,"area":null},{"id":"2205.15480","title":"Post-hoc Concept Bottleneck Models","created":"2022-05-31","cited_by_count":293,"area":null},{"id":"2211.11031","title":"Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptors","created":"2022-11-20","cited_by_count":271,"area":null},{"id":"2402.08787","title":"Rethinking Machine Unlearning for Large Language Models","created":"2024-02-13","cited_by_count":257,"area":"lr"},{"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,"area":null},{"id":"2205.13636","title":"Quark: Controllable Text Generation with Reinforced Unlearning","created":"2022-05-26","cited_by_count":237,"area":"safety"},{"id":"2404.16789","title":"Continual Learning of Large Language Models: A Comprehensive Survey","created":"2024-04-25","cited_by_count":234,"area":null},{"id":"2307.14324","title":"Evaluating the Moral Beliefs Encoded in LLMs","created":"2023-07-26","cited_by_count":215,"area":null},{"id":"2310.16218","title":"Knowledge Editing for Large Language Models: A Survey","created":"2023-10-24","cited_by_count":194,"area":"lr"},{"id":"2309.17410","title":"Can Sensitive Information Be Deleted From LLMs? Objectives for Defending Against Extraction Attacks","created":"2023-09-29","cited_by_count":158,"area":null},{"id":"2204.06031","title":"A Review on Language Models as Knowledge Bases","created":"2022-04-12","cited_by_count":157,"area":null},{"id":"2304.00740","title":"Inspecting and Editing Knowledge Representations in Language Models","created":"2023-04-03","cited_by_count":141,"area":null},{"id":"2212.01681","title":"Language Models as Agent Models","created":"2022-12-03","cited_by_count":132,"area":"agents"},{"id":"2306.12672","title":"From Word Models to World Models: Translating from Natural Language to the Probabilistic Language of Thought","created":"2023-06-22","cited_by_count":119,"area":"wm"},{"id":"2208.02957","title":"Meaning without reference in large language models","created":"2022-08-05","cited_by_count":76,"area":null},{"id":"2407.02996","title":"Are Large Language Models Consistent over Value-laden Questions?","created":"2024-07-03","cited_by_count":58,"area":null},{"id":"2305.09955","title":"Knowledge Card: Filling LLMs' Knowledge Gaps with Plug-in Specialized Language Models","created":"2023-05-17","cited_by_count":46,"area":null},{"id":"2302.13406","title":"GNNDelete: A General Strategy for Unlearning in Graph Neural Networks","created":"2023-02-26","cited_by_count":43,"area":null},{"id":"2305.15076","title":"Meta-Learning Online Adaptation of Language Models","created":"2023-05-24","cited_by_count":43,"area":null},{"id":"2402.10426","title":"DELL: Generating Reactions and Explanations for LLM-Based Misinformation Detection","created":"2024-02-16","cited_by_count":41,"area":null},{"id":"2204.13074","title":"Towards Teachable Reasoning Systems: Using a Dynamic Memory of User Feedback for Continual System Improvement","created":"2022-04-27","cited_by_count":37,"area":"lr"},{"id":"2404.00492","title":"Multi-hop Question Answering under Temporal Knowledge Editing","created":"2024-03-30","cited_by_count":36,"area":null},{"id":"2406.11194","title":"In-Context Editing: Learning Knowledge from Self-Induced Distributions","created":"2024-06-17","cited_by_count":34,"area":null},{"id":"2401.10471","title":"DeepEdit: Knowledge Editing as Decoding with Constraints","created":"2024-01-19","cited_by_count":33,"area":"lr"},{"id":"2205.12677","title":"Language Anisotropic Cross-Lingual Model Editing","created":"2022-05-25","cited_by_count":26,"area":null},{"id":"2401.17585","title":"Propagation and Pitfalls: Reasoning-based Assessment of Knowledge Editing through Counterfactual Tasks","created":"2024-01-31","cited_by_count":24,"area":null},{"id":"2406.19354","title":"Fundamental Problems With Model Editing: How Should Rational Belief Revision Work in LLMs?","created":"2024-06-27","cited_by_count":24,"area":null},{"id":"2211.03154","title":"On