{"total":67,"rows":[{"id":"2407.17817","title":"Demystifying Verbatim Memorization in Large Language Models","created":"2024-07-25","cited_by_count":56,"area":null},{"id":"2404.10859","title":"Forcing Diffuse Distributions out of Language Models","created":"2024-04-16","cited_by_count":48,"area":null},{"id":"2406.18664","title":"Evaluating Copyright Takedown Methods for Language Models","created":"2024-06-26","cited_by_count":43,"area":null},{"id":"2504.16980","title":"Safety Pretraining: Toward the Next Generation of Safe AI","created":"2025-04-23","cited_by_count":43,"area":null},{"id":"2404.15500","title":"GeoLLM-Engine: A Realistic Environment for Building Geospatial Copilots","created":"2024-04-23","cited_by_count":30,"area":null},{"id":"2410.18966","title":"Does Data Contamination Detection Work (Well) for LLMs? A Survey and Evaluation on Detection Assumptions","created":"2024-10-24","cited_by_count":26,"area":null},{"id":"2506.19004","title":"Broken Tokens? Your Language Model can Secretly Handle Non-Canonical Tokenizations","created":"2025-06-23","cited_by_count":17,"area":null},{"id":"2601.21571","title":"Shaping capabilities with token-level data filtering","created":"2026-01-29","cited_by_count":13,"area":null},{"id":"2505.15962","title":"Pre-training Limited Memory Language Models with Internal and External Knowledge","created":"2025-05-21","cited_by_count":12,"area":null},{"id":"2408.04140","title":"UNLEARN Efficient Removal of Knowledge in Large Language Models","created":"2024-08-08","cited_by_count":10,"area":null},{"id":"2406.16135","title":"Crosslingual Capabilities and Knowledge Barriers in Multilingual Large Language Models","created":"2024-06-23","cited_by_count":9,"area":null},{"id":"2502.11910","title":"Adversarial Alignment for LLMs Requires Simpler, Reproducible, and More Measurable Objectives","created":"2025-02-17","cited_by_count":8,"area":null},{"id":"2502.13593","title":"Toward Robust Non-Transferable Learning: A Survey and Benchmark","created":"2025-02-19","cited_by_count":7,"area":null},{"id":"2408.04983","title":"Get Confused Cautiously: Textual Sequence Memorization Erasure with Selective Entropy Maximization","created":"2024-08-09","cited_by_count":4,"area":null},{"id":"2508.04329","title":"Forgetting: A New Mechanism Towards Better Large Language Model Fine-tuning","created":"2025-08-06","cited_by_count":4,"area":null},{"id":"2601.22313","title":"Hair-Trigger Alignment: Black-Box Evaluation Cannot Guarantee Post-Update Alignment","created":"2026-01-29","cited_by_count":4,"area":null},{"id":"2605.12705","title":"Early Data Exposure Improves Robustness to Subsequent Fine-Tuning","created":"2026-05-12","cited_by_count":4,"area":null},{"id":"2503.12314","title":"Empirical Privacy Variance","created":"2025-03-16","cited_by_count":3,"area":null},{"id":"2506.14387","title":"SEAT: Sparse Entity-Aware Tuning for Knowledge Adaptation while Preserving Epistemic Abstention","created":"2025-06-17","cited_by_count":3,"area":null},{"id":"2607.27539","title":"Can an AI Assistant Really Forget? Auditable Deletion from Addressable Memory","created":"2026-07-30","cited_by_count":3,"area":null},{"id":"2410.17599","title":"Cross-model Control: Improving Multiple Large Language Models in One-time Training","created":"2024-10-23","cited_by_count":2,"area":null},{"id":"2412.00789","title":"A Cognac Shot To Forget Bad Memories: Corrective Unlearning for Graph Neural Networks","created":"2024-12-01","cited_by_count":2,"area":null},{"id":"2505.03052","title":"Teaching Models to Understand (but not Generate) High-risk Data","created":"2025-05-05","cited_by_count":2,"area":null},{"id":"2511.14774","title":"LiveCLKTBench: Towards Reliable Evaluation of Cross-Lingual Knowledge Transfer in Multilingual LLMs","created":"2025-11-03","cited_by_count":2,"area":null},{"id":"2605.24564","title":"Summoning the Oracle to Slay It: Mitigating Look-Ahead Bias in Financial Backtesting with Large Language Models","created":"2026-05-23","cited_by_count":2,"area":null},{"id":"2606.02293","title":"AI as a Tool for Simulation-Based Experiments in Literary Studies","created":"2026-06-01","cited_by_count":2,"area":null},{"id":"2606.06667","title":"The Piggyback Hypothesis of Generalization: Explaining and Mitigating Emergent Misalignment","created":"2026-06-04","cited_by_count":2,"area":null},{"id":"2504.05059","title":"MIAT: Maneuver-Intention-Aware Transformer for Spatio-Temporal Trajectory Prediction","created":"2025-04-07","cited_by_count":1,"area":null},{"id":"2504.16046","title":"Certified Mitigation of Worst-Case LLM Copyright Infringement","created":"2025-04-22","cited_by_count":1,"area":null},{"id":"2506.19140","title":"Command-V: Pasting LLM Behaviors via Activation Profiles","created":"2025-06-23","cited_by_count":1,"area":null},{"id":"2508.10065","title":"Invisible Watermarks, Visible Gains: Steering Machine Unlearning with Bi-Level Watermarking Design","created":"2025-08-13","cited_by_count":1,"area":null},{"id":"2512.15235","title":"FAME: Fictional Actors for Multilingual Erasure","created":"2025-12-17","cited_by_count":1,"area":null},{"id":"2601.11575","title":"Concept Attractors in LLMs and their Applications","created":"2025-12-30","cited_by_count":1,"area":null},{"id":"2605.20005","title":"Fine-Tuning Without