{"total":144,"rows":[{"id":"2402.13116","title":"A Survey on Knowledge Distillation of Large Language Models","created":"2024-02-20","cited_by_count":284,"area":"distill"},{"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":"2407.15549","title":"Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs","created":"2024-07-22","cited_by_count":173,"area":"safety"},{"id":"2402.16835","title":"Eight Methods to Evaluate Robust Unlearning in LLMs","created":"2024-02-26","cited_by_count":163,"area":"safety"},{"id":"2402.01364","title":"Continual Learning for Large Language Models: A Survey","created":"2024-02-02","cited_by_count":147,"area":null},{"id":"2404.02831","title":"Empowering Biomedical Discovery with AI Agents","created":"2024-04-03","cited_by_count":118,"area":null},{"id":"2401.02906","title":"MLLM-Protector: Ensuring MLLM's Safety without Hurting Performance","created":"2024-01-05","cited_by_count":117,"area":"mllm"},{"id":"2311.12786","title":"Mechanistically analyzing the effects of fine-tuning on procedurally defined tasks","created":"2023-11-21","cited_by_count":115,"area":null},{"id":"2403.03329","title":"Guardrail Baselines for Unlearning in LLMs","created":"2024-03-05","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":"2403.05030","title":"Defending Against Unforeseen Failure Modes with Latent Adversarial Training","created":"2024-03-08","cited_by_count":88,"area":"safety"},{"id":"2410.23054","title":"Controlling Language and Diffusion Models by Transporting Activations","created":"2024-10-30","cited_by_count":68,"area":"diffusion"},{"id":"2410.13886","title":"Refusal-Trained LLMs Are Easily Jailbroken As Browser Agents","created":"2024-10-11","cited_by_count":65,"area":"agents"},{"id":"2504.04377","title":"PolyGuard: A Multilingual Safety Moderation Tool for 17 Languages","created":"2025-04-06","cited_by_count":59,"area":null},{"id":"2407.10264","title":"What Makes and Breaks Safety Fine-tuning? A Mechanistic Study","created":"2024-07-14","cited_by_count":55,"area":"safety"},{"id":"2502.04194","title":"The Best Instruction-Tuning Data are Those That Fit","created":"2025-02-06","cited_by_count":52,"area":null},{"id":"2403.04893","title":"A Safe Harbor for AI Evaluation and Red Teaming","created":"2024-03-07","cited_by_count":47,"area":"safety"},{"id":"2502.12446","title":"Multi-Attribute Steering of Language Models via Targeted Intervention","created":"2025-02-18","cited_by_count":46,"area":null},{"id":"2505.05408","title":"Crosslingual Reasoning through Test-Time Scaling","created":"2025-05-08","cited_by_count":46,"area":"lr"},{"id":"2402.09269","title":"Personalized Large Language Models","created":"2024-02-14","cited_by_count":44,"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":"2411.02959","title":"HtmlRAG: HTML is Better Than Plain Text for Modeling Retrieved Knowledge in RAG Systems","created":"2024-11-05","cited_by_count":37,"area":"rag"},{"id":"2509.16679","title":"Reinforcement Learning Meets Large Language Models: A Survey of Advancements and Applications Across the LLM Lifecycle","created":"2025-09-20","cited_by_count":35,"area":null},{"id":"2402.12052","title":"Small Models, Big Insights: Leveraging Slim Proxy Models To Decide When and What to Retrieve for LLMs","created":"2024-02-19","cited_by_count":34,"area":null},{"id":"2407.18369","title":"AI Safety in Generative AI Large Language Models: A Survey","created":"2024-07-06","cited_by_count":33,"area":null},{"id":"2505.24726","title":"Reflect, Retry, Reward: Self-Improving LLMs via Reinforcement Learning","created":"2025-05-30","cited_by_count":33,"area":"synth"},{"id":"2505.02795","title":"HSplitLoRA: A Heterogeneous Split Parameter-Efficient Fine-Tuning Framework for Large Language Models","created":"2025-05-05","cited_by_count":31,"area":null},{"id":"2509.12235","title":"RL