{"total":183,"rows":[{"id":"2406.05946","title":"Safety Alignment Should Be Made More Than Just a Few Tokens Deep","created":"2024-06-10","cited_by_count":472,"area":"alignment"},{"id":"2404.16789","title":"Continual Learning of Large Language Models: A Comprehensive Survey","created":"2024-04-25","cited_by_count":234,"area":null},{"id":"2508.03613","title":"Goedel-Prover-V2: Scaling Formal Theorem Proving with Scaffolded Data Synthesis and Self-Correction","created":"2025-08-05","cited_by_count":154,"area":"synth"},{"id":"2402.01364","title":"Continual Learning for Large Language Models: A Survey","created":"2024-02-02","cited_by_count":147,"area":null},{"id":"2309.10313","title":"Investigating the Catastrophic Forgetting in Multimodal Large Language Models","created":"2023-09-19","cited_by_count":119,"area":"mllm"},{"id":"2401.02906","title":"MLLM-Protector: Ensuring MLLM's Safety without Hurting Performance","created":"2024-01-05","cited_by_count":117,"area":"mllm"},{"id":"2504.17550","title":"HalluLens: LLM Hallucination Benchmark","created":"2025-04-24","cited_by_count":92,"area":null},{"id":"2404.14387","title":"A Survey on Self-Evolution of Large Language Models","created":"2024-04-22","cited_by_count":91,"area":null},{"id":"2404.08555","title":"RLHF Deciphered: A Critical Analysis of Reinforcement Learning from Human Feedback for LLMs","created":"2024-04-12","cited_by_count":90,"area":"alignment"},{"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":"2502.02384","title":"STAIR: Improving Safety Alignment with Introspective Reasoning","created":"2025-02-04","cited_by_count":77,"area":"lr"},{"id":"2403.08730","title":"Strengthening Multimodal Large Language Model with Bootstrapped Preference Optimization","created":"2024-03-13","cited_by_count":75,"area":"mllm"},{"id":"2312.07000","title":"Alignment for Honesty","created":"2023-12-12","cited_by_count":74,"area":"alignment"},{"id":"2402.15018","title":"Unintended Impacts of LLM Alignment on Global Representation","created":"2024-02-22","cited_by_count":66,"area":"alignment"},{"id":"2406.06391","title":"Towards Lifelong Learning of Large Language Models: A Survey","created":"2024-06-10","cited_by_count":64,"area":null},{"id":"2410.03642","title":"Aligning LLMs with Individual Preferences via Interaction","created":"2024-10-04","cited_by_count":63,"area":"alignment"},{"id":"2502.00674","title":"Rethinking Mixture-of-Agents: Is Mixing Different Large Language Models Beneficial?","created":"2025-02-02","cited_by_count":54,"area":"lr"},{"id":"2504.16656","title":"Skywork R1V2: Multimodal Hybrid Reinforcement Learning for Reasoning","created":"2025-04-23","cited_by_count":49,"area":"lr"},{"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":"2406.16768","title":"WARP: On the Benefits of Weight Averaged Rewarded Policies","created":"2024-06-24","cited_by_count":45,"area":"alignment"},{"id":"2407.06089","title":"Merge, Ensemble, and Cooperate! A Survey on Collaborative Strategies in the Era of Large Language Models","created":"2024-07-08","cited_by_count":44,"area":null},{"id":"2505.11049","title":"GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning","created":"2025-05-16","cited_by_count":42,"area":"lr"},{"id":"2603.10749","title":"AttriGuard: Defeating Indirect Prompt Injection in LLM Agents via Causal Attribution of Tool Invocations","created":"2026-03-11","cited_by_count":38,"area":"agents"},{"id":"2404.16792","title":"Model Extrapolation Expedites Alignment","created":"2024-04-25","cited_by_count":37,"area":"alignment"},{"id":"2407.08699","title":"Mitigating Catastrophic Forgetting in Language Transfer via Model Merging","created":"2024-07-11","cited_by_count":36,"area":null},{"id":"2503.11701","title":"A Survey of Direct Preference Optimization","created":"2025-03-12","cited_by_count":36,"area":"alignment"},{"id":"2505.10833","title":"MergeBench: A Benchmark for Merging Domain-Specialized