{"total":105,"rows":[{"id":"2310.15213","title":"Function Vectors in Large Language Models","created":"2023-10-23","cited_by_count":308,"area":null},{"id":"2402.05162","title":"Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications","created":"2024-02-07","cited_by_count":231,"area":"alignment"},{"id":"2403.17887","title":"The Unreasonable Ineffectiveness of the Deeper Layers","created":"2024-03-26","cited_by_count":226,"area":"lr"},{"id":"2309.06256","title":"Mitigating the Alignment Tax of RLHF","created":"2023-09-12","cited_by_count":183,"area":"alignment"},{"id":"2402.14811","title":"Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity Tracking","created":"2024-02-22","cited_by_count":149,"area":null},{"id":"2406.19384","title":"The Remarkable Robustness of LLMs: Stages of Inference?","created":"2024-06-27","cited_by_count":146,"area":null},{"id":"2405.07813","title":"Localizing Task Information for Improved Model Merging and Compression","created":"2024-05-13","cited_by_count":131,"area":null},{"id":"2407.08735","title":"Real-Time Anomaly Detection and Reactive Planning with Large Language Models","created":"2024-07-11","cited_by_count":68,"area":null},{"id":"2406.01563","title":"LoFiT: Localized Fine-tuning on LLM Representations","created":"2024-06-03","cited_by_count":57,"area":null},{"id":"2402.12048","title":"Model Tailor: Mitigating Catastrophic Forgetting in Multi-modal Large Language Models","created":"2024-02-19","cited_by_count":54,"area":"mllm"},{"id":"2408.13656","title":"Localize-and-Stitch: Efficient Model Merging via Sparse Task Arithmetic","created":"2024-08-24","cited_by_count":50,"area":null},{"id":"2311.16206","title":"Continual Instruction Tuning for Large Multimodal Models","created":"2023-11-27","cited_by_count":49,"area":"mllm"},{"id":"2505.11711","title":"Reinforcement Learning Finetunes Small Subnetworks in Large Language Models","created":"2025-05-16","cited_by_count":49,"area":null},{"id":"2409.01659","title":"Interpreting and Improving Large Language Models in Arithmetic Calculation","created":"2024-09-03","cited_by_count":45,"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":"2410.12949","title":"Mechanistic Unlearning: Robust Knowledge Unlearning and Editing via Mechanistic Localization","created":"2024-10-16","cited_by_count":35,"area":"safety"},{"id":"2411.02280","title":"The LLM Language Network: A Neuroscientific Approach for Identifying Causally Task-Relevant Units","created":"2024-11-04","cited_by_count":34,"area":"lr"},{"id":"2410.18210","title":"Towards Understanding the Fragility of Multilingual LLMs against Fine-Tuning Attacks","created":"2024-10-23","cited_by_count":33,"area":"safety"},{"id":"2505.10833","title":"MergeBench: A Benchmark for Merging Domain-Specialized LLMs","created":"2025-05-16","cited_by_count":33,"area":null},{"id":"2309.07418","title":"A Fast Optimization View: Reformulating Single Layer Attention in LLM Based on Tensor and SVM Trick, and Solving It in Matrix Multiplication Time","created":"2023-09-14","cited_by_count":30,"area":null},{"id":"2311.09060","title":"Do Localization Methods Actually Localize Memorized Data in LLMs? A Tale of Two Benchmarks","created":"2023-11-15","cited_by_count":29,"area":null},{"id":"2401.12200","title":"APT: Adaptive Pruning and Tuning Pretrained Language Models for Efficient Training and Inference","created":"2024-01-22","cited_by_count":29,"area":null},{"id":"2406.02913","title":"Zeroth-Order Fine-Tuning of LLMs with Extreme Sparsity","created":"2024-06-05","cited_by_count":28,"area":null},{"id":"2601.14004","title":"Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models","created":"2026-01-20","cited_by_count":27,"area":"mechinterp"},{"id":"2311.09627","title":"Mitigating Biases for Instruction-following Language Models via Bias Neurons Elimination","created":"2023-11-16","cited_by_count":23,"area":null},{"id":"2410.21804","title":"Efficient