Fine-Tuning Heals OOD Forgetting in SFT","created":"2025-09-08","cited_by_count":31,"area":"lr"},{"id":"2406.12034","title":"Self-MoE: Towards Compositional Large Language Models with Self-Specialized Experts","created":"2024-06-17","cited_by_count":23,"area":"moe"},{"id":"2405.09373","title":"PolygloToxicityPrompts: Multilingual Evaluation of Neural Toxic Degeneration in Large Language Models","created":"2024-05-15","cited_by_count":20,"area":null},{"id":"2407.03994","title":"Unlocking the Potential of Model Merging for Low-Resource Languages","created":"2024-07-04","cited_by_count":19,"area":null},{"id":"2410.01294","title":"Endless Jailbreaks with Bijection Learning","created":"2024-10-02","cited_by_count":19,"area":"safety"},{"id":"2510.24702","title":"Agent Data Protocol: Unifying Datasets for Diverse, Effective Fine-tuning of LLM Agents","created":"2025-10-28","cited_by_count":17,"area":"agents"},{"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":"2505.07843","title":"PosterO: Structuring Layout Trees to Enable Language Models in Generalized Content-Aware Layout Generation","created":"2025-05-06","cited_by_count":16,"area":null},{"id":"2506.12860","title":"QFFT, Question-Free Fine-Tuning for Adaptive Reasoning","created":"2025-06-15","cited_by_count":15,"area":"lr"},{"id":"2510.04309","title":"Activation Steering with a Feedback Controller","created":"2025-10-05","cited_by_count":15,"area":"alignment"},{"id":"2406.20030","title":"LEMoE: Advanced Mixture of Experts Adaptor for Lifelong Model Editing of Large Language Models","created":"2024-06-28","cited_by_count":14,"area":"moe"},{"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":"2603.04964","title":"Replaying pre-training data improves fine-tuning","created":"2026-03-05","cited_by_count":13,"area":null},{"id":"2507.07341","title":"On the Impossibility of Separating Intelligence from Judgment: The Computational Intractability of Filtering for AI Alignment","created":"2025-07-09","cited_by_count":12,"area":"safety"},{"id":"2510.20956","title":"Self-Jailbreaking: Language Models Can Reason Themselves Out of Safety Alignment After Benign Reasoning Training","created":"2025-10-23","cited_by_count":12,"area":"lr"},{"id":"2507.04642","title":"R1-RE: Cross-Domain Relation Extraction with RLVR","created":"2025-07-07","cited_by_count":11,"area":null},{"id":"2510.17776","title":"Mapping Post-Training Forgetting in Language Models at Scale","created":"2025-10-20","cited_by_count":11,"area":null},{"id":"2404.00942","title":"Evaluating the Factuality of Large Language Models using Large-Scale Knowledge Graphs","created":"2024-04-01","cited_by_count":10,"area":null},{"id":"2410.10796","title":"Context-Parametric Inversion: Why Instruction Finetuning Can Worsen Context Reliance","created":"2024-10-14","cited_by_count":10,"area":null},{"id":"2605.02105","title":"Sharpness-Aware Pretraining Mitigates Catastrophic Forgetting","created":"2026-05-04","cited_by_count":10,"area":null},{"id":"2405.15007","title":"RE-Adapt: Reverse Engineered Adaptation of Large Language Models","created":"2024-05-23","cited_by_count":9,"area":null},{"id":"2406.14026","title":"Demystifying Language Model Forgetting with Low-rank Example Associations","created":"2024-06-20","cited_by_count":8,"area":null},{"id":"2410.09982","title":"Self-Data Distillation for Recovering Quality in Pruned Large Language Models","created":"2024-10-13","cited_by_count":8,"area":null},{"id":"2411.07175","title":"Continual Memorization of Factoids in Language Models","created":"2024-11-11","cited_by_count":8,"area":null},{"id":"2604.10079","title":"Why Supervised Fine-Tuning Fails to Learn: A Systematic Study of Incomplete Learning in Large Language Models","created":"2026-04-11","cited_by_count":8,"area":null},{"id":"2604.14090","title":"From Weights to Activations: Is