{"total":242,"rows":[{"id":"2310.01558","title":"Making Retrieval-Augmented Language Models Robust to Irrelevant Context","created":"2023-10-02","cited_by_count":369,"area":"rag"},{"id":"2402.08787","title":"Rethinking Machine Unlearning for Large Language Models","created":"2024-02-13","cited_by_count":257,"area":"lr"},{"id":"2502.14802","title":"From RAG to Memory: Non-Parametric Continual Learning for Large Language Models","created":"2025-02-20","cited_by_count":231,"area":"rag"},{"id":"2310.07521","title":"Survey on Factuality in Large Language Models: Knowledge, Retrieval and Domain-Specificity","created":"2023-10-11","cited_by_count":206,"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":"2308.08742","title":"PMET: Precise Model Editing in a Transformer","created":"2023-08-17","cited_by_count":173,"area":null},{"id":"2402.16837","title":"Do Large Language Models Latently Perform Multi-Hop Reasoning?","created":"2024-02-26","cited_by_count":169,"area":"lr"},{"id":"2401.01286","title":"A Comprehensive Study of Knowledge Editing for Large Language Models","created":"2024-01-02","cited_by_count":163,"area":null},{"id":"2407.02646","title":"A Practical Review of Mechanistic Interpretability for Transformer-Based Language Models","created":"2024-07-02","cited_by_count":118,"area":"mechinterp"},{"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,"area":null},{"id":"2308.07269","title":"EasyEdit: An Easy-to-use Knowledge Editing Framework for Large Language Models","created":"2023-08-14","cited_by_count":98,"area":null},{"id":"2401.07453","title":"Model Editing at Scale leads to Gradual and Catastrophic Forgetting","created":"2024-01-15","cited_by_count":93,"area":null},{"id":"2403.14472","title":"Detoxifying Large Language Models via Knowledge Editing","created":"2024-03-21","cited_by_count":87,"area":null},{"id":"2311.17030","title":"Is This the Subspace You Are Looking for? An Interpretability Illusion for Subspace Activation Patching","created":"2023-11-28","cited_by_count":80,"area":"mechinterp"},{"id":"2402.17700","title":"RAVEL: Evaluating Interpretability Methods on Disentangling Language Model Representations","created":"2024-02-27","cited_by_count":79,"area":"mechinterp"},{"id":"2406.12775","title":"Hopping Too Late: Exploring the Limitations of Large Language Models on Multi-Hop Queries","created":"2024-06-18","cited_by_count":78,"area":null},{"id":"2407.10827","title":"LLM Circuit Analyses Are Consistent Across Training and Scale","created":"2024-07-15","cited_by_count":63,"area":null},{"id":"2405.17969","title":"Knowledge Circuits in Pretrained Transformers","created":"2024-05-28","cited_by_count":60,"area":"mechinterp"},{"id":"2409.07431","title":"Synthetic continued pretraining","created":"2024-09-11","cited_by_count":60,"area":null},{"id":"2403.14236","title":"A Unified Framework for Model Editing","created":"2024-03-21","cited_by_count":57,"area":null},{"id":"2406.01563","title":"LoFiT: Localized Fine-tuning on LLM Representations","created":"2024-06-03","cited_by_count":57,"area":null},{"id":"2504.13151","title":"MIB: A Mechanistic Interpretability Benchmark","created":"2025-04-17","cited_by_count":56,"area":"mechinterp"},{"id":"2407.15017","title":"Knowledge Mechanisms in Large Language Models: A Survey and Perspective","created":"2024-07-22","cited_by_count":51,"area":null},{"id":"2403.07175","title":"Rebuilding ROME : Resolving Model Collapse during Sequential Model Editing","created":"2024-03-11","cited_by_count":50,"area":"synth"},{"id":"2412.15280","title":"Context-DPO: Aligning Language Models for Context-Faithfulness","created":"2024-12-18","cited_by_count":50,"area":"alignment"},{"id":"2502.14829","title":"Measuring