the Domain Adaptation and Generalization of Pretrained Language Models: A Survey","created":"2022-11-06","cited_by_count":23,"area":null},{"id":"2303.07616","title":"The Life Cycle of Knowledge in Big Language Models: A Survey","created":"2023-03-14","cited_by_count":23,"area":null},{"id":"2402.09394","title":"Long-form evaluation of model editing","created":"2024-02-14","cited_by_count":23,"area":null},{"id":"2309.05605","title":"Memory Injections: Correcting Multi-Hop Reasoning Failures during Inference in Transformer-Based Language Models","created":"2023-09-11","cited_by_count":21,"area":"lr"},{"id":"2206.14268","title":"BertNet: Harvesting Knowledge Graphs with Arbitrary Relations from Pretrained Language Models","created":"2022-06-28","cited_by_count":20,"area":null},{"id":"2209.15093","title":"Unpacking Large Language Models with Conceptual Consistency","created":"2022-09-29","cited_by_count":18,"area":null},{"id":"2305.03742","title":"Improved Logical Reasoning of Language Models via Differentiable Symbolic Programming","created":"2023-05-05","cited_by_count":18,"area":"lr"},{"id":"2305.06349","title":"RECKONING: Reasoning through Dynamic Knowledge Encoding","created":"2023-05-10","cited_by_count":18,"area":"lr"},{"id":"2312.05497","title":"History Matters: Temporal Knowledge Editing in Large Language Model","created":"2023-12-09","cited_by_count":17,"area":null},{"id":"2405.09341","title":"Large Language Model Bias Mitigation from the Perspective of Knowledge Editing","created":"2024-05-15","cited_by_count":16,"area":null},{"id":"2305.14250","title":"Language Models with Rationality","created":"2023-05-23","cited_by_count":15,"area":null},{"id":"2408.07728","title":"Moderator: Moderating Text-to-Image Diffusion Models through Fine-grained Context-based Policies","created":"2024-08-14","cited_by_count":15,"area":"diffusion"},{"id":"2408.11843","title":"Identifying and Mitigating Social Bias Knowledge in Language Models","created":"2024-08-07","cited_by_count":13,"area":null},{"id":"2405.15452","title":"Leveraging Logical Rules in Knowledge Editing: A Cherry on the Top","created":"2024-05-24","cited_by_count":12,"area":null},{"id":"2502.15826","title":"CoME: An Unlearning-based Approach to Conflict-free Model Editing","created":"2025-02-20","cited_by_count":12,"area":"safety"},{"id":"2305.18582","title":"Information Association for Language Model Updating by Mitigating LM-Logical Discrepancy","created":"2023-05-29","cited_by_count":10,"area":null},{"id":"2406.03442","title":"Are language models rational? The case of coherence norms and belief revision","created":"2024-06-05","cited_by_count":10,"area":null},{"id":"2408.10210","title":"A Survey on Symbolic Knowledge Distillation of Large Language Models","created":"2024-07-12","cited_by_count":9,"area":"distill"},{"id":"2112.08583","title":"Does Pre-training Induce Systematic Inference? How Masked Language Models Acquire Commonsense Knowledge","created":"2021-12-16","cited_by_count":8,"area":null},{"id":"2303.00046","title":"Edit at your own risk: evaluating the robustness of edited models to distribution shifts","created":"2023-02-28","cited_by_count":8,"area":null},{"id":"2507.17216","title":"The Pluralistic Moral Gap: Understanding Judgment and Value Differences between Humans and Large Language Models","created":"2025-07-23","cited_by_count":7,"area":null},{"id":"2601.15495","title":"Tracking the Limits of Knowledge Propagation: How LLMs Fail at Multi-Step Reasoning with Conflicting Knowledge","created":"2026-01-21","cited_by_count":7,"area":"lr"},{"id":"2403.07825","title":"Efficiently Quantifying and Mitigating Ripple Effects in Model Editing","created":"2024-03-12","cited_by_count":6,"area":null},{"id":"2503.12545","title":"PEBench: A Fictitious Dataset to Benchmark Machine Unlearning for Multimodal Large Language Models","created":"2025-03-16","cited_by_count":6,"area":"mllm"},{"id":"2504.12187","title":"What