and Effective Weight-Ensembling Mixture of Experts for Multi-Task Model Merging","created":"2024-10-29","cited_by_count":23,"area":"moe"},{"id":"2409.02877","title":"Configurable Foundation Models: Building LLMs from a Modular Perspective","created":"2024-09-04","cited_by_count":22,"area":null},{"id":"2502.17601","title":"Representation Engineering for Large-Language Models: Survey and Research Challenges","created":"2025-02-24","cited_by_count":21,"area":"mechinterp"},{"id":"2412.11041","title":"Separate the Wheat from the Chaff: A Post-Hoc Approach to Safety Re-Alignment for Fine-Tuned Language Models","created":"2024-12-15","cited_by_count":20,"area":"alignment"},{"id":"2510.15103","title":"Continual Learning via Sparse Memory Finetuning","created":"2025-10-16","cited_by_count":20,"area":null},{"id":"2404.11534","title":"Decomposing and Editing Predictions by Modeling Model Computation","created":"2024-04-17","cited_by_count":19,"area":null},{"id":"2410.17875","title":"Understanding Layer Significance in LLM Alignment","created":"2024-10-23","cited_by_count":19,"area":"alignment"},{"id":"2408.09857","title":"TaSL: Continual Dialog State Tracking via Task Skill Localization and Consolidation","created":"2024-08-19","cited_by_count":18,"area":null},{"id":"2310.11685","title":"Why Softmax Attention Outperforms Linear Attention","created":"2023-10-18","cited_by_count":15,"area":null},{"id":"2404.11225","title":"In-Context Learning State Vector with Inner and Momentum Optimization","created":"2024-04-17","cited_by_count":15,"area":null},{"id":"2408.12109","title":"RoVRM: A Robust Visual Reward Model Optimized via Auxiliary Textual Preference Data","created":"2024-08-22","cited_by_count":15,"area":"mllm"},{"id":"2502.17510","title":"Recurrent Knowledge Identification and Fusion for Language Model Continual Learning","created":"2025-02-22","cited_by_count":15,"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":"2406.11828","title":"Learning sum of diverse features: computational hardness and efficient gradient-based training for ridge combinations","created":"2024-06-17","cited_by_count":13,"area":null},{"id":"2509.08255","title":"Mitigating Catastrophic Forgetting in Large Language Models with Forgetting-aware Pruning","created":"2025-09-10","cited_by_count":13,"area":null},{"id":"2310.12462","title":"Unmasking Transformers: A Theoretical Approach to Data Recovery via Attention Weights","created":"2023-10-19","cited_by_count":12,"area":null},{"id":"2311.04354","title":"Uncovering Intermediate Variables in Transformers using Circuit Probing","created":"2023-11-07","cited_by_count":12,"area":null},{"id":"2401.15207","title":"HiFT: A Hierarchical Full Parameter Fine-Tuning Strategy","created":"2024-01-26","cited_by_count":12,"area":null},{"id":"2410.14389","title":"SurgeryV2: Bridging the Gap Between Model Merging and Multi-Task Learning with Deep Representation Surgery","created":"2024-10-18","cited_by_count":12,"area":null},{"id":"2410.09016","title":"Parameter-Efficient Fine-Tuning of State Space Models","created":"2024-10-11","cited_by_count":11,"area":"ssm"},{"id":"2502.05390","title":"Learning Task Representations from In-Context Learning","created":"2025-02-08","cited_by_count":11,"area":null},{"id":"2505.18713","title":"Neural Parameter Search for Slimmer Fine-Tuned Models and Better Transfer","created":"2025-05-24","cited_by_count":11,"area":null},{"id":"2310.03843","title":"From Channel Bias to Feature Redundancy: Uncovering the \"Less is More\" Principle in Few-Shot Learning","created":"2023-10-05","cited_by_count":10,"area":null},{"id":"2403.03942","title":"The Heuristic Core: Understanding Subnetwork Generalization in Pretrained Language Models","created":"2024-03-06","cited_by_count":10,"area":null},{"id":"2410.22316","title":"Understanding Synthetic Context Extension via