LLMs","created":"2025-05-16","cited_by_count":33,"area":null},{"id":"2406.05587","title":"Creativity Has Left the Chat: The Price of Debiasing Language Models","created":"2024-06-08","cited_by_count":29,"area":"alignment"},{"id":"2509.03403","title":"Beyond Correctness: Harmonizing Process and Outcome Rewards through RL Training","created":"2025-09-03","cited_by_count":29,"area":"alignment"},{"id":"2405.17931","title":"Online Merging Optimizers for Boosting Rewards and Mitigating Tax in Alignment","created":"2024-05-28","cited_by_count":28,"area":"alignment"},{"id":"2410.15595","title":"A Comprehensive Survey of Direct Preference Optimization: Datasets, Theories, Variants, and Applications","created":"2024-10-21","cited_by_count":27,"area":"lr"},{"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":"2407.08770","title":"Model Surgery: Modulating LLM's Behavior Via Simple Parameter Editing","created":"2024-07-11","cited_by_count":23,"area":"alignment"},{"id":"2412.06712","title":"How to Merge Your Multimodal Models Over Time?","created":"2024-12-09","cited_by_count":23,"area":null},{"id":"2503.18991","title":"Inverse Reinforcement Learning with Dynamic Reward Scaling for LLM Alignment","created":"2025-03-23","cited_by_count":20,"area":"alignment"},{"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":"2411.10928","title":"Learn from Downstream and Be Yourself in Multimodal Large Language Model Fine-Tuning","created":"2024-11-17","cited_by_count":19,"area":"mllm"},{"id":"2412.18295","title":"Pirates of the RAG: Adaptively Attacking LLMs to Leak Knowledge Bases","created":"2024-12-24","cited_by_count":18,"area":"rag"},{"id":"2502.08301","title":"Compromising Honesty and Harmlessness in Language Models via Deception Attacks","created":"2025-02-12","cited_by_count":17,"area":null},{"id":"2502.02797","title":"Upweighting Easy Samples in Fine-Tuning Mitigates Forgetting","created":"2025-02-05","cited_by_count":16,"area":null},{"id":"2502.11019","title":"Unlocking the Power of Function Vectors for Characterizing and Mitigating Catastrophic Forgetting in Continual Instruction Tuning","created":"2025-02-16","cited_by_count":16,"area":null},{"id":"2406.10991","title":"Adaptive Query Rewriting: Aligning Rewriters through Marginal Probability of Conversational Answers","created":"2024-06-16","cited_by_count":15,"area":"alignment"},{"id":"2507.21183","title":"MaPPO: Maximum a Posteriori Preference Optimization with Prior Knowledge","created":"2025-07-27","cited_by_count":15,"area":"alignment"},{"id":"2508.06249","title":"In-Training Defenses against Emergent Misalignment in Language Models","created":"2025-08-08","cited_by_count":15,"area":"alignment"},{"id":"2310.02527","title":"CITING: Large Language Models Create Curriculum for Instruction Tuning","created":"2023-10-04","cited_by_count":14,"area":null},{"id":"2407.20999","title":"MoFO: Momentum-Filtered Optimizer for Mitigating Forgetting in LLM Fine-Tuning","created":"2024-07-30","cited_by_count":14,"area":null},{"id":"2410.10862","title":"Superficial Safety Alignment Hypothesis","created":"2024-10-07","cited_by_count":14,"area":"alignment"},{"id":"2505.17231","title":"ExeSQL: Self-Taught Text-to-SQL Models with Execution-Driven Bootstrapping for SQL Dialects","created":"2025-05-22","cited_by_count":12,"area":"synth"},{"id":"2505.18658","title":"Robustness in Large Language Models: A Survey of Mitigation Strategies and Evaluation Metrics","created":"2025-05-24","cited_by_count":12,"area":null},{"id":"2411.02688","title":"On the Loss of Context-awareness in General Instruction Fine-tuning","created":"2024-11-05","cited_by_count":11,"area":null},{"id":"2505.17496","title":"Analyzing Mitigation Strategies for Catastrophic Forgetting in End-to-End Training of Spoken Language Models","created":"2025-05-23","cited_by_count":11,"area":null},{"id":"2507.07375","title":"Bradley-Terry and Multi-Objective Reward Modeling Are