{"total":639,"rows":[{"id":"2310.03693","title":"Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!","created":"2023-10-05","cited_by_count":1154,"area":"alignment"},{"id":"2412.05579","title":"LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods","created":"2024-12-07","cited_by_count":465,"area":null},{"id":"2402.13116","title":"A Survey on Knowledge Distillation of Large Language Models","created":"2024-02-20","cited_by_count":284,"area":"distill"},{"id":"2404.16789","title":"Continual Learning of Large Language Models: A Comprehensive Survey","created":"2024-04-25","cited_by_count":234,"area":null},{"id":"2407.04295","title":"Jailbreak Attacks and Defenses Against Large Language Models: A Survey","created":"2024-07-05","cited_by_count":230,"area":"safety"},{"id":"2310.07521","title":"Survey on Factuality in Large Language Models: Knowledge, Retrieval and Domain-Specificity","created":"2023-10-11","cited_by_count":206,"area":null},{"id":"2310.16218","title":"Knowledge Editing for Large Language Models: A Survey","created":"2023-10-24","cited_by_count":194,"area":"lr"},{"id":"2311.01964","title":"Don't Make Your LLM an Evaluation Benchmark Cheater","created":"2023-11-03","cited_by_count":194,"area":null},{"id":"2402.00888","title":"Security and Privacy Challenges of Large Language Models: A Survey","created":"2024-01-30","cited_by_count":186,"area":"safety"},{"id":"2403.16952","title":"Data Mixing Laws: Optimizing Data Mixtures by Predicting Language Modeling Performance","created":"2024-03-25","cited_by_count":184,"area":null},{"id":"2312.05934","title":"Fine-Tuning or Retrieval? Comparing Knowledge Injection in LLMs","created":"2023-12-10","cited_by_count":178,"area":null},{"id":"2509.04259","title":"RL's Razor: Why Online Reinforcement Learning Forgets Less","created":"2025-09-04","cited_by_count":176,"area":"lr"},{"id":"2405.16009","title":"Streaming Long Video Understanding with Large Language Models","created":"2024-05-25","cited_by_count":167,"area":null},{"id":"2504.00906","title":"Agent S2: A Compositional Generalist-Specialist Framework for Computer Use Agents","created":"2025-04-01","cited_by_count":159,"area":"agents"},{"id":"2309.10105","title":"Understanding Catastrophic Forgetting in Language Models via Implicit Inference","created":"2023-09-18","cited_by_count":144,"area":"alignment"},{"id":"2407.12404","title":"Analyzing the Generalization and Reliability of Steering Vectors","created":"2024-07-17","cited_by_count":143,"area":"mechinterp"},{"id":"2502.21321","title":"LLM Post-Training: A Deep Dive into Reasoning Large Language Models","created":"2025-02-28","cited_by_count":135,"area":"lr"},{"id":"2407.19354","title":"The Emerged Security and Privacy of LLM Agent: A Survey with Case Studies","created":"2024-07-28","cited_by_count":131,"area":"agents"},{"id":"2405.13792","title":"xRAG: Extreme Context Compression for Retrieval-augmented Generation with One Token","created":"2024-05-22","cited_by_count":125,"area":"rag"},{"id":"2403.01244","title":"Mitigating Catastrophic Forgetting in Large Language Models with Self-Synthesized Rehearsal","created":"2024-03-02","cited_by_count":118,"area":null},{"id":"2401.00908","title":"DocLLM: A layout-aware generative language model for multimodal document understanding","created":"2023-12-31","cited_by_count":116,"area":null},{"id":"2502.14420","title":"ChatVLA: Unified Multimodal Understanding and Robot Control with Vision-Language-Action Model","created":"2025-02-20","cited_by_count":113,"area":"vla"},{"id":"2402.13669","title":"Self-Distillation Bridges Distribution Gap in Language Model Fine-Tuning","created":"2024-02-21","cited_by_count":96,"area":"distill"},{"id":"2402.18540","title":"Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt Templates","created":"2024-02-28","cited_by_count":96,"area":null},{"id":"2403.13355","title":"BadEdit: Backdooring large language models by model editing","created":"2024-03-20","cited_by_count":96,"area":"safety"},{"id":"2510.18874","title":"Retaining by Doing: The Role of On-Policy