Retrieval Heads","created":"2024-10-29","cited_by_count":10,"area":"rag"},{"id":"2309.00244","title":"NeuroSurgeon: A Toolkit for Subnetwork Analysis","created":"2023-09-01","cited_by_count":9,"area":null},{"id":"2311.15390","title":"Local Convergence of Approximate Newton Method for Two Layer Nonlinear Regression","created":"2023-11-26","cited_by_count":9,"area":null},{"id":"2408.05200","title":"KIF: Knowledge Identification and Fusion for Language Model Continual Learning","created":"2024-08-09","cited_by_count":9,"area":null},{"id":"2410.05583","title":"NegMerge: Sign-Consensual Weight Merging for Machine Unlearning","created":"2024-10-08","cited_by_count":9,"area":"safety"},{"id":"2505.18502","title":"Knowledge Fusion of Large Language Models Via Modular SkillPacks","created":"2025-05-24","cited_by_count":8,"area":null},{"id":"2310.20051","title":"The Expressibility of Polynomial based Attention Scheme","created":"2023-10-30","cited_by_count":7,"area":null},{"id":"2404.03784","title":"A Layer Selection Approach to Test Time Adaptation","created":"2024-04-04","cited_by_count":7,"area":null},{"id":"2410.09343","title":"ELICIT: LLM Augmentation via External In-Context Capability","created":"2024-10-12","cited_by_count":7,"area":null},{"id":"2308.08358","title":"Convergence of Two-Layer Regression with Nonlinear Units","created":"2023-08-16","cited_by_count":6,"area":null},{"id":"2406.16563","title":"Are there identifiable structural parts in the sentence embedding whole?","created":"2024-06-24","cited_by_count":6,"area":null},{"id":"2407.18119","title":"Tracking linguistic information in transformer-based sentence embeddings through targeted sparsification","created":"2024-07-25","cited_by_count":6,"area":null},{"id":"2606.00831","title":"Subliminal Learning is a LoRA Artifact","created":"2026-05-30","cited_by_count":6,"area":null},{"id":"2505.17110","title":"Multi-Modality Expansion and Retention for LLMs through Parameter Merging and Decoupling","created":"2025-05-21","cited_by_count":5,"area":"mllm"},{"id":"2509.22263","title":"Erase or Hide? Suppressing Spurious Unlearning Neurons for Robust Unlearning","created":"2025-09-26","cited_by_count":5,"area":"safety"},{"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":"2403.08477","title":"Unleashing the Power of Meta-tuning for Few-shot Generalization Through Sparse Interpolated Experts","created":"2024-03-13","cited_by_count":3,"area":null},{"id":"2404.10306","title":"Balancing Speciality and Versatility: A Coarse to Fine Framework for Mitigating Catastrophic Forgetting in Large Language Models","created":"2024-04-16","cited_by_count":3,"area":"alignment"},{"id":"2502.15796","title":"Pruning as a Defense: Reducing Memorization in Large Language Models","created":"2025-02-18","cited_by_count":3,"area":null},{"id":"2506.20746","title":"Dynamic Weight Grafting: Localizing Finetuned Factual Knowledge in Transformers","created":"2025-06-25","cited_by_count":3,"area":null},{"id":"2602.01599","title":"The Multiple Ticket Hypothesis: Random Sparse Subnetworks Suffice for RLVR","created":"2026-02-02","cited_by_count":3,"area":null},{"id":"2605.20296","title":"Spectral Unforgetting: Post-Hoc Recovery of Damaged Capabilities Without Retraining","created":"2026-05-19","cited_by_count":3,"area":null},{"id":"2412.13526","title":"MOMA: Masked Orthogonal Matrix Alignment for Zero-Additional-Parameter Model Merging","created":"2024-12-18","cited_by_count":2,"area":null},{"id":"2507.17107","title":"Reinforcement Learning Fine-Tunes a Sparse Subnetwork in Large Language Models","created":"2025-07-23","cited_by_count":2,"area":"alignment"},{"id":"2511.05171","title":"Model Merging Improves Zero-Shot Generalization in Bioacoustic Foundation Models","created":"2025-11-07","cited_by_count":2,"area":null},{"id":"2602.04509","title":"Model-Dowser: Data-Free Importance Probing to Mitigate