Steering the Next Frontier of Adaptation?","created":"2026-04-15","cited_by_count":8,"area":null},{"id":"2408.12263","title":"Toward the Evaluation of Large Language Models Considering Score Variance across Instruction Templates","created":"2024-08-22","cited_by_count":7,"area":null},{"id":"2410.11677","title":"Understanding Likelihood Over-optimisation in Direct Alignment Algorithms","created":"2024-10-15","cited_by_count":7,"area":"alignment"},{"id":"2410.15489","title":"Generative AI Agents in Autonomous Machines: A Safety Perspective","created":"2024-10-20","cited_by_count":7,"area":null},{"id":"2509.06100","title":"Orthogonal Low-rank Adaptation in Lie Groups for Continual Learning of Large Language Models","created":"2025-09-07","cited_by_count":7,"area":null},{"id":"2605.10468","title":"Can Muon Fine-tune Adam-Pretrained Models?","created":"2026-05-11","cited_by_count":7,"area":null},{"id":"2311.08662","title":"Evaluating Concurrent Robustness of Language Models Across Diverse Challenge Sets","created":"2023-11-15","cited_by_count":6,"area":null},{"id":"2405.19265","title":"AlchemistCoder: Harmonizing and Eliciting Code Capability by Hindsight Tuning on Multi-source Data","created":"2024-05-29","cited_by_count":6,"area":null},{"id":"2502.17390","title":"Mitigating Bias in RAG: Controlling the Embedder","created":"2025-02-24","cited_by_count":6,"area":"rag"},{"id":"2605.05892","title":"Beyond Steering Vector: Flow-based Activation Steering for Inference-Time Intervention","created":"2026-05-07","cited_by_count":6,"area":"mechinterp"},{"id":"2410.12104","title":"To Err is AI : A Case Study Informing LLM Flaw Reporting Practices","created":"2024-10-15","cited_by_count":5,"area":null},{"id":"2505.12814","title":"PsyMem: Fine-grained psychological alignment and Explicit Memory Control for Advanced Role-Playing LLMs","created":"2025-05-19","cited_by_count":5,"area":null},{"id":"2506.01301","title":"Overcoming Multi-step Complexity in Multimodal Theory-of-Mind Reasoning: A Scalable Bayesian Planner","created":"2025-06-02","cited_by_count":5,"area":"lr"},{"id":"2507.21914","title":"Rote Learning Considered Useful: Generalizing over Memorized Data in LLMs","created":"2025-07-29","cited_by_count":5,"area":null},{"id":"2509.07370","title":"PersonaFuse: A Personality Activation-Driven Framework for Enhancing Human-LLM Interactions","created":"2025-09-09","cited_by_count":5,"area":null},{"id":"2510.20479","title":"RECALL: REpresentation-aligned Catastrophic-forgetting ALLeviation via Hierarchical Model Merging","created":"2025-10-23","cited_by_count":5,"area":"mechinterp"},{"id":"2510.21978","title":"Beyond Reasoning Gains: Mitigating General-Capability Forgetting in Large Reasoning Models","created":"2025-10-24","cited_by_count":5,"area":"lr"},{"id":"2404.18410","title":"Mixture-of-Instructions: Aligning Large Language Models via Mixture Prompting","created":"2024-04-29","cited_by_count":4,"area":"alignment"},{"id":"2505.13500","title":"Noise Injection Systemically Degrades Large Language Model Safety Guardrails","created":"2025-05-16","cited_by_count":4,"area":"safety"},{"id":"2603.12011","title":"Can RL Improve Generalization of LLM Agents? An Empirical Study","created":"2026-03-12","cited_by_count":4,"area":"agents"},{"id":"2605.10770","title":"DynaMiCS: Fine-tuning LLMs with Performance Constraints using Dynamic Mixtures","created":"2026-05-11","cited_by_count":4,"area":null},{"id":"2605.14967","title":"InfoSFT: Learn More and Forget Less with Information-Aware Token Weighting","created":"2026-05-14","cited_by_count":4,"area":null},{"id":"2411.11932","title":"Unveiling and Addressing Pseudo Forgetting in Large Language Models","created":"2024-11-18","cited_by_count":3,"area":null},{"id":"2412.16469","title":"Chained Tuning Leads to Biased