{"total":245,"rows":[{"id":"2502.21074","title":"CODI: Compressing Chain-of-Thought into Continuous Space via Self-Distillation","created":"2025-02-28","cited_by_count":225,"area":"lr"},{"id":"2501.17148","title":"AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders","created":"2025-01-28","cited_by_count":218,"area":"mechinterp"},{"id":"2404.03592","title":"ReFT: Representation Finetuning for Language Models","created":"2024-04-04","cited_by_count":197,"area":null},{"id":"2410.12877","title":"Improving Instruction-Following in Language Models through Activation Steering","created":"2024-10-15","cited_by_count":160,"area":"mechinterp"},{"id":"2405.20003","title":"Kernel Language Entropy: Fine-grained Uncertainty Quantification for LLMs from Semantic Similarities","created":"2024-05-30","cited_by_count":159,"area":null},{"id":"2507.03724","title":"MemOS: A Memory OS for AI System","created":"2025-07-04","cited_by_count":138,"area":"rag"},{"id":"2406.02630","title":"AI Agents Under Threat: A Survey of Key Security Challenges and Future Pathways","created":"2024-06-04","cited_by_count":127,"area":null},{"id":"2406.00045","title":"Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization","created":"2024-05-28","cited_by_count":118,"area":"alignment"},{"id":"2411.11296","title":"Steering Language Model Refusal with Sparse Autoencoders","created":"2024-11-18","cited_by_count":95,"area":"mechinterp"},{"id":"2505.21523","title":"More Thinking, Less Seeing? Assessing Amplified Hallucination in Multimodal Reasoning Models","created":"2025-05-23","cited_by_count":86,"area":"lr"},{"id":"2505.20063","title":"SAEs Are Good for Steering -- If You Select the Right Features","created":"2025-05-26","cited_by_count":78,"area":"mechinterp"},{"id":"2410.04343","title":"Inference Scaling for Long-Context Retrieval Augmented Generation","created":"2024-10-06","cited_by_count":65,"area":"rag"},{"id":"2406.05954","title":"Aligning Large Language Models with Representation Editing: A Control Perspective","created":"2024-06-10","cited_by_count":64,"area":"alignment"},{"id":"2410.12299","title":"Semantics-Adaptive Activation Intervention for LLMs via Dynamic Steering Vectors","created":"2024-10-16","cited_by_count":63,"area":"mechinterp"},{"id":"2410.15999","title":"Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering","created":"2024-10-21","cited_by_count":63,"area":"mechinterp"},{"id":"2410.15778","title":"Reducing Hallucinations in Vision-Language Models via Latent Space Steering","created":"2024-10-21","cited_by_count":59,"area":"mllm"},{"id":"2404.07544","title":"From Words to Numbers: Your Large Language Model Is Secretly A Capable Regressor When Given In-Context Examples","created":"2024-04-11","cited_by_count":57,"area":null},{"id":"2405.09719","title":"Spectral Editing of Activations for Large Language Model Alignment","created":"2024-05-15","cited_by_count":56,"area":"alignment"},{"id":"2408.11491","title":"SCANS: Mitigating the Exaggerated Safety for LLMs via Safety-Conscious Activation Steering","created":"2024-08-21","cited_by_count":50,"area":"alignment"},{"id":"2502.02716","title":"A Unified Understanding and Evaluation of Steering Methods","created":"2025-02-04","cited_by_count":46,"area":"mechinterp"},{"id":"2502.12446","title":"Multi-Attribute Steering of Language Models via Targeted Intervention","created":"2025-02-18","cited_by_count":46,"area":null},{"id":"2507.16003","title":"Learning without training: The implicit dynamics of in-context learning","created":"2025-07-21","cited_by_count":43,"area":null},{"id":"2406.12094","title":"Who's asking? User personas and the mechanics of latent misalignment","created":"2024-06-17","cited_by_count":40,"area":"safety"},{"id":"2501.02497","title":"A Survey of Test-Time Compute: From Intuitive Inference to Deliberate Reasoning","created":"2025-01-05","cited_by_count":40,"area":"lr"},{"id":"2406.17563","title":"Multi-property Steering of Large Language Models with Dynamic Activation