Complementary","created":"2025-07-10","cited_by_count":11,"area":"alignment"},{"id":"2510.08564","title":"How to Teach Large Multimodal Models New Skills","created":"2025-10-09","cited_by_count":11,"area":"mllm"},{"id":"2510.17776","title":"Mapping Post-Training Forgetting in Language Models at Scale","created":"2025-10-20","cited_by_count":11,"area":null},{"id":"2512.11391","title":"Mitigating the Safety Alignment Tax with Null-Space Constrained Policy Optimization","created":"2025-12-12","cited_by_count":11,"area":"alignment"},{"id":"2503.15548","title":"Privacy-Aware RAG: Secure and Isolated Knowledge Retrieval","created":"2025-03-17","cited_by_count":10,"area":"rag"},{"id":"2510.09913","title":"Don't Throw Away Your Pretrained Model","created":"2025-10-10","cited_by_count":10,"area":"lr"},{"id":"2510.17426","title":"Navigating the Alignment-Calibration Trade-off: A Pareto-Superior Frontier via Model Merging","created":"2025-10-20","cited_by_count":10,"area":"alignment"},{"id":"2402.17982","title":"Collaborative decoding of critical tokens for boosting factuality of large language models","created":"2024-02-28","cited_by_count":9,"area":null},{"id":"2501.06481","title":"Focus-N-Fix: Region-Aware Fine-Tuning for Text-to-Image Generation","created":"2025-01-11","cited_by_count":9,"area":"alignment"},{"id":"2503.08796","title":"Robust Multi-Objective Controlled Decoding of Large Language Models","created":"2025-03-11","cited_by_count":9,"area":null},{"id":"2503.13505","title":"Ensemble Learning for Large Language Models in Text and Code Generation: A Survey","created":"2025-03-13","cited_by_count":9,"area":null},{"id":"2506.01901","title":"Understanding Overadaptation in Supervised Fine-Tuning: The Role of Ensemble Methods","created":"2025-06-02","cited_by_count":9,"area":null},{"id":"2502.00666","title":"Avoiding $\\mathbf{exp(R_{max})}$ scaling in RLHF through Preference-based Exploration","created":"2025-02-02","cited_by_count":8,"area":"alignment"},{"id":"2505.12060","title":"Why Not Act on What You Know? Unleashing Safety Potential of LLMs via Self-Aware Guard Enhancement","created":"2025-05-17","cited_by_count":8,"area":"safety"},{"id":"2507.11500","title":"ARMOR: Aligning Secure and Safe Large Language Models via Meticulous Reasoning","created":"2025-07-14","cited_by_count":8,"area":"alignment"},{"id":"2407.03856","title":"Q-Adapter: Customizing Pre-trained LLMs to New Preferences with Forgetting Mitigation","created":"2024-07-04","cited_by_count":7,"area":"alignment"},{"id":"2509.24610","title":"OrthAlign: Orthogonal Subspace Decomposition for Non-Interfering Multi-Objective Alignment","created":"2025-09-29","cited_by_count":7,"area":"alignment"},{"id":"2410.04834","title":"As Simple as Fine-tuning: LLM Alignment via Bidirectional Negative Feedback Loss","created":"2024-10-07","cited_by_count":6,"area":"alignment"},{"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":"2505.00808","title":"A Mathematical Philosophy of Explanations in Mechanistic Interpretability -- The Strange Science Part I.i","created":"2025-05-01","cited_by_count":6,"area":"mechinterp"},{"id":"2602.07892","title":"Safety Alignment as Continual Learning: Mitigating the Alignment Tax via Orthogonal Gradient Projection","created":"2026-02-08","cited_by_count":6,"area":"alignment"},{"id":"2605.12484","title":"Learning, Fast and Slow: Towards LLMs That Adapt Continually","created":"2026-05-12","cited_by_count":6,"area":null},{"id":"2411.19335","title":"PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning","created":"2024-11-28","cited_by_count":5,"area":"safety"},{"id":"2503.21383","title":"Controlling Large Language Model with Latent Actions","created":"2025-03-27","cited_by_count":5,"area":null},{"id":"2505.13811","title":"Context-Free Synthetic Data Mitigates Forgetting","created":"2025-05-20","cited_by_count":5,"area":"synth"},{"id":"2509.05381","title":"Murphys Laws of AI Alignment: Why the