{"total":32,"rows":[{"id":"2403.13372","title":"LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models","created":"2024-03-20","cited_by_count":1464,"area":null},{"id":"2408.07666","title":"Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities","created":"2024-08-14","cited_by_count":254,"area":null},{"id":"2505.23836","title":"Large Language Models Often Know When They Are Being Evaluated","created":"2025-05-28","cited_by_count":128,"area":null},{"id":"2407.18418","title":"Know Your Limits: A Survey of Abstention in Large Language Models","created":"2024-07-25","cited_by_count":121,"area":null},{"id":"2409.01586","title":"Booster: Tackling Harmful Fine-tuning for Large Language Models via Attenuating Harmful Perturbation","created":"2024-09-03","cited_by_count":92,"area":null},{"id":"2402.16382","title":"Immunization against harmful fine-tuning attacks","created":"2024-02-26","cited_by_count":35,"area":null},{"id":"2411.18729","title":"Multi-Task Model Merging via Adaptive Weight Disentanglement","created":"2024-11-27","cited_by_count":22,"area":null},{"id":"2505.12038","title":"Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets","created":"2025-05-17","cited_by_count":18,"area":null},{"id":"2408.03837","title":"WalledEval: A Comprehensive Safety Evaluation Toolkit for Large Language Models","created":"2024-08-07","cited_by_count":17,"area":null},{"id":"2410.10801","title":"Mix Data or Merge Models? Optimizing for Diverse Multi-Task Learning","created":"2024-10-14","cited_by_count":17,"area":null},{"id":"2406.02925","title":"Task Arithmetic can Mitigate Synthetic-to-Real Gap in Automatic Speech Recognition","created":"2024-06-05","cited_by_count":14,"area":null},{"id":"2502.15924","title":"Improving Consistency in Large Language Models through Chain of Guidance","created":"2025-02-21","cited_by_count":13,"area":null},{"id":"2412.19512","title":"Safeguard Fine-Tuned LLMs Through Pre- and Post-Tuning Model Merging","created":"2024-12-27","cited_by_count":11,"area":null},{"id":"2410.04524","title":"Toward Secure Tuning: Mitigating Security Risks from Instruction Fine-Tuning","created":"2024-10-06","cited_by_count":8,"area":null},{"id":"2507.21141","title":"The Geometry of Harmfulness in LLMs through Subconcept Probing","created":"2025-07-23","cited_by_count":7,"area":null},{"id":"2509.06795","title":"Anchoring Refusal Direction: Mitigating Safety Risks in Tuning via Projection Constraint","created":"2025-09-08","cited_by_count":7,"area":null},{"id":"2411.06824","title":"Combining Domain and Alignment Vectors to Achieve Better Knowledge-Safety Trade-offs in LLMs","created":"2024-11-11","cited_by_count":6,"area":null},{"id":"2502.20186","title":"Layer-Aware Task Arithmetic: Disentangling Task-Specific and Instruction-Following Knowledge","created":"2025-02-27","cited_by_count":6,"area":null},{"id":"2505.00649","title":"Investigating Task Arithmetic for Zero-Shot Information Retrieval","created":"2025-05-01","cited_by_count":4,"area":null},{"id":"2511.10712","title":"Do Not Merge My Model! Safeguarding Open-Source LLMs Against Unauthorized Model Merging","created":"2025-11-13","cited_by_count":2,"area":null},{"id":"2602.13071","title":"Bus-Conditioned Zero-Shot Trajectory Generation via Task Arithmetic","created":"2026-02-13","cited_by_count":2,"area":null},{"id":"2509.06807","title":"MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security","created":"2025-09-08","cited_by_count":1,"area":null},{"id":"2510.11268","title":"Exploring and Leveraging Class Vectors for Classifier Editing","created":"2025-10-13","cited_by_count":1,"area":null},{"id":"2603.22214","title":"Evaluating the Reliability and Fidelity of Automated Judgment Systems of Large Language Models","created":"2026-03-23","cited_by_count":0,"area":null},{"id":"2604.09265","title":"EthicMind: A Risk-Aware Framework for Ethical-Emotional Alignment in Multi-Turn Dialogue","created":"2026-04-10","cited_by_count":0,"area":null},{"id":"2605.30640","title":"CSULoRA: Closest Safe Update Low-Rank Adaptation","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2606.09697","title":"PsychoSafe: Eliciting Psychologically-Informed Refusals in Large Language Models","created":"2026-06-08","cited_by_count":0,"area":null},{"id":"2606.27944","title":"It Lied to a Doctor to Buy Poison Ingredients: Quantifying Real-World Misuse of Phone-use Agents","created":"2026-06-26","cited_by_count":0,"area":null},{"id":"2608.00042","title":"Trustworthiness Costs of Domain Adaptation in Small Language Models:A Cross-Architecture Empirical Study","created":"2026-07-23","cited_by_count":0,"area":null},{"id":"2609.00519","title":"The Safeguard Worked. Is the LLM System Safer?","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.09054","title":"Training-Free Task Vectors for LLM Behavioral Control","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}],"next_cursor":null}