Composition","created":"2024-06-25","cited_by_count":39,"area":"mechinterp"},{"id":"2504.10957","title":"When is Task Vector Provably Effective for Model Editing? A Generalization Analysis of Nonlinear Transformers","created":"2025-04-15","cited_by_count":38,"area":"safety"},{"id":"2504.04633","title":"M$^2$IV: Towards Efficient and Fine-grained Multimodal In-Context Learning via Representation Engineering","created":"2025-04-06","cited_by_count":35,"area":"mllm"},{"id":"2502.17516","title":"A Survey on Mechanistic Interpretability for Multi-Modal Foundation Models","created":"2025-02-22","cited_by_count":34,"area":"mllm"},{"id":"2503.05213","title":"Personalized Text Generation with Contrastive Activation Steering","created":"2025-03-07","cited_by_count":34,"area":"mechinterp"},{"id":"2505.20977","title":"Evaluating and Steering Modality Preferences in Multimodal Large Language Model","created":"2025-05-27","cited_by_count":33,"area":"mllm"},{"id":"2406.11801","title":"Safety Arithmetic: A Framework for Test-time Safety Alignment of Language Models by Steering Parameters and Activations","created":"2024-06-17","cited_by_count":32,"area":"alignment"},{"id":"2403.02990","title":"Data Augmentation using Large Language Models: Data Perspectives, Learning Paradigms and Challenges","created":"2024-03-05","cited_by_count":30,"area":null},{"id":"2504.01550","title":"Representation Bending for Large Language Model Safety","created":"2025-04-02","cited_by_count":30,"area":"safety"},{"id":"2502.18862","title":"One-shot Optimized Steering Vectors Mediate Safety-relevant Behaviors in LLMs","created":"2025-02-26","cited_by_count":29,"area":"mechinterp"},{"id":"2401.16332","title":"Tradeoffs Between Alignment and Helpfulness in Language Models with Steering Methods","created":"2024-01-29","cited_by_count":28,"area":"alignment"},{"id":"2510.09719","title":"ICL-Router: In-Context Learned Model Representations for LLM Routing","created":"2025-10-10","cited_by_count":28,"area":null},{"id":"2410.00153","title":"Beyond Single Concept Vector: Modeling Concept Subspace in LLMs with Gaussian Distribution","created":"2024-09-30","cited_by_count":27,"area":null},{"id":"2404.05729","title":"Finding Visual Task Vectors","created":"2024-04-08","cited_by_count":24,"area":null},{"id":"2410.02298","title":"Jailbreak Antidote: Runtime Safety-Utility Balance via Sparse Representation Adjustment in Large Language Models","created":"2024-10-03","cited_by_count":23,"area":"safety"},{"id":"2504.19483","title":"Improving Reasoning Performance in Large Language Models via Representation Engineering","created":"2025-04-28","cited_by_count":23,"area":"lr"},{"id":"2409.02877","title":"Configurable Foundation Models: Building LLMs from a Modular Perspective","created":"2024-09-04","cited_by_count":22,"area":null},{"id":"2402.02160","title":"Data Poisoning for In-context Learning","created":"2024-02-03","cited_by_count":21,"area":"safety"},{"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":"2505.20809","title":"Improved Representation Steering for Language Models","created":"2025-05-27","cited_by_count":21,"area":"mechinterp"},{"id":"2602.08169","title":"Spherical Steering: Geometry-Aware Activation Rotation for Language Models","created":"2026-02-09","cited_by_count":21,"area":null},{"id":"2406.04331","title":"PaCE: Parsimonious Concept Engineering for Large Language Models","created":"2024-06-06","cited_by_count":19,"area":null},{"id":"2411.08790","title":"Can sparse autoencoders be used to decompose and interpret steering vectors?","created":"2024-11-13","cited_by_count":19,"area":"mechinterp"},{"id":"2509.01321","title":"Towards High Data Efficiency in Reinforcement Learning with Verifiable Reward","created":"2025-09-01","cited_by_count":19,"area":"lr"},{"id":"2402.19465","title":"Towards Tracing Trustworthiness Dynamics: Revisiting Pre-training Period of Large Language Models","created":"2024-02-29","cited_by_count":18,"area":null},{"id":"2410.01174","title":"Towards Inference-time