Data in Mitigating Forgetting","created":"2025-10-21","cited_by_count":94,"area":null},{"id":"2403.08715","title":"SOTOPIA-$\\pi$: Interactive Learning of Socially Intelligent Language Agents","created":"2024-03-13","cited_by_count":93,"area":"agents"},{"id":"2405.14768","title":"WISE: Rethinking the Knowledge Memory for Lifelong Model Editing of Large Language Models","created":"2024-05-23","cited_by_count":92,"area":"lr"},{"id":"2406.11813","title":"How Do Large Language Models Acquire Factual Knowledge During Pretraining?","created":"2024-06-17","cited_by_count":90,"area":null},{"id":"2501.07278","title":"Lifelong Learning of Large Language Model based Agents: A Roadmap","created":"2025-01-13","cited_by_count":83,"area":"agents"},{"id":"2407.08223","title":"Speculative RAG: Enhancing Retrieval Augmented Generation through Drafting","created":"2024-07-11","cited_by_count":77,"area":"rag"},{"id":"2408.16673","title":"Preserving Diversity in Supervised Fine-Tuning of Large Language Models","created":"2024-08-29","cited_by_count":70,"area":null},{"id":"2410.23054","title":"Controlling Language and Diffusion Models by Transporting Activations","created":"2024-10-30","cited_by_count":68,"area":"diffusion"},{"id":"2310.06762","title":"TRACE: A Comprehensive Benchmark for Continual Learning in Large Language Models","created":"2023-10-10","cited_by_count":66,"area":"alignment"},{"id":"2404.01030","title":"Survey of Bias In Text-to-Image Generation: Definition, Evaluation, and Mitigation","created":"2024-04-01","cited_by_count":66,"area":null},{"id":"2505.23646","title":"Are Reasoning Models More Prone to Hallucination?","created":"2025-05-29","cited_by_count":64,"area":"lr"},{"id":"2402.11260","title":"MoRAL: MoE Augmented LoRA for LLMs' Lifelong Learning","created":"2024-02-17","cited_by_count":63,"area":"moe"},{"id":"2403.08350","title":"CoIN: A Benchmark of Continual Instruction tuNing for Multimodel Large Language Model","created":"2024-03-13","cited_by_count":61,"area":"mllm"},{"id":"2403.11435","title":"InsCL: A Data-efficient Continual Learning Paradigm for Fine-tuning Large Language Models with Instructions","created":"2024-03-18","cited_by_count":58,"area":null},{"id":"2402.17400","title":"Investigating Continual Pretraining in Large Language Models: Insights and Implications","created":"2024-02-27","cited_by_count":57,"area":null},{"id":"2405.12035","title":"KG-RAG: Bridging the Gap Between Knowledge and Creativity","created":"2024-05-20","cited_by_count":56,"area":"rag"},{"id":"2310.04799","title":"Chat Vector: A Simple Approach to Equip LLMs with Instruction Following and Model Alignment in New Languages","created":"2023-10-07","cited_by_count":54,"area":"alignment"},{"id":"2310.10640","title":"LLM Blueprint: Enabling Text-to-Image Generation with Complex and Detailed Prompts","created":"2023-10-16","cited_by_count":54,"area":"diffusion"},{"id":"2602.15260","title":"Fast and Effective On-policy Distillation from Reasoning Prefixes","created":"2026-02-16","cited_by_count":53,"area":"distill"},{"id":"2502.04194","title":"The Best Instruction-Tuning Data are Those That Fit","created":"2025-02-06","cited_by_count":52,"area":null},{"id":"2311.16206","title":"Continual Instruction Tuning for Large Multimodal Models","created":"2023-11-27","cited_by_count":49,"area":"mllm"},{"id":"2602.01869","title":"Skill-Pro: Learning Reusable Skills from Experience via Non-Parametric PPO for LLM Agents","created":"2026-02-02","cited_by_count":47,"area":"agents"},{"id":"2405.18653","title":"Recent Advances of Foundation Language Models-based Continual Learning: A Survey","created":"2024-05-28","cited_by_count":46,"area":null},{"id":"2311.13534","title":"LM-Cocktail: Resilient Tuning of Language Models via Model Merging","created":"2023-11-22","cited_by_count":44,"area":null},{"id":"2310.19698","title":"When Do Prompting and Prefix-Tuning Work? A Theory of Capabilities and Limitations","created":"2023-10-30","cited_by_count":43,"area":null},{"id":"2312.10908","title":"CLOVA: A Closed-Loop Visual Assistant