{"total":82,"rows":[{"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,"area":null},{"id":"2305.13172","title":"Editing Large Language Models: Problems, Methods, and Opportunities","created":"2023-05-22","cited_by_count":372,"area":null},{"id":"2307.12976","title":"Evaluating the Ripple Effects of Knowledge Editing in Language Models","created":"2023-07-24","cited_by_count":242,"area":null},{"id":"2308.09124","title":"Linearity of Relation Decoding in Transformer Language Models","created":"2023-08-17","cited_by_count":200,"area":null},{"id":"2308.08742","title":"PMET: Precise Model Editing in a Transformer","created":"2023-08-17","cited_by_count":173,"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":"2402.17811","title":"TruthX: Alleviating Hallucinations by Editing Large Language Models in Truthful Space","created":"2024-02-27","cited_by_count":91,"area":null},{"id":"2403.10949","title":"SelfIE: Self-Interpretation of Large Language Model Embeddings","created":"2024-03-16","cited_by_count":67,"area":null},{"id":"2409.20089","title":"Robust LLM safeguarding via refusal feature adversarial training","created":"2024-09-30","cited_by_count":64,"area":null},{"id":"2412.08686","title":"LatentQA: Teaching LLMs to Decode Activations Into Natural Language","created":"2024-12-11","cited_by_count":51,"area":null},{"id":"2401.12874","title":"From Understanding to Utilization: A Survey on Explainability for Large Language Models","created":"2024-01-23","cited_by_count":48,"area":null},{"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":"2410.04962","title":"Activation Scaling for Steering and Interpreting Language Models","created":"2024-10-07","cited_by_count":35,"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":"2310.06827","title":"Teaching Language Models to Hallucinate Less with Synthetic Tasks","created":"2023-10-10","cited_by_count":31,"area":null},{"id":"2406.01394","title":"PrivacyRestore: Privacy-Preserving Inference in Large Language Models via Privacy Removal and Restoration","created":"2024-06-03","cited_by_count":28,"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":"2404.09554","title":"Explainable Generative AI (GenXAI): A Survey, Conceptualization, and Research Agenda","created":"2024-04-15","cited_by_count":22,"area":null},{"id":"2409.02877","title":"Configurable Foundation Models: Building LLMs from a Modular Perspective","created":"2024-09-04","cited_by_count":22,"area":null},{"id":"2602.08169","title":"Spherical Steering: Geometry-Aware Activation Rotation for Language Models","created":"2026-02-09","cited_by_count":21,"area":null},{"id":"2405.15454","title":"LiSeCo: Linear Semantic Control for Language Generation","created":"2024-05-24","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":"2407.06249","title":"CodeUpdateArena: Benchmarking Knowledge Editing on API Updates","created":"2024-07-08","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":"2310.03084","title":"Discovering Knowledge-Critical Subnetworks in Pretrained Language Models","created":"2023-10-04","cited_by_count":16,"area":null},{"id":"2403.09053","title":"Towards a theory of model distillation","created":"2024-03-14","cited_by_count":15,"area":null},{"id":"2403.10381","title":"Monotonic Representation of Numeric Properties in Language Models","created":"2024-03-15","cited_by_count":15,"area":null},{"id":"2404.08417","title":"AdapterSwap: Continuous Training of LLMs with Data Removal and Access-Control Guarantees","created":"2024-04-12","cited_by_count":14,"area":null},{"id":"2405.02765","title":"Has this Fact been Edited? Detecting Knowledge Edits in Language Models","created":"2024-05-04","cited_by_count":14,"area":null},{"id":"2401.02575","title":"Large Language Models for Social Networks: Applications, Challenges, and Solutions","created":"2024-01-04","cited_by_count":11,"area":null},{"id":"2406.01352","title":"Position: An Inner Interpretability Framework for AI Inspired by Lessons from Cognitive