Chain of Thought Faithfulness by Unlearning Reasoning Steps","created":"2025-02-20","cited_by_count":47,"area":"lr"},{"id":"2310.08475","title":"Can We Edit Multimodal Large Language Models?","created":"2023-10-12","cited_by_count":44,"area":"mllm"},{"id":"2402.11905","title":"Learning to Edit: Aligning LLMs with Knowledge Editing","created":"2024-02-19","cited_by_count":43,"area":null},{"id":"2501.08319","title":"Enhancing Automated Interpretability with Output-Centric Feature Descriptions","created":"2025-01-14","cited_by_count":41,"area":null},{"id":"2402.13593","title":"Knowledge Graph Enhanced Large Language Model Editing","created":"2024-02-21","cited_by_count":40,"area":null},{"id":"2405.03279","title":"Lifelong Knowledge Editing for LLMs with Retrieval-Augmented Continuous Prompt Learning","created":"2024-05-06","cited_by_count":40,"area":"rag"},{"id":"2406.12673","title":"Estimating Knowledge in Large Language Models Without Generating a Single Token","created":"2024-06-18","cited_by_count":40,"area":null},{"id":"2309.14534","title":"Teach AI How to Code: Using Large Language Models as Teachable Agents for Programming Education","created":"2023-09-25","cited_by_count":39,"area":"agents"},{"id":"2410.07819","title":"Uncovering Overfitting in Large Language Model Editing","created":"2024-10-10","cited_by_count":39,"area":null},{"id":"2402.18909","title":"AKEW: Assessing Knowledge Editing in the Wild","created":"2024-02-29","cited_by_count":36,"area":null},{"id":"2404.00492","title":"Multi-hop Question Answering under Temporal Knowledge Editing","created":"2024-03-30","cited_by_count":36,"area":null},{"id":"2405.11613","title":"Decoding by Contrasting Knowledge: Enhancing LLMs' Confidence on Edited Facts","created":"2024-05-19","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":"2310.07343","title":"How Do Large Language Models Capture the Ever-changing World Knowledge? A Review of Recent Advances","created":"2023-10-11","cited_by_count":33,"area":null},{"id":"2401.10471","title":"DeepEdit: Knowledge Editing as Decoding with Constraints","created":"2024-01-19","cited_by_count":33,"area":"lr"},{"id":"2403.07350","title":"VLKEB: A Large Vision-Language Model Knowledge Editing Benchmark","created":"2024-03-12","cited_by_count":30,"area":"mllm"},{"id":"2409.13724","title":"Logically Consistent Language Models via Neuro-Symbolic Integration","created":"2024-09-09","cited_by_count":30,"area":null},{"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,"area":null},{"id":"2406.11614","title":"Intrinsic Test of Unlearning Using Parametric Knowledge Traces","created":"2024-06-17","cited_by_count":29,"area":"safety"},{"id":"2311.05876","title":"Trends in Integration of Knowledge and Large Language Models: A Survey and Taxonomy of Methods, Benchmarks, and Applications","created":"2023-11-10","cited_by_count":28,"area":null},{"id":"2405.16821","title":"Perturbation-Restrained Sequential Model Editing","created":"2024-05-27","cited_by_count":28,"area":null},{"id":"2410.09223","title":"The Same But Different: Structural Similarities and Differences in Multilingual Language Modeling","created":"2024-10-11","cited_by_count":28,"area":"mechinterp"},{"id":"2410.16251","title":"Can Knowledge Editing Really Correct Hallucinations?","created":"2024-10-21","cited_by_count":28,"area":null},{"id":"2411.16679","title":"Do Large Language Models Perform Latent Multi-Hop Reasoning without Exploiting Shortcuts?","created":"2024-11-25","cited_by_count":28,"area":"lr"},{"id":"2310.11958","title":"Emptying the Ocean with a Spoon: Should We Edit Models?","created":"2023-10-18","cited_by_count":27,"area":null},{"id":"2412.06676","title":"I