Do Large Language Models Know? Tacit Knowledge as a Potential Causal-Explanatory Structure","created":"2025-04-16","cited_by_count":6,"area":null},{"id":"2512.02914","title":"Martingale Score: An Unsupervised Metric for Bayesian Rationality in LLM Reasoning","created":"2025-12-02","cited_by_count":5,"area":"lr"},{"id":"2212.10557","title":"DialGuide: Aligning Dialogue Model Behavior with Developer Guidelines","created":"2022-12-20","cited_by_count":4,"area":null},{"id":"2403.00180","title":"\"Flex Tape Can't Fix That\": Bias and Misinformation in Edited Language Models","created":"2024-02-29","cited_by_count":4,"area":null},{"id":"2507.11128","title":"What Should LLMs Forget? Quantifying Personal Data in LLMs for Right-to-Be-Forgotten Requests","created":"2025-07-15","cited_by_count":4,"area":"safety"},{"id":"2510.13912","title":"AI Debaters are More Persuasive when Arguing in Alignment with Their Own Beliefs","created":"2025-10-15","cited_by_count":4,"area":null},{"id":"2305.15529","title":"Editable Graph Neural Network for Node Classifications","created":"2023-05-24","cited_by_count":3,"area":null},{"id":"2307.11031","title":"Embroid: Unsupervised Prediction Smoothing Can Improve Few-Shot Classification","created":"2023-07-20","cited_by_count":3,"area":null},{"id":"2506.20746","title":"Dynamic Weight Grafting: Localizing Finetuned Factual Knowledge in Transformers","created":"2025-06-25","cited_by_count":3,"area":null},{"id":"2201.06009","title":"Memory-assisted prompt editing to improve GPT-3 after deployment","created":"2022-01-16","cited_by_count":2,"area":null},{"id":"2311.10614","title":"A Self-enhancement Approach for Domain-specific Chatbot Training via Knowledge Mining and Digest","created":"2023-11-17","cited_by_count":2,"area":null},{"id":"2407.08689","title":"Operationalizing the Blueprint for an AI Bill of Rights: Recommendations for Practitioners, Researchers, and Policy Makers","created":"2024-07-11","cited_by_count":2,"area":null},{"id":"2408.11855","title":"FactorLLM: Factorizing Knowledge via Mixture of Experts for Large Language Models","created":"2024-08-15","cited_by_count":2,"area":"moe"},{"id":"2504.20980","title":"Jekyll-and-Hyde Tipping Point in an AI's Behavior","created":"2025-04-29","cited_by_count":2,"area":null},{"id":"2607.10645","title":"MafiaScope: Non-Invasive, Time-Resolved Belief Probing for LLM Agents in Social Deduction Games","created":"2026-07-12","cited_by_count":2,"area":"agents"},{"id":"2406.04553","title":"Better Late Than Never: Formulating and Benchmarking Recommendation Editing","created":"2024-06-06","cited_by_count":1,"area":null},{"id":"2406.13660","title":"Towards Minimal Targeted Updates of Language Models with Targeted Negative Training","created":"2024-06-19","cited_by_count":1,"area":null},{"id":"2307.07507","title":"MGit: A Model Versioning and Management System","created":"2023-07-14","cited_by_count":0,"area":null},{"id":"2402.17389","title":"FairBelief -- Assessing Harmful Beliefs in Language Models","created":"2024-02-27","cited_by_count":0,"area":null},{"id":"2406.10974","title":"Towards Supporting Legal Argumentation with NLP: Is More Data Really All You Need?","created":"2024-06-16","cited_by_count":0,"area":null},{"id":"2406.15940","title":"Beyond Individual Facts: Investigating Categorical Knowledge Locality of Taxonomy and Meronomy Concepts in GPT Models","created":"2024-06-22","cited_by_count":0,"area":null},{"id":"2410.04272","title":"Evaluating Language Model Character Traits","created":"2024-10-05","cited_by_count":0,"area":null},{"id":"2608.25152","title":"Belief Cascades Drive Persuasion in LLM Agent Networks","created":"2026-08-25","cited_by_count":0,"area":"agents"},{"id":"2608.29431","title":"Evaluating the Semantic Specificity of Representation Steering in Language Models","created":"2026-08-29","cited_by_count":0,"area":"lr"}],"next_cursor":null}