Gap Always Wins","created":"2025-09-04","cited_by_count":5,"area":"alignment"},{"id":"2605.07632","title":"Post-training makes large language models less human-like","created":"2026-05-08","cited_by_count":5,"area":null},{"id":"2401.06792","title":"LightHouse: A Survey of AGI Hallucination","created":"2024-01-08","cited_by_count":4,"area":null},{"id":"2402.08096","title":"An Efficient Rehearsal Scheme for Catastrophic Forgetting Mitigation during Multi-stage Fine-tuning","created":"2024-02-12","cited_by_count":4,"area":null},{"id":"2404.05499","title":"Guiding Large Language Models to Generate Computer-Parsable Content","created":"2024-04-08","cited_by_count":4,"area":null},{"id":"2410.12926","title":"DEeR: Deviation Eliminating and Noise Regulating for Privacy-preserving Federated Low-rank Adaptation","created":"2024-10-16","cited_by_count":4,"area":null},{"id":"2411.17471","title":"Learning New Concepts, Remembering the Old: Continual Learning for Multimodal Concept Bottleneck Models","created":"2024-11-25","cited_by_count":4,"area":null},{"id":"2502.19127","title":"Exploring the Generalizability of Factual Hallucination Mitigation via Enhancing Precise Knowledge Utilization","created":"2025-02-26","cited_by_count":4,"area":null},{"id":"2508.09473","title":"NeuronTune: Fine-Grained Neuron Modulation for Balanced Safety-Utility Alignment in LLMs","created":"2025-08-13","cited_by_count":4,"area":"alignment"},{"id":"2509.14760","title":"Reasoning over Boundaries: Enhancing Specification Alignment via Test-time Deliberation","created":"2025-09-18","cited_by_count":4,"area":"lr"},{"id":"2509.23765","title":"Knowledge-Level Consistency Reinforcement Learning: Dual-Fact Alignment for Long-Form Factuality","created":"2025-09-28","cited_by_count":4,"area":"alignment"},{"id":"2510.06652","title":"Aligning Large Language Models via Fully Self-Synthetic Data","created":"2025-10-08","cited_by_count":4,"area":"alignment"},{"id":"2511.05933","title":"Reinforcement Learning Improves Traversal of Parametric Knowledge in LLMs","created":"2025-11-08","cited_by_count":4,"area":null},{"id":"2511.11966","title":"On the Entropy Calibration of Language Models","created":"2025-11-15","cited_by_count":4,"area":null},{"id":"2602.02477","title":"Training LLMs for Divide-and-Conquer Reasoning Elevates Test-Time Scalability","created":"2026-02-02","cited_by_count":4,"area":"lr"},{"id":"2602.03806","title":"Bridging Online and Offline RL: Contextual Bandit Learning for Multi-Turn Code Generation","created":"2026-02-03","cited_by_count":4,"area":"offlinerl"},{"id":"2602.15156","title":"Panini: Continual Learning in Token Space via Structured Memory","created":"2026-02-16","cited_by_count":4,"area":null},{"id":"2603.24124","title":"The Alignment Tax: Response Homogenization in Aligned LLMs and Its Implications for Uncertainty Estimation","created":"2026-03-25","cited_by_count":4,"area":"alignment"},{"id":"2604.19292","title":"Location Not Found: Exposing Implicit Local and Global Biases in Multilingual LLMs","created":"2026-04-21","cited_by_count":4,"area":null},{"id":"2502.00136","title":"A Checks-and-Balances Framework for Context-Aware Ethical AI Alignment","created":"2025-01-31","cited_by_count":3,"area":"alignment"},{"id":"2502.08657","title":"Refining Positive and Toxic Samples for Dual Safety Self-Alignment of LLMs with Minimal Human Interventions","created":"2025-02-08","cited_by_count":3,"area":"alignment"},{"id":"2503.23777","title":"CONGRAD:Conflicting Gradient Filtering for Multilingual Preference Alignment","created":"2025-03-31","cited_by_count":3,"area":"alignment"},{"id":"2505.19327","title":"Paying Alignment Tax with Contrastive Learning","created":"2025-05-25","cited_by_count":3,"area":"alignment"},{"id":"2506.15717","title":"daDPO: Distribution-Aware DPO for Distilling Conversational Abilities","created":"2025-06-03","cited_by_count":3,"area":"alignment"}],"next_cursor":"100"}