Don't Know: Explicit Modeling of Uncertainty with an [IDK] Token","created":"2024-12-09","cited_by_count":26,"area":null},{"id":"2404.08700","title":"DyKnow: Dynamically Verifying Time-Sensitive Factual Knowledge in LLMs","created":"2024-04-10","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":"2408.01416","title":"The Quest for the Right Mediator: Surveying Mechanistic Interpretability Through the Lens of Causal Mediation Analysis","created":"2024-08-02","cited_by_count":24,"area":"mechinterp"},{"id":"2312.15194","title":"PokeMQA: Programmable knowledge editing for Multi-hop Question Answering","created":"2023-12-23","cited_by_count":23,"area":"lr"},{"id":"2402.09394","title":"Long-form evaluation of model editing","created":"2024-02-14","cited_by_count":23,"area":null},{"id":"2402.11078","title":"Model Editing by Standard Fine-Tuning","created":"2024-02-16","cited_by_count":23,"area":null},{"id":"2504.18070","title":"PropRAG: Guiding Retrieval with Beam Search over Proposition Paths","created":"2025-04-25","cited_by_count":23,"area":"rag"},{"id":"2310.02168","title":"Editing Personality for Large Language Models","created":"2023-10-03","cited_by_count":22,"area":null},{"id":"2402.10688","title":"Towards Uncovering How Large Language Model Works: An Explainability Perspective","created":"2024-02-16","cited_by_count":22,"area":"lr"},{"id":"2407.20224","title":"Can Editing LLMs Inject Harm?","created":"2024-07-29","cited_by_count":22,"area":"safety"},{"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":"2403.06259","title":"Editing Conceptual Knowledge for Large Language Models","created":"2024-03-10","cited_by_count":21,"area":null},{"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,"area":null},{"id":"2403.19631","title":"Retrieval-enhanced Knowledge Editing in Language Models for Multi-Hop Question Answering","created":"2024-03-28","cited_by_count":20,"area":null},{"id":"2502.11812","title":"Towards Understanding Fine-Tuning Mechanisms of LLMs via Circuit Analysis","created":"2025-02-17","cited_by_count":20,"area":null},{"id":"2311.16087","title":"DUnE: Dataset for Unified Editing","created":"2023-11-27","cited_by_count":19,"area":null},{"id":"2404.11534","title":"Decomposing and Editing Predictions by Modeling Model Computation","created":"2024-04-17","cited_by_count":19,"area":null},{"id":"2407.06249","title":"CodeUpdateArena: Benchmarking Knowledge Editing on API Updates","created":"2024-07-08","cited_by_count":19,"area":null},{"id":"2410.17194","title":"Representation Shattering in Transformers: A Synthetic Study with Knowledge Editing","created":"2024-10-22","cited_by_count":19,"area":null},{"id":"2503.00306","title":"Unlocking Efficient, Scalable, and Continual Knowledge Editing with Basis-Level Representation Fine-Tuning","created":"2025-03-01","cited_by_count":19,"area":null},{"id":"2407.12828","title":"Why Does New Knowledge Create Messy Ripple Effects in LLMs?","created":"2024-07-02","cited_by_count":18,"area":null},{"id":"2409.13456","title":"Concept-Based Explanations in Computer Vision: Where Are We and Where Could We Go?","created":"2024-09-20","cited_by_count":18,"area":null},{"id":"2410.18785","title":"Should We Really Edit Language Models? On the Evaluation of Edited Language Models","created":"2024-10-24","cited_by_count":18,"area":null},{"id":"2312.05497","title":"History Matters: Temporal Knowledge Editing in Large Language Model","created":"2023-12-09","cited_by_count":17,"area":null},{"id":"2402.16123","title":"InstructEdit: Instruction-based Knowledge Editing for Large Language Models","created":"2024-02-25","cited_by_count":17,"area":null},{"id":"2502.01083","title":"Tool