Catastrophic Forgetting in Multimodal Large Language Models","created":"2026-02-04","cited_by_count":2,"area":"mllm"},{"id":"2603.03335","title":"Compressed Sensing for Capability Localization in Large Language Models","created":"2026-02-11","cited_by_count":2,"area":"lr"},{"id":"2604.15706","title":"Target-Oriented Pretraining Data Selection via Neuron-Activated Graph","created":"2026-04-17","cited_by_count":2,"area":null},{"id":"2501.00457","title":"Differentiable Prompt Learning for Vision Language Models","created":"2024-12-31","cited_by_count":1,"area":"mllm"},{"id":"2502.11439","title":"An Efficient Sparse Fine-Tuning with Low Quantization Error via Neural Network Pruning","created":"2025-02-17","cited_by_count":1,"area":null},{"id":"2503.06734","title":"Gender Encoding Patterns in Pretrained Language Model Representations","created":"2025-03-09","cited_by_count":1,"area":null},{"id":"2505.16178","title":"Understanding Fact Recall in Language Models: Why Two-Stage Training Encourages Memorization but Mixed Training Teaches Knowledge","created":"2025-05-22","cited_by_count":1,"area":null},{"id":"2507.04487","title":"LoSiA: Efficient High-Rank Fine-Tuning via Subnet Localization and Optimization","created":"2025-07-06","cited_by_count":1,"area":null},{"id":"2509.11167","title":"Harnessing Optimization Dynamics for Curvature-Informed Model Merging","created":"2025-09-14","cited_by_count":1,"area":null},{"id":"2603.08647","title":"Grow, Don't Overwrite: Fine-tuning Without Forgetting","created":"2026-03-09","cited_by_count":1,"area":null},{"id":"2603.17823","title":"Discovering Decoupled Functional Modules in Large Language Models","created":"2026-03-18","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":"2605.18904","title":"Dynamic Model Merging Made Slim","created":"2026-05-17","cited_by_count":1,"area":null},{"id":"2605.22205","title":"Skill Weaving: Efficient LLM Improvement via Modular Skillpacks","created":"2026-05-21","cited_by_count":1,"area":null},{"id":"2606.18453","title":"LLM Parameters for Math Across Languages: Shared or Separate?","created":"2026-06-16","cited_by_count":1,"area":"lr"},{"id":"2404.11916","title":"Unplug and Play Language Models: Decomposing Experts in Language Models at Inference Time","created":"2024-04-18","cited_by_count":0,"area":null},{"id":"2405.16027","title":"Feature Protection For Out-of-distribution Generalization","created":"2024-05-25","cited_by_count":0,"area":null},{"id":"2408.01308","title":"Reconsidering Degeneration of Token Embeddings with Definitions for Encoder-based Pre-trained Language Models","created":"2024-08-02","cited_by_count":0,"area":null},{"id":"2501.07596","title":"Optimize Incompatible Parameters through Compatibility-aware Knowledge Integration","created":"2025-01-10","cited_by_count":0,"area":null},{"id":"2508.18192","title":"Unraveling the cognitive patterns of Large Language Models through module communities","created":"2025-08-25","cited_by_count":0,"area":null},{"id":"2605.05995","title":"Safety Anchor: Defending Harmful Fine-tuning via Geometric Bottlenecks","created":"2026-05-07","cited_by_count":0,"area":"alignment"},{"id":"2605.06166","title":"One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.25134","title":"Theoretical Analysis of Sparse Optimization with Reparameterization, Weight Decay, and Adaptive Learning Rate","created":"2026-05-24","cited_by_count":0,"area":null},{"id":"2605.31025","title":"TRACE: Discovering Task-Specific Parameter via Adaptation-Aware Probing for Continual Fine-Tuning","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2606.14997","title":"AI Engram: In Search of Memory Traces in Artificial Intelligence","created":"2026-06-12","cited_by_count":0,"area":null},{"id":"2606.24963","title":"Curvature-Guided Mixing for MLLM Adaptation","created":"2026-06-23","cited_by_count":0,"area":"mllm"}],"next_cursor":"100"}