Category-wise Safety Steering for Large Language Models","created":"2024-10-02","cited_by_count":18,"area":"alignment"},{"id":"2507.09709","title":"Large Language Models Encode Semantics and Alignment in Linearly Separable Representations","created":"2025-07-13","cited_by_count":17,"area":"safety"},{"id":"2507.13255","title":"Automating Steering for Safe Multimodal Large Language Models","created":"2025-07-17","cited_by_count":17,"area":"lr"},{"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":"2406.03631","title":"Discovering Bias in Latent Space: An Unsupervised Debiasing Approach","created":"2024-06-05","cited_by_count":15,"area":null},{"id":"2410.22330","title":"Vision-Language Models Create Cross-Modal Task Representations","created":"2024-10-29","cited_by_count":15,"area":"mllm"},{"id":"2501.18532","title":"Differentially Private Steering for Large Language Model Alignment","created":"2025-01-30","cited_by_count":15,"area":"alignment"},{"id":"2502.02958","title":"Position: Editing Large Language Models Poses Serious Safety Risks","created":"2025-02-05","cited_by_count":15,"area":null},{"id":"2402.02212","title":"A Survey to Recent Progress Towards Understanding In-Context Learning","created":"2024-02-03","cited_by_count":14,"area":null},{"id":"2409.14026","title":"Uncovering Latent Chain of Thought Vectors in Language Models","created":"2024-09-21","cited_by_count":14,"area":"lr"},{"id":"2410.05603","title":"Everything Everywhere All at Once: LLMs can In-Context Learn Multiple Tasks in Superposition","created":"2024-10-08","cited_by_count":14,"area":"mechinterp"},{"id":"2411.07213","title":"Comparing Bottom-Up and Top-Down Steering Approaches on In-Context Learning Tasks","created":"2024-11-11","cited_by_count":14,"area":null},{"id":"2602.01654","title":"Steering Vector Fields for Context-Aware Inference-Time Control in Large Language Models","created":"2026-02-02","cited_by_count":13,"area":"mechinterp"},{"id":"2406.15609","title":"Automated radiotherapy treatment planning guided by GPT-4Vision","created":"2024-06-21","cited_by_count":12,"area":null},{"id":"2504.08851","title":"Mimic In-Context Learning for Multimodal Tasks","created":"2025-04-11","cited_by_count":12,"area":"mllm"},{"id":"2601.08331","title":"CLaS-Bench: A Cross-Lingual Alignment and Steering Benchmark","created":"2026-01-13","cited_by_count":12,"area":null},{"id":"2401.02575","title":"Large Language Models for Social Networks: Applications, Challenges, and Solutions","created":"2024-01-04","cited_by_count":11,"area":null},{"id":"2502.05390","title":"Learning Task Representations from In-Context Learning","created":"2025-02-08","cited_by_count":11,"area":null},{"id":"2507.02503","title":"Continual Gradient Low-Rank Projection Fine-Tuning for LLMs","created":"2025-07-03","cited_by_count":11,"area":null},{"id":"2508.13650","title":"CRISP: Persistent Concept Unlearning via Sparse Autoencoders","created":"2025-08-19","cited_by_count":11,"area":"safety"},{"id":"2602.15293","title":"The Information Geometry of Softmax: Probing and Steering","created":"2026-02-17","cited_by_count":11,"area":null},{"id":"2504.02181","title":"A Survey of Scaling in Large Language Model Reasoning","created":"2025-04-02","cited_by_count":10,"area":"lr"},{"id":"2506.04250","title":"SafeSteer: Interpretable Safety Steering with Refusal-Evasion in LLMs","created":"2025-06-01","cited_by_count":10,"area":"mechinterp"},{"id":"2506.19382","title":"Measuring and Guiding Monosemanticity","created":"2025-06-24","cited_by_count":10,"area":"mechinterp"},{"id":"2510.01243","title":"Detoxifying Large Language Models via Autoregressive Reward Guided Representation Editing","created":"2025-09-24","cited_by_count":10,"area":"alignment"},{"id":"2510.03659","title":"Does higher interpretability imply better utility? A Pairwise Analysis on Sparse Autoencoders","created":"2025-10-04","cited_by_count":10,"area":"mechinterp"},{"id":"2510.04491","title":"Impatient Users Confuse AI Agents: High-fidelity