Unlearning for Tool-Augmented LLMs","created":"2025-02-03","cited_by_count":17,"area":"agents"},{"id":"2402.11324","title":"EVEDIT: Event-based Knowledge Editing with Deductive Editing Boundaries","created":"2024-02-17","cited_by_count":16,"area":null},{"id":"2312.01858","title":"Evaluating Dependencies in Fact Editing for Language Models: Specificity and Implication Awareness","created":"2023-12-04","cited_by_count":14,"area":null},{"id":"2406.04496","title":"Time Sensitive Knowledge Editing through Efficient Finetuning","created":"2024-06-06","cited_by_count":14,"area":null},{"id":"2406.12468","title":"Adaptive Token Biaser: Knowledge Editing via Biasing Key Entities","created":"2024-06-18","cited_by_count":14,"area":null},{"id":"2412.04614","title":"Extractive Structures Learned in Pretraining Enable Generalization on Finetuned Facts","created":"2024-12-05","cited_by_count":14,"area":null},{"id":"2502.20377","title":"PhantomWiki: On-Demand Datasets for Reasoning and Retrieval Evaluation","created":"2025-02-27","cited_by_count":14,"area":"lr"},{"id":"2402.13048","title":"Stable Knowledge Editing in Large Language Models","created":"2024-02-20","cited_by_count":13,"area":null},{"id":"2405.14117","title":"Knowledge Localization: Mission Not Accomplished? Enter Query Localization!","created":"2024-05-23","cited_by_count":13,"area":null},{"id":"2406.17764","title":"BMIKE-53: Investigating Cross-Lingual Knowledge Editing with In-Context Learning","created":"2024-06-25","cited_by_count":13,"area":null},{"id":"2503.01751","title":"SAKE: Steering Activations for Knowledge Editing","created":"2025-03-03","cited_by_count":13,"area":null},{"id":"2405.02714","title":"Beyond Relevance: Evaluate and Improve Retrievers on Perspective Awareness","created":"2024-05-04","cited_by_count":12,"area":null},{"id":"2406.01436","title":"Editing the Mind of Giants: An In-Depth Exploration of Pitfalls of Knowledge Editing in Large Language Models","created":"2024-06-03","cited_by_count":12,"area":null},{"id":"2502.18848","title":"A Causal Lens for Evaluating Faithfulness Metrics","created":"2025-02-26","cited_by_count":12,"area":null},{"id":"2309.08594","title":"\"Merge Conflicts!\" Exploring the Impacts of External Distractors to Parametric Knowledge Graphs","created":"2023-09-15","cited_by_count":11,"area":null},{"id":"2402.13463","title":"RefuteBench: Evaluating Refuting Instruction-Following for Large Language Models","created":"2024-02-21","cited_by_count":11,"area":null},{"id":"2404.00486","title":"Dialectical Alignment: Resolving the Tension of 3H and Security Threats of LLMs","created":"2024-03-30","cited_by_count":11,"area":"alignment"},{"id":"2404.04990","title":"MLaKE: Multilingual Knowledge Editing Benchmark for Large Language Models","created":"2024-04-07","cited_by_count":11,"area":null},{"id":"2410.22590","title":"Characterizing the Role of Similarity in the Property Inferences of Language Models","created":"2024-10-29","cited_by_count":11,"area":null},{"id":"2510.05141","title":"To model human linguistic prediction, make LLMs less superhuman","created":"2025-10-01","cited_by_count":11,"area":null},{"id":"2401.17623","title":"Neighboring Perturbations of Knowledge Editing on Large Language Models","created":"2024-01-31","cited_by_count":10,"area":null},{"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,"area":null},{"id":"2404.03036","title":"MuLan: A Study of Fact Mutability in Language Models","created":"2024-04-03","cited_by_count":10,"area":null},{"id":"2411.06638","title":"Model Editing for LLMs4Code: How Far are We?","created":"2024-11-11","cited_by_count":10,"area":null}],"next_cursor":"100"}