{"total":91,"rows":[{"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":"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":"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":"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":"2504.04377","title":"PolyGuard: A Multilingual Safety Moderation Tool for 17 Languages","created":"2025-04-06","cited_by_count":59,"area":null},{"id":"2502.04194","title":"The Best Instruction-Tuning Data are Those That Fit","created":"2025-02-06","cited_by_count":52,"area":null},{"id":"2502.12446","title":"Multi-Attribute Steering of Language Models via Targeted Intervention","created":"2025-02-18","cited_by_count":46,"area":null},{"id":"2402.09269","title":"Personalized Large Language Models","created":"2024-02-14","cited_by_count":44,"area":null},{"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":"2505.02795","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":"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":"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":"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":"2507.04642","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":"2410.15489","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":"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":"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":"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":"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":"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":"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":"2601.21984","title":"PowerGenie: Analytically-Guided Evolutionary Discovery of Superior Reconfigurable Power Converters","created":"2026-01-29","cited_by_count":1,"area":null},{"id":"2602.03542","title":"Can Large Language Models Generalize Procedures Across Representations?","created":"2026-02-03","cited_by_count":1,"area":null},{"id":"2602.06665","title":"Not All Layers Need Tuning: Selective Layer Restoration Recovers Diversity","created":"2026-02-06","cited_by_count":1,"area":null},{"id":"2603.06905","title":"MedInjection-FR: Exploring the Role of Native, Synthetic, and Translated Data in Biomedical Instruction Tuning","created":"2026-03-06","cited_by_count":1,"area":null},{"id":"2605.12908","title":"The Mechanism of Weak-to-Strong Generalization: Feature Elicitation from Latent Knowledge","created":"2026-05-13","cited_by_count":1,"area":null},{"id":"2607.22676","title":"How LLM Task-Adaptation Reshapes Alignment: A Multi-dimensional Study of Behavioral and Representational Drift","created":"2026-07-10","cited_by_count":1,"area":null},{"id":"2608.01743","title":"Toward Plasticity-Preserving KL Regularization for Capability Retention in LLM Reinforcement Learning","created":"2026-08-03","cited_by_count":1,"area":null},{"id":"2608.30158","title":"CPR for LLMs: Critical-Point Routing against Catastrophic Forgetting in Domain Adaptation","created":"2026-08-31","cited_by_count":1,"area":null},{"id":"2502.21236","title":"Transforming Tuberculosis Care: Optimizing Large Language Models For Enhanced Clinician-Patient Communication","created":"2025-02-28","cited_by_count":0,"area":null},{"id":"2503.07550","title":"KSOD: Knowledge Supplement for LLMs On Demand","created":"2025-03-10","cited_by_count":0,"area":null},{"id":"2506.23423","title":"TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs","created":"2025-06-29","cited_by_count":0,"area":null},{"id":"2602.02708","title":"BinaryPPO: Efficient Policy Optimization for Binary Classification","created":"2026-02-02","cited_by_count":0,"area":null},{"id":"2603.11957","title":"CHiL(L)Grader: Calibrated Human-in-the-Loop Short-Answer Grading","created":"2026-03-12","cited_by_count":0,"area":null},{"id":"2604.00324","title":"The Persistent Vulnerability of Aligned AI Systems","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2604.15460","title":"The Crutch or the Ceiling? How Different Generations of LLMs Shape EFL Student Writings","created":"2026-04-16","cited_by_count":0,"area":null},{"id":"2606.00132","title":"Foundation-Preserving Optimization in Generalized Eigenspace","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2606.01967","title":"Training Prompt Matters: State-Adaptive Optimization for Robust Fine-Tuning","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2606.26102","title":"Helpfulness Hurts: Domain-Dependent Degradation of Mid-Trained Compassion Values Under Post-Training","created":"2026-04-30","cited_by_count":0,"area":null},{"id":"2606.30258","title":"KnowsTFM: Knowledge-Informed Fine-Tuning of Small Tabular Foundation Models","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2607.11020","title":"Can a Language Model Learn Facts Continually in Its Weights?","created":"2026-07-13","cited_by_count":0,"area":null},{"id":"2608.20794","title":"Knowing but Not Saying: Preventing Factual Access Failures in LLM SFT via Recall-Anchored Distillation","created":"2026-08-21","cited_by_count":0,"area":null},{"id":"2609.01573","title":"Scaling Near-Optimal SFT-RL Annotation Budget Allocation from Small to Large LLMs","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.11291","title":"Off-Target Effects of Response-Style Alignment in a Korean 27B Language Model","created":"2026-09-10","cited_by_count":0,"area":null},{"id":"2609.13680","title":"Drift-Constrained Optimization: Only Direction Matters in Fine-Tuning Instruct Models","created":"2026-09-12","cited_by_count":0,"area":null},{"id":"2609.14652","title":"Natural Language Knowledge Graph Query Execution: Leveraging Controlled Semantics in the LLM Context Window","created":"2026-09-13","cited_by_count":0,"area":null},{"id":"2609.18560","title":"The evolution of sex for artificial intelligence: a population-genetic framework for multigenerational model populations","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2609.27248","title":"Repurposing Pre-trained LLMs as High Fidelity Continuous Text Autoencoders","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2609.33559","title":"Fine Until Fine-Tuned: Repeated Solutions Make Reasoning Fragile","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2610.12995","title":"What Should SFT Learn? Conditional Information Gain for Generalizable Post-Training","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}