Forgetting","created":"2024-12-21","cited_by_count":3,"area":null},{"id":"2502.06106","title":"Fine-Tuning is Subgraph Search: A New Lens on Learning Dynamics","created":"2025-02-10","cited_by_count":3,"area":"mechinterp"},{"id":"2504.21239","title":"Memorization and Knowledge Injection in Gated LLMs","created":"2025-04-30","cited_by_count":3,"area":null},{"id":"2507.09440","title":"Transformers Don't In-Context Learn Least Squares Regression","created":"2025-07-13","cited_by_count":3,"area":null},{"id":"2511.13052","title":"Learning from the Undesirable: Robust Adaptation of Language Models without Forgetting","created":"2025-11-17","cited_by_count":3,"area":null},{"id":"2601.04110","title":"Causal Data Augmentation for Robust Fine-Tuning of Tabular Foundation Models","created":"2026-01-07","cited_by_count":3,"area":null},{"id":"2602.08813","title":"Robust Policy Optimization to Prevent Catastrophic Forgetting","created":"2026-02-09","cited_by_count":3,"area":"alignment"},{"id":"2603.06610","title":"CapTrack: Multifaceted Evaluation of Forgetting in LLM Post-Training","created":"2026-02-19","cited_by_count":3,"area":null},{"id":"2606.00147","title":"RAFT: Data Refinement and Adaptive Distillation for Domain Fine-Tuning with Alleviated Forgetting","created":"2026-05-29","cited_by_count":3,"area":null},{"id":"2607.11889","title":"Scaling Point-in-Time Language Models: Enabling Economic Evaluation of Embeddings","created":"2026-04-24","cited_by_count":3,"area":null},{"id":"2503.04750","title":"AI Agents Should be Regulated Based on the Extent of Their Autonomous Operations","created":"2025-02-07","cited_by_count":2,"area":null},{"id":"2503.17811","title":"Feather-SQL: A Lightweight NL2SQL Framework with Dual-Model Collaboration Paradigm for Small Language Models","created":"2025-03-22","cited_by_count":2,"area":null},{"id":"2505.22120","title":"LoKI: Low-damage Knowledge Implanting of Large Language Models","created":"2025-05-28","cited_by_count":2,"area":null},{"id":"2508.06178","title":"Comparing Knowledge Injection Methods for LLMs in a Low-Resource Regime","created":"2025-08-08","cited_by_count":2,"area":null},{"id":"2601.21577","title":"Collaborative Parameter Learning: Mitigating Forgetting via Parameter-Level Gradient Analysis","created":"2026-01-29","cited_by_count":2,"area":null},{"id":"2605.18309","title":"Alignment Dynamics in LLM Fine-Tuning","created":"2026-05-18","cited_by_count":2,"area":"alignment"},{"id":"2606.06667","title":"The Piggyback Hypothesis of Generalization: Explaining and Mitigating Emergent Misalignment","created":"2026-06-04","cited_by_count":2,"area":null},{"id":"2606.29184","title":"BaRA: Bayesian Adaptive Rank Allocation for Parameter-Efficient Fine-Tuning","created":"2026-06-28","cited_by_count":2,"area":null},{"id":"2607.19604","title":"Scaling Laws for Hypernetwork-Based Knowledge Injection in Large Language Models","created":"2026-07-21","cited_by_count":2,"area":null},{"id":"2406.14764","title":"RE-AdaptIR: Improving Information Retrieval through Reverse Engineered Adaptation","created":"2024-06-20","cited_by_count":1,"area":null},{"id":"2505.12533","title":"Relation Extraction or Pattern Matching? Unravelling the Generalisation Limits of Language Models for Biographical RE","created":"2025-05-18","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":"2511.07070","title":"RedOne 2.0: Rethinking Domain-specific LLM Post-Training in Social Networking Services","created":"2025-11-10","cited_by_count":1,"area":"lr"},{"id":"2601.21984","title":"PowerGenie: Analytically-Guided Evolutionary Discovery of Superior Reconfigurable Power Converters","created":"2026-01-29","cited_by_count":1,"area":null},{"id":"2602.03073","title":"TMS: Trajectory-Mixed Supervision for Reward-Free, On-Policy SFT","created":"2026-02-03","cited_by_count":1,"area":"alignment"}],"next_cursor":"100"}