Forgetting via Loss-Adaptive Learning Rates","created":"2026-05-19","cited_by_count":1,"area":null},{"id":"2607.24805","title":"Forgetting Is Not a Fix: Path Dependence in Sequential Engram Editing","created":"2026-07-06","cited_by_count":1,"area":null},{"id":"2608.28691","title":"Defending Wearable VLMs Against Private Attribute Inference","created":"2026-08-26","cited_by_count":1,"area":null},{"id":"2412.10257","title":"Targeted Angular Reversal of Weights (TARS) for Knowledge Removal in Large Language Models","created":"2024-12-13","cited_by_count":0,"area":null},{"id":"2505.05064","title":"WaterDrum: Watermarking for Data-centric Unlearning Metric","created":"2025-05-08","cited_by_count":0,"area":null},{"id":"2506.05639","title":"FictionalQA: A Dataset for Studying Memorization and Knowledge Acquisition","created":"2025-06-05","cited_by_count":0,"area":null},{"id":"2509.07909","title":"Uncovering Scaling Laws for Large Language Models via Inverse Problems","created":"2025-09-09","cited_by_count":0,"area":null},{"id":"2602.23286","title":"SPARTA: Scalable and Principled Benchmark of Tree-Structured Multi-hop QA over Text and Tables","created":"2026-02-26","cited_by_count":0,"area":null},{"id":"2603.14672","title":"Seamless Deception: Larger Language Models Are Better Knowledge Concealers","created":"2026-03-15","cited_by_count":0,"area":null},{"id":"2603.17884","title":"DebugLM: Learning Traceable Training Data Provenance for LLMs","created":"2026-03-18","cited_by_count":0,"area":null},{"id":"2604.00324","title":"The Persistent Vulnerability of Aligned AI Systems","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2606.01849","title":"ContinuousBench: Can Differentially Private Synthetic Text Improve Capabilities?","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2606.05029","title":"Validity Threats for Foundation Model Research","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2606.14997","title":"AI Engram: In Search of Memory Traces in Artificial Intelligence","created":"2026-06-12","cited_by_count":0,"area":null},{"id":"2606.15088","title":"When the Same Musical Knowledge Forgets Differently: A Clean Probe of Pathway-Dependent Forgetting","created":"2026-06-13","cited_by_count":0,"area":null},{"id":"2606.26807","title":"KARLA: Knowledge-base Augmented Retrieval for Language Models","created":"2026-06-25","cited_by_count":0,"area":null},{"id":"2606.30788","title":"Revocable Learned State via Process Sidecars","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2606.31168","title":"Probe Choice Changes Canary-Memorization Verdicts: Three Post-Hoc Disagreement Case Studies in a Text-Dominant LoRA-Tuned Autoregressive Testbed","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2606.31250","title":"Probing Stylistic Appropriation using Large Language Models: An Evaluation Framework for Copyright Infringement under EU Law","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2607.07707","title":"Co-LMLM: Continuous-Query Limited Memory Language Models","created":"2026-07-08","cited_by_count":0,"area":null},{"id":"2607.10803","title":"Weight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs","created":"2026-07-12","cited_by_count":0,"area":null},{"id":"2609.06872","title":"Exact Record Omission in Delta Attention: A Transport Criterion, Its Cost, and a Replay Certificate","created":"2026-09-06","cited_by_count":0,"area":null},{"id":"2609.08418","title":"Feyospace-v1: How the Cyber Mercury Seven Trained Frontier Cyber Models","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.22153","title":"SafeTune: A Unified Faithful Library for Auditing and Repairing Safety Drift in Fine-Tuned LLMs","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2609.27115","title":"Damnatio Memoriae: Adversarially and Selectively Forgetting Identities in the Embedding Space of Face Recognition Models","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2609.27593","title":"Hidden not Deleted: How Networks Suppress Entangled Features","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2609.30094","title":"PrivDrift: Auditing User-Secret Leakage Under Topic Drift in Active LLM Conversations","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2609.36310","title":"Learning Samples Importance: Parameterizing Dual Variables in Everywhere Learning","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.36414","title":"Eternal Sunshine of the Spotless Mind: Systematically Erasing LLM's Memories","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.02886","title":"Misinformation Without Triggers: From Factual Answers to Downstream Decisions","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.14089","title":"SAGE: Efficient Protected Vision-Language Inference on Smart Glasses","created":"2026-10-08","cited_by_count":0,"area":null},{"id":"2610.15882","title":"Engram Injection: A Study of Temporal Validity in Parametric Language-Model Memory","created":"2026-10-11","cited_by_count":0,"area":null},{"id":"2610.18098","title":"From Spectral Saliency to Finite Deletion: Evaluating Selective Language Model Edits","created":"2026-10-13","cited_by_count":0,"area":null},{"id":"2610.20253","title":"Repairing Speech Access After Text Updates with Frozen Affine Fields","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}