Simulations of Human Traits for Testing Agents","created":"2025-10-06","cited_by_count":10,"area":null},{"id":"2510.04560","title":"ContextNav: Towards Agentic Multimodal In-Context Learning","created":"2025-10-06","cited_by_count":10,"area":"mllm"},{"id":"2410.10074","title":"Divide, Reweight, and Conquer: A Logit Arithmetic Approach for In-Context Learning","created":"2024-10-14","cited_by_count":9,"area":null},{"id":"2505.15038","title":"Denoising Concept Vectors with Sparse Autoencoders for Improved Language Model Steering","created":"2025-05-21","cited_by_count":9,"area":"mechinterp"},{"id":"2506.09048","title":"Understanding Task Vectors in In-Context Learning: Emergence, Functionality, and Limitations","created":"2025-06-10","cited_by_count":9,"area":null},{"id":"2507.01321","title":"ICLShield: Exploring and Mitigating In-Context Learning Backdoor Attacks","created":"2025-07-02","cited_by_count":9,"area":"safety"},{"id":"2410.22888","title":"Effective and Efficient Adversarial Detection for Vision-Language Models via A Single Vector","created":"2024-10-30","cited_by_count":8,"area":"mllm"},{"id":"2503.21902","title":"OntoAligner: A Comprehensive Modular and Robust Python Toolkit for Ontology Alignment","created":"2025-03-27","cited_by_count":8,"area":null},{"id":"2505.12826","title":"Mitigating Hallucination in VideoLLMs via Temporal-Aware Activation Engineering","created":"2025-05-19","cited_by_count":8,"area":"mllm"},{"id":"2507.06445","title":"Can Interpretation Predict Behavior on Unseen Data?","created":"2025-07-08","cited_by_count":8,"area":null},{"id":"2508.17621","title":"Steering When Necessary: Flexible Steering Large Language Models with Backtracking","created":"2025-08-25","cited_by_count":8,"area":"mechinterp"},{"id":"2509.06608","title":"Small Vectors, Big Effects: A Mechanistic Study of RL-Induced Reasoning via Steering Vectors","created":"2025-09-08","cited_by_count":8,"area":"lr"},{"id":"2509.22854","title":"Train Once, Reuse Everywhere: Generalizable Implicit In-Context Learning by Routing Attention","created":"2025-09-26","cited_by_count":8,"area":null},{"id":"2510.22851","title":"Semantic Surgery: Zero-Shot Concept Erasure in Diffusion Models","created":"2025-10-26","cited_by_count":8,"area":"diffusion"},{"id":"2511.05562","title":"Effective Test-Time Scaling of Discrete Diffusion through Iterative Refinement","created":"2025-11-04","cited_by_count":8,"area":"lr"},{"id":"2602.00333","title":"Efficient and accurate steering of Large Language Models through attention-guided feature learning","created":"2026-01-30","cited_by_count":8,"area":null},{"id":"2603.06495","title":"COLD-Steer: Steering Large Language Models via In-Context One-step Learning Dynamics","created":"2026-03-06","cited_by_count":8,"area":"mechinterp"},{"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":"2410.09343","title":"ELICIT: LLM Augmentation via External In-Context Capability","created":"2024-10-12","cited_by_count":7,"area":null},{"id":"2503.02989","title":"Effectively Steer LLM To Follow Preference via Building Confident Directions","created":"2025-03-04","cited_by_count":7,"area":"alignment"},{"id":"2506.00653","title":"Linear Representation Transferability Hypothesis: Leveraging Small Models to Steer Large Models","created":"2025-05-31","cited_by_count":7,"area":null},{"id":"2509.07983","title":"Steering Protein Language Models","created":"2025-07-01","cited_by_count":7,"area":null},{"id":"2601.22873","title":"EmoShift: Lightweight Activation Steering for Enhanced Emotion-Aware Speech Synthesis","created":"2026-01-30","cited_by_count":7,"area":"mechinterp"},{"id":"2406.13131","title":"When Parts Are Greater Than Sums: Individual LLM Components Can Outperform Full Models","created":"2024-06-19","cited_by_count":6,"area":null},{"id":"2502.04075","title":"From Rational Answers to Emotional Resonance: The Role of Controllable Emotion Generation in Language Models","created":"2025-02-06","cited_by_count":6,"area":null}],"next_cursor":"100"}