{"total":46,"rows":[{"id":"2410.20290","title":"Fast Best-of-N Decoding via Speculative Rejection","created":"2024-10-26","cited_by_count":112,"area":null},{"id":"2503.14286","title":"Tapered Off-Policy REINFORCE: Stable and efficient reinforcement learning for LLMs","created":"2025-03-18","cited_by_count":61,"area":null},{"id":"2412.07097","title":"On Evaluating the Durability of Safeguards for Open-Weight LLMs","created":"2024-12-10","cited_by_count":52,"area":null},{"id":"2406.10209","title":"Be like a Goldfish, Don't Memorize! Mitigating Memorization in Generative LLMs","created":"2024-06-14","cited_by_count":50,"area":null},{"id":"2505.11711","title":"Reinforcement Learning Finetunes Small Subnetworks in Large Language Models","created":"2025-05-16","cited_by_count":49,"area":null},{"id":"2406.18664","title":"Evaluating Copyright Takedown Methods for Language Models","created":"2024-06-26","cited_by_count":43,"area":null},{"id":"2505.00030","title":"Can Language Models Represent the Past without Anachronism?","created":"2025-04-28","cited_by_count":14,"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":"2505.22586","title":"Precise In-Parameter Concept Erasure in Large Language Models","created":"2025-05-28","cited_by_count":11,"area":null},{"id":"2502.00602","title":"Mitigating Heterogeneous Token Overfitting in LLM Knowledge Editing","created":"2025-02-02","cited_by_count":8,"area":null},{"id":"2509.18868","title":"Memory in Large Language Models: Mechanisms, Evaluation and Evolution","created":"2025-09-23","cited_by_count":8,"area":null},{"id":"2412.06619","title":"Copyright-Protected Language Generation via Adaptive Model Fusion","created":"2024-12-09","cited_by_count":7,"area":null},{"id":"2412.15557","title":"MORTAR: Multi-turn Metamorphic Testing for LLM-based Dialogue Systems","created":"2024-12-20","cited_by_count":7,"area":null},{"id":"2507.09937","title":"Memorization Sinks: Isolating Memorization during LLM Training","created":"2025-07-14","cited_by_count":7,"area":null},{"id":"2409.03274","title":"Recent Advances in Attack and Defense Approaches of Large Language Models","created":"2024-09-05","cited_by_count":6,"area":null},{"id":"2410.09543","title":"Boltzmann-Aligned Inverse Folding Model as a Predictor of Mutational Effects on Protein-Protein Interactions","created":"2024-10-12","cited_by_count":5,"area":null},{"id":"2505.19145","title":"Do Large Language Models (Really) Need Statistical Foundations?","created":"2025-05-25","cited_by_count":5,"area":null},{"id":"2407.20105","title":"Strong Copyright Protection for Language Models via Adaptive Model Fusion","created":"2024-07-29","cited_by_count":4,"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":"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":"2602.05164","title":"Position: Capability Control Should be a Separate Goal From Alignment","created":"2026-02-05","cited_by_count":2,"area":null},{"id":"2602.08901","title":"Mitigating Memorization Where It Happens","created":"2026-02-09","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":"2510.12117","title":"Locket: Robust Feature-Locking Technique for Language Models","created":"2025-10-14","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":"2603.18570","title":"Attack by Unlearning: Unlearning-Induced Adversarial Attacks on Graph Neural Networks","created":"2026-03-19","cited_by_count":1,"area":null},{"id":"2604.05995","title":"The Model Agreed, But Didn't Learn: Diagnosing Surface Compliance in Large Language Models","created":"2026-04-07","cited_by_count":1,"area":null},{"id":"2510.03271","title":"Decision Potential Surface: A Theoretical and Practical Approximation of Large Language Model Decision Boundary","created":"2025-09-27","cited_by_count":0,"area":null},{"id":"2512.12469","title":"Sparse Concept Anchoring for Interpretable and Controllable Neural Representations","created":"2025-12-13","cited_by_count":0,"area":null},{"id":"2512.20634","title":"Real Time Detection and Quantitative Analysis of Spurious Forgetting in Continual Learning","created":"2025-12-02","cited_by_count":0,"area":null},{"id":"2602.10430","title":"Breaking the Curse of Repulsion: Remoteness-Aware Control of Negative Off-Policy Updates","created":"2026-02-11","cited_by_count":0,"area":null},{"id":"2603.07551","title":"Speech Generation Speaker Poisoning: Capability Erasure in Zero-Shot Text-to-Speech","created":"2026-03-08","cited_by_count":0,"area":null},{"id":"2605.13595","title":"Inducing Artificial Uncertainty in Language Models","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2606.03695","title":"Don't Forget Your Embeddings: Robust Knowledge Erasure via Precise Editing of Embeddings","created":"2026-06-02","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":"2606.30788","title":"Revocable Learned State via Process Sidecars","created":"2026-06-29","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":"2608.27782","title":"Memorization Is Not Extraction: Tight Differential-Privacy Bounds and Audit Blind Spots","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2609.00184","title":"Synthetic Worlds for Temporal Evaluation and Knowledge Updating in LLMs","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.00492","title":"The Privacy-Hallucination Tradeoff in Differentially Private Language Models","created":"2026-08-31","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":"2609.34528","title":"Preference-Guided Adaptation for Open-Vocabulary Semantic Segmentation via Prompt Disagreement","created":"2026-09-28","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}],"next_cursor":null}