with Tool Usage and Update","created":"2023-12-18","cited_by_count":43,"area":null},{"id":"2403.10854","title":"A Comprehensive Study of Multimodal Large Language Models for Image Quality Assessment","created":"2024-03-16","cited_by_count":43,"area":"mllm"},{"id":"2505.13308","title":"Seek in the Dark: Reasoning via Test-Time Instance-Level Policy Gradient in Latent Space","created":"2025-05-19","cited_by_count":43,"area":"lr"},{"id":"2505.14646","title":"CAD-Coder: An Open-Source Vision-Language Model for Computer-Aided Design Code Generation","created":"2025-05-20","cited_by_count":43,"area":null},{"id":"2406.11171","title":"SUGARCREPE++ Dataset: Vision-Language Model Sensitivity to Semantic and Lexical Alterations","created":"2024-06-17","cited_by_count":42,"area":"mllm"},{"id":"2409.12993","title":"CraftRTL: High-quality Synthetic Data Generation for Verilog Code Models with Correct-by-Construction Non-Textual Representations and Targeted Code Repair","created":"2024-09-19","cited_by_count":42,"area":"synth"},{"id":"2501.01377","title":"Improving Medical Large Vision-Language Models with Abnormal-Aware Feedback","created":"2025-01-02","cited_by_count":42,"area":"mllm"},{"id":"2404.09486","title":"MMCode: Benchmarking Multimodal Large Language Models for Code Generation with Visually Rich Programming Problems","created":"2024-04-15","cited_by_count":40,"area":"mllm"},{"id":"2402.01763","title":"When Large Language Models Meet Vector Databases: A Survey","created":"2024-01-30","cited_by_count":39,"area":null},{"id":"2401.05605","title":"Scaling Laws for Forgetting When Fine-Tuning Large Language Models","created":"2024-01-11","cited_by_count":38,"area":null},{"id":"2310.15469","title":"The Janus Interface: How Fine-Tuning in Large Language Models Amplifies the Privacy Risks","created":"2023-10-24","cited_by_count":36,"area":null},{"id":"2406.06852","title":"A Survey of Recent Backdoor Attacks and Defenses in Large Language Models","created":"2024-06-10","cited_by_count":36,"area":"safety"},{"id":"2405.04798","title":"From LLMs to Actions: Latent Codes as Bridges in Hierarchical Robot Control","created":"2024-05-08","cited_by_count":35,"area":null},{"id":"2410.24087","title":"In-Context Fine-Tuning for Time-Series Foundation Models","created":"2024-10-31","cited_by_count":35,"area":null},{"id":"2502.06042","title":"Scaling Laws for Forgetting during Finetuning with Pretraining Data Injection","created":"2025-02-09","cited_by_count":35,"area":null},{"id":"2408.07362","title":"BadMerging: Backdoor Attacks Against Model Merging","created":"2024-08-14","cited_by_count":34,"area":null},{"id":"2410.13509","title":"RAG-DDR: Optimizing Retrieval-Augmented Generation Using Differentiable Data Rewards","created":"2024-10-17","cited_by_count":33,"area":"rag"},{"id":"2311.09179","title":"SiRA: Sparse Mixture of Low Rank Adaptation","created":"2023-11-15","cited_by_count":32,"area":"moe"},{"id":"2402.17887","title":"JMLR: Joint Medical LLM and Retrieval Training for Enhancing Reasoning and Professional Question Answering Capability","created":"2024-02-27","cited_by_count":32,"area":"lr"},{"id":"2406.16797","title":"Lottery Ticket Adaptation: Mitigating Destructive Interference in LLMs","created":"2024-06-24","cited_by_count":31,"area":null},{"id":"2512.04797","title":"SIMA 2: A Generalist Embodied Agent for Virtual Worlds","created":"2025-12-04","cited_by_count":31,"area":"agents"},{"id":"2312.13951","title":"Typhoon: Thai Large Language Models","created":"2023-12-21","cited_by_count":30,"area":null},{"id":"2510.07841","title":"Self-Improving LLM Agents at Test-Time","created":"2025-10-09","cited_by_count":30,"area":"agents"},{"id":"2510.09781","title":"Building a Foundational Guardrail for General Agentic Systems via Synthetic Data","created":"2025-10-10","cited_by_count":29,"area":"agents"},{"id":"2502.04506","title":"When One LLM Drools, Multi-LLM Collaboration Rules","created":"2025-02-06","cited_by_count":28,"area":null},{"id":"2510.13900","title":"Narrow Finetuning Leaves Clearly Readable Traces