{"total":27,"rows":[{"id":"2502.20968","title":"Beware of Your Po! Measuring and Mitigating AI Safety Risks in Role-Play Fine-Tuning of LLMs","created":"2025-02-28","cited_by_count":22,"area":null},{"id":"2501.18100","title":"Panacea: Mitigating Harmful Fine-tuning for Large Language Models via Post-fine-tuning Perturbation","created":"2025-01-30","cited_by_count":20,"area":null},{"id":"2506.08473","title":"AsFT: Anchoring Safety During LLM Fine-Tuning Within Narrow Safety Basin","created":"2025-06-10","cited_by_count":19,"area":null},{"id":"2503.20807","title":"Fundamental Safety-Capability Trade-offs in Fine-tuning Large Language Models","created":"2025-03-24","cited_by_count":17,"area":null},{"id":"2505.17895","title":"DataRater: Meta-Learned Dataset Curation","created":"2025-05-23","cited_by_count":13,"area":null},{"id":"2510.27172","title":"Adaptive Defense against Harmful Fine-Tuning for Large Language Models via Bayesian Data Scheduler","created":"2025-10-31","cited_by_count":12,"area":null},{"id":"2502.00840","title":"Activation Approximations Can Incur Safety Vulnerabilities Even in Aligned LLMs: Comprehensive Analysis and Defense","created":"2025-02-02","cited_by_count":7,"area":null},{"id":"2502.08585","title":"LDC-MTL: Balancing Multi-Task Learning through Scalable Loss Discrepancy Control","created":"2025-02-12","cited_by_count":7,"area":null},{"id":"2510.06048","title":"BLISS: A Lightweight Bilevel Influence Scoring Method for Data Selection in Language Model Pretraining","created":"2025-10-07","cited_by_count":3,"area":null},{"id":"2603.01185","title":"Token-level Data Selection for Safe LLM Fine-tuning","created":"2026-03-01","cited_by_count":3,"area":null},{"id":"2511.21056","title":"Bilevel Data Curation for LLM Fine-tuning: Offline Selection and Online Self-Refining Generation","created":"2025-11-26","cited_by_count":2,"area":null},{"id":"2509.02937","title":"Faster Gradient Methods for Highly-Smooth Stochastic Bilevel Optimization","created":"2025-09-03","cited_by_count":1,"area":null},{"id":"2509.15543","title":"Nonconvex Decentralized Stochastic Bilevel Optimization under Heavy-Tailed Noise","created":"2025-09-19","cited_by_count":1,"area":null},{"id":"2510.21885","title":"Preventing Catastrophic Forgetting: Behavior-Aware Sampling for Safer Language Model Fine-Tuning","created":"2025-10-23","cited_by_count":1,"area":null},{"id":"2602.04306","title":"DeFrame: Debiasing Large Language Models Against Framing Effects","created":"2026-02-04","cited_by_count":1,"area":null},{"id":"2605.09094","title":"A Tale of Two Problems: Multi-Task Bilevel Learning Meets Equality Constrained Multi-Objective Optimization","created":"2026-05-09","cited_by_count":1,"area":null},{"id":"2606.00160","title":"DataShield: Safety-degrading Data Filtering for LLM Benign Instruction Fine-Tuning","created":"2026-05-29","cited_by_count":1,"area":null},{"id":"2505.17151","title":"Bayesian Optimization for Enhanced Language Models: Optimizing Acquisition Functions","created":"2025-05-22","cited_by_count":0,"area":null},{"id":"2601.22016","title":"TBDFiltering: Sample-Efficient Tree-Based Data Filtering","created":"2026-01-29","cited_by_count":0,"area":null},{"id":"2605.06166","title":"One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.10288","title":"BROS: Bias-Corrected Randomized Subspaces for Memory-Efficient Single-Loop Bilevel Optimization","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.14194","title":"GradShield: Alignment Preserving Finetuning","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2608.04322","title":"DataRx: Missingness-Aware Sampling for Safer Large Language Model Task-Specific Fine-Tuning","created":"2026-08-05","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":"2609.30501","title":"To Solve Bilevel Optimization with Nonconvex Lower Levels, We Need Second-Order Stationarity","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2609.32484","title":"Towards Scalable Data Diversification for Language Model Pretraining via Leverage Score Sampling","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2610.02092","title":"Scalable, Transferable Meta-network for Data Selection Requires a Different Loss (and Why the Obvious Choice is Problematic)","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}