Neuroscience","created":"2024-06-03","cited_by_count":11,"area":null},{"id":"2410.02899","title":"FactCheckmate: Preemptively Detecting and Mitigating Hallucinations in LMs","created":"2024-10-03","cited_by_count":11,"area":null},{"id":"2502.02173","title":"Mass-Editing Memory with Attention in Transformers: A cross-lingual exploration of knowledge","created":"2025-02-04","cited_by_count":10,"area":null},{"id":"2508.17670","title":"CoCoA: Confidence and Context-Aware Adaptive Decoding for Resolving Knowledge Conflicts in Large Language Models","created":"2025-08-25","cited_by_count":10,"area":null},{"id":"2409.06328","title":"Extracting Paragraphs from LLM Token Activations","created":"2024-09-10","cited_by_count":9,"area":null},{"id":"2404.05783","title":"A Survey on Responsible Generative AI: What to Generate and What Not","created":"2024-04-08","cited_by_count":8,"area":null},{"id":"2406.17513","title":"Brittle Minds, Fixable Activations: Understanding Belief Representations in Language Models","created":"2024-06-25","cited_by_count":8,"area":null},{"id":"2507.23220","title":"Model Directions, Not Words: Mechanistic Topic Models Using Sparse Autoencoders","created":"2025-07-31","cited_by_count":8,"area":null},{"id":"2602.00333","title":"Efficient and accurate steering of Large Language Models through attention-guided feature learning","created":"2026-01-30","cited_by_count":8,"area":null},{"id":"2603.01281","title":"Spectral Attention Steering for Prompt Highlighting","created":"2026-03-01","cited_by_count":8,"area":null},{"id":"2407.12543","title":"Abstraction Alignment: Comparing Model-Learned and Human-Encoded Conceptual Relationships","created":"2024-07-17","cited_by_count":7,"area":null},{"id":"2509.14814","title":"ReCoVeR the Target Language: Language Steering without Sacrificing Task Performance","created":"2025-09-18","cited_by_count":6,"area":null},{"id":"2602.10161","title":"Omni-Safety under Cross-Modality Conflict: Vulnerabilities, Dynamics Mechanisms and Efficient Alignment","created":"2026-02-10","cited_by_count":6,"area":null},{"id":"2605.23932","title":"When Correct Beliefs Collapse: Epistemic Resilience of LLMs under Clinical Pressure","created":"2026-04-23","cited_by_count":6,"area":null},{"id":"2508.19720","title":"Continuously Steering LLMs Sensitivity to Contextual Knowledge with Proxy Models","created":"2025-08-27","cited_by_count":5,"area":null},{"id":"2310.09725","title":"KGQuiz: Evaluating the Generalization of Encoded Knowledge in Large Language Models","created":"2023-10-15","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":"2505.14158","title":"Temporal Alignment of Time Sensitive Facts with Activation Engineering","created":"2025-05-20","cited_by_count":4,"area":null},{"id":"2402.06155","title":"Model Editing with Canonical Examples","created":"2024-02-09","cited_by_count":3,"area":null},{"id":"2406.13184","title":"Locating and Extracting Relational Concepts in Large Language Models","created":"2024-06-19","cited_by_count":3,"area":null},{"id":"2504.10421","title":"Can We Edit LLMs for Long-Tail Biomedical Knowledge?","created":"2025-04-14","cited_by_count":3,"area":null},{"id":"2504.16871","title":"Exploring How LLMs Capture and Represent Domain-Specific Knowledge","created":"2025-04-23","cited_by_count":3,"area":null},{"id":"2505.18933","title":"REACT: Representation Extraction And Controllable Tuning to Overcome Overfitting in LLM Knowledge Editing","created":"2025-05-25","cited_by_count":3,"area":null},{"id":"2510.07896","title":"ACE: Attribution-Controlled Knowledge Editing for Multi-hop Factual Recall","created":"2025-10-09","cited_by_count":3,"area":null},{"id":"2603.10705","title":"PRISM-$\\Delta$: Differential Subspace Steering for Prompt Highlighting in Large Language Models","created":"2026-03-11","cited_by_count":2,"area":null},{"id":"2502.06115","title":"Task-driven Layerwise Additive Activation Intervention","created":"2025-02-10","cited_by_count":1,"area":null},{"id":"2502.18644","title":"Steered Generation via