in Activation Differences","created":"2025-10-14","cited_by_count":28,"area":null},{"id":"2510.03264","title":"Front-Loading Reasoning: The Synergy between Pretraining and Post-Training Data","created":"2025-09-26","cited_by_count":27,"area":"lr"},{"id":"2402.11248","title":"CoLLaVO: Crayon Large Language and Vision mOdel","created":"2024-02-17","cited_by_count":26,"area":"mllm"},{"id":"2406.15477","title":"CrisisSense-LLM: Instruction Fine-Tuned Large Language Model for Multi-label Social Media Text Classification in Disaster Informatics","created":"2024-06-16","cited_by_count":25,"area":null},{"id":"2409.05314","title":"Tele-LLMs: A Series of Specialized Large Language Models for Telecommunications","created":"2024-09-09","cited_by_count":25,"area":null},{"id":"2505.24535","title":"Beyond Linear Steering: Unified Multi-Attribute Control for Language Models","created":"2025-05-30","cited_by_count":25,"area":null},{"id":"2310.09089","title":"Qilin-Med: Multi-stage Knowledge Injection Advanced Medical Large Language Model","created":"2023-10-13","cited_by_count":24,"area":null},{"id":"2312.12736","title":"Learning and Forgetting Unsafe Examples in Large Language Models","created":"2023-12-20","cited_by_count":24,"area":null},{"id":"2507.05418","title":"Learn Globally, Speak Locally: Bridging the Gaps in Multilingual Reasoning","created":"2025-07-07","cited_by_count":24,"area":"lr"},{"id":"2510.02453","title":"How to Train Your Advisor: Steering Black-Box LLMs with Advisor Models","created":"2025-10-02","cited_by_count":24,"area":null},{"id":"2602.05842","title":"Reinforcement World Model Learning for LLM-based Agents","created":"2026-02-05","cited_by_count":24,"area":"wm"},{"id":"2402.02868","title":"Fine-tuning Reinforcement Learning Models is Secretly a Forgetting Mitigation Problem","created":"2024-02-05","cited_by_count":23,"area":"deeprl"},{"id":"2407.08770","title":"Model Surgery: Modulating LLM's Behavior Via Simple Parameter Editing","created":"2024-07-11","cited_by_count":23,"area":"alignment"},{"id":"2407.17467","title":"CMR Scaling Law: Predicting Critical Mixture Ratios for Continual Pre-training of Language Models","created":"2024-07-24","cited_by_count":23,"area":null},{"id":"2402.01713","title":"Prompting Large Language Models for Zero-Shot Clinical Prediction with Structured Longitudinal Electronic Health Record Data","created":"2024-01-25","cited_by_count":22,"area":null},{"id":"2405.20089","title":"The Fine-Tuning Paradox: Boosting Translation Quality Without Sacrificing LLM Abilities","created":"2024-05-30","cited_by_count":22,"area":null},{"id":"2405.17830","title":"More Than Catastrophic Forgetting: Integrating General Capabilities For Domain-Specific LLMs","created":"2024-05-28","cited_by_count":21,"area":null},{"id":"2411.13405","title":"On the Way to LLM Personalization: Learning to Remember User Conversations","created":"2024-11-20","cited_by_count":21,"area":null},{"id":"2312.01678","title":"Jellyfish: A Large Language Model for Data Preprocessing","created":"2023-12-04","cited_by_count":20,"area":null},{"id":"2407.02446","title":"Predicting vs. Acting: A Trade-off Between World Modeling & Agent Modeling","created":"2024-07-02","cited_by_count":20,"area":"wm"},{"id":"2505.16690","title":"Your Pre-trained LLM is Secretly an Unsupervised Confidence Calibrator","created":"2025-05-22","cited_by_count":20,"area":null},{"id":"2509.21117","title":"TrustJudge: Inconsistencies of LLM-as-a-Judge and How to Alleviate Them","created":"2025-09-25","cited_by_count":20,"area":null},{"id":"2510.15103","title":"Continual Learning via Sparse Memory Finetuning","created":"2025-10-16","cited_by_count":20,"area":null},{"id":"2402.18150","title":"Unsupervised Information Refinement Training of Large Language Models for Retrieval-Augmented Generation","created":"2024-02-28","cited_by_count":19,"area":"rag"},{"id":"2403.04746","title":"LLMs in the Imaginarium: Tool Learning through Simulated Trial and Error","created":"2024-03-07","cited_by_count":19,"area":"agents"}],"next_cursor":"100"}