Gradient Descent on Sparse Features","created":"2025-02-25","cited_by_count":1,"area":null},{"id":"2502.19416","title":"Norm Growth and Stability Challenges in Localized Sequential Knowledge Editing","created":"2025-02-26","cited_by_count":1,"area":null},{"id":"2505.23291","title":"ScEdit: Script-based Assessment of Knowledge Editing","created":"2025-05-29","cited_by_count":1,"area":null},{"id":"2510.17001","title":"Vocab Diet: Reshaping the Vocabulary of LLMs via Vector Arithmetic","created":"2025-10-19","cited_by_count":1,"area":null},{"id":"2510.26543","title":"The Structure of Relation Decoding Linear Operators in Large Language Models","created":"2025-10-30","cited_by_count":1,"area":null},{"id":"2511.20233","title":"REFLEX: Self-Refining Explainable Fact-Checking via Verdict-Anchored Style Control","created":"2025-11-25","cited_by_count":1,"area":null},{"id":"2604.23837","title":"One Size Fits None: Heuristic Collapse in LLM Investment Advice","created":"2026-04-26","cited_by_count":1,"area":null},{"id":"2607.13047","title":"Targeted Recovery of Weight-Space Mechanisms From Neural Networks","created":"2026-06-19","cited_by_count":1,"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":"2411.18645","title":"Bi-ICE: An Inner Interpretable Framework for Image Classification via Bi-directional Interactions between Concept and Input Embeddings","created":"2024-11-26","cited_by_count":0,"area":null},{"id":"2412.15698","title":"Concept Boundary Vectors","created":"2024-12-20","cited_by_count":0,"area":null},{"id":"2505.24292","title":"Mind the Quote: Enabling Quotation-Aware Dialogue in LLMs via Plug-and-Play Modules","created":"2025-05-30","cited_by_count":0,"area":null},{"id":"2508.01892","title":"How Does Controllability Emerge In Language Models During Pretraining?","created":"2025-08-03","cited_by_count":0,"area":null},{"id":"2508.03741","title":"Latent Knowledge Scalpel: Precise and Massive Knowledge Editing for Large Language Models","created":"2025-08-01","cited_by_count":0,"area":null},{"id":"2508.14025","title":"Ask Good Questions for Large Language Models","created":"2025-08-19","cited_by_count":0,"area":null},{"id":"2511.18359","title":"TRANSPORTER: Transferring Visual Semantics from VLM Manifolds","created":"2025-11-23","cited_by_count":0,"area":null},{"id":"2601.04600","title":"On the Limitations of Rank-One Model Editing in Answering Multi-hop Questions","created":"2026-01-08","cited_by_count":0,"area":null},{"id":"2603.27338","title":"CounterMoral: Editing Morals in Language Models","created":"2026-03-28","cited_by_count":0,"area":null},{"id":"2604.17698","title":"The Geometric Canary: Predicting Steerability and Detecting Drift via Representational Stability","created":"2026-04-20","cited_by_count":0,"area":null},{"id":"2605.22532","title":"Relational Linear Properties in Language Models: An Empirical Investigation","created":"2026-05-21","cited_by_count":0,"area":null},{"id":"2606.00570","title":"Revisiting Parameter-Based Knowledge Editing in Large Language Models: Theoretical Limits and Empirical Evidence","created":"2026-05-30","cited_by_count":0,"area":null},{"id":"2606.07555","title":"Persistent Priors, Preserved Targets: A Stroop-Style Paradigm for Lexical Override","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2606.12160","title":"A Controlled Study of Decoding-Time Truthfulness Methods on Instruction-Tuned LLMs","created":"2026-06-10","cited_by_count":0,"area":null},{"id":"2606.22627","title":"Orthogonal Representation Editing: Decoupling Semantic Entanglement in Batch Knowledge Editing of LLMs","created":"2026-06-21","cited_by_count":0,"area":null},{"id":"2608.08284","title":"Fair on the Surface? Benchmarking Hidden-Output Fairness Gaps in LLM Recommenders","created":"2026-08-08","cited_by_count":0,"area":null},{"id":"2609.32449","title":"Self-Reports Do Not Identify Self-Models: An Identifiability Test for Counterfactual Reports","created":"2026-09-26","cited_by_count":0,"area":null}],"next_cursor":null}