{"total":70,"rows":[{"id":"2409.05907","title":"Programming Refusal with Conditional Activation Steering","created":"2024-09-06","cited_by_count":206,"area":"mechinterp"},{"id":"2507.03724","title":"MemOS: A Memory OS for AI System","created":"2025-07-04","cited_by_count":138,"area":"rag"},{"id":"2410.03642","title":"Aligning LLMs with Individual Preferences via Interaction","created":"2024-10-04","cited_by_count":63,"area":"alignment"},{"id":"2411.16721","title":"Steering Away from Harm: An Adaptive Approach to Defending Vision Language Model Against Jailbreaks","created":"2024-11-23","cited_by_count":48,"area":"mllm"},{"id":"2310.01779","title":"HallE-Control: Controlling Object Hallucination in Large Multimodal Models","created":"2023-10-03","cited_by_count":32,"area":"mllm"},{"id":"2408.09429","title":"Reefknot: A Comprehensive Benchmark for Relation Hallucination Evaluation, Analysis and Mitigation in Multimodal Large Language Models","created":"2024-08-18","cited_by_count":30,"area":"mllm"},{"id":"2502.01042","title":"SafeSwitch: Steering Unsafe LLM Behavior via Internal Activation Signals","created":"2025-02-03","cited_by_count":29,"area":"safety"},{"id":"2505.16188","title":"SAE-SSV: Supervised Steering in Sparse Representation Spaces for Reliable Control of Language Models","created":"2025-05-22","cited_by_count":29,"area":"mechinterp"},{"id":"2411.12405","title":"Evaluating the Prompt Steerability of Large Language Models","created":"2024-11-19","cited_by_count":27,"area":null},{"id":"2509.09660","title":"Steering MoE LLMs via Expert (De)Activation","created":"2025-09-11","cited_by_count":26,"area":"moe"},{"id":"2402.11452","title":"AutoPRM: Automating Procedural Supervision for Multi-Step Reasoning via Controllable Question Decomposition","created":"2024-02-18","cited_by_count":24,"area":"lr"},{"id":"2505.20322","title":"Beyond Prompt Engineering: Robust Behavior Control in LLMs via Steering Target Atoms","created":"2025-05-23","cited_by_count":24,"area":null},{"id":"2507.13255","title":"Automating Steering for Safe Multimodal Large Language Models","created":"2025-07-17","cited_by_count":17,"area":"lr"},{"id":"2505.23559","title":"SafeScientist: Toward Risk-Aware Scientific Discoveries by LLM Agents","created":"2025-05-29","cited_by_count":16,"area":"agents"},{"id":"2503.01048","title":"Personalize Your LLM: Fake it then Align it","created":"2025-03-02","cited_by_count":15,"area":"alignment"},{"id":"2509.25175","title":"EasySteer: A Unified Framework for High-Performance and Extensible LLM Steering","created":"2025-09-29","cited_by_count":13,"area":null},{"id":"2504.10823","title":"CLASH: Evaluating Language Models on Judging High-Stakes Dilemmas from Multiple Perspectives","created":"2025-04-15","cited_by_count":10,"area":null},{"id":"2602.20708","title":"ICON: Indirect Prompt Injection Defense for Agents based on Inference-Time Correction","created":"2026-02-24","cited_by_count":10,"area":"agents"},{"id":"2409.18997","title":"PropaInsight: Toward Deeper Understanding of Propaganda in Terms of Techniques, Appeals, and Intent","created":"2024-09-19","cited_by_count":9,"area":null},{"id":"2503.23306","title":"Focus Directions Make Your Language Models Pay More Attention to Relevant Contexts","created":"2025-03-30","cited_by_count":9,"area":null},{"id":"2505.14536","title":"Breaking Bad Tokens: Detoxification of LLMs Using Sparse Autoencoders","created":"2025-05-20","cited_by_count":9,"area":"mechinterp"},{"id":"2602.02343","title":"Why Steering Works: Toward a Unified View of Language Model Parameter Dynamics","created":"2026-02-02","cited_by_count":9,"area":null},{"id":"2405.00711","title":"Fake Artificial Intelligence Generated Contents (FAIGC): A Survey of Theories, Detection Methods, and Opportunities","created":"2024-04-25","cited_by_count":8,"area":"diffusion"},{"id":"2504.20500","title":"UniDetox: Universal Detoxification of Large Language Models via Dataset Distillation","created":"2025-04-29","cited_by_count":8,"area":null},{"id":"2504.15133","title":"EasyEdit2: An Easy-to-use Steering Framework for Editing Large Language Models","created":"2025-04-21","cited_by_count":7,"area":"mechinterp"},{"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":"2602.04428","title":"Fine-Grained Activation Steering: Steering Less, Achieving More","created":"2026-02-04","cited_by_count":7,"area":"mechinterp"},{"id":"2411.05036","title":"From Word Vectors to Multimodal Embeddings: Techniques, Applications, and Future Directions For Large Language Models","created":"2024-11-06","cited_by_count":6,"area":null},{"id":"2506.00304","title":"Can LLMs Understand Unvoiced Speech? Exploring EMG-to-Text Conversion with LLMs","created":"2025-05-30","cited_by_count":6,"area":null},{"id":"2602.12418","title":"Sparse Autoencoders are Capable LLM Jailbreak Mitigators","created":"2026-02-12","cited_by_count":6,"area":"safety"},{"id":"2410.22944","title":"Focus On This, Not That! Steering LLMs with Adaptive Feature Specification","created":"2024-10-30","cited_by_count":5,"area":null},{"id":"2503.15117","title":"Exploring Model Editing for LLM-based Aspect-Based Sentiment Classification","created":"2025-03-19","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":"2508.19720","title":"Continuously Steering LLMs Sensitivity to Contextual Knowledge with Proxy Models","created":"2025-08-27","cited_by_count":5,"area":null},{"id":"2511.02919","title":"Cache Mechanism for Agent RAG Systems","created":"2025-11-04","cited_by_count":5,"area":"rag"},{"id":"2512.23988","title":"Fantastic Reasoning Behaviors and Where to Find Them: Unsupervised Discovery of the Reasoning Process","created":"2025-12-30","cited_by_count":5,"area":"lr"},{"id":"2601.05062","title":"Compositional Steering of Large Language Models with Steering Tokens","created":"2026-01-08","cited_by_count":5,"area":null},{"id":"2310.20633","title":"Defining a New NLP Playground","created":"2023-10-31","cited_by_count":4,"area":null},{"id":"2505.06262","title":"Dialz: A Python Toolkit for Steering Vectors","created":"2025-05-04","cited_by_count":4,"area":"mechinterp"},{"id":"2506.06686","title":"Learning Distribution-Wise Control in Representation Space for Language Models","created":"2025-06-07","cited_by_count":4,"area":null},{"id":"2404.07117","title":"Continuous Language Model Interpolation for Dynamic and Controllable Text Generation","created":"2024-04-10","cited_by_count":3,"area":null},{"id":"2412.14626","title":"LDC: Learning to Generate Research Idea with Dynamic Control","created":"2024-12-19","cited_by_count":3,"area":null},{"id":"2511.20892","title":"Representation Interventions Enable Lifelong Knowledge Memory Control in LLMs","created":"2025-11-25","cited_by_count":3,"area":null},{"id":"2603.01227","title":"The Lattice Representation Hypothesis of Large Language Models","created":"2026-03-01","cited_by_count":3,"area":null},{"id":"2604.14602","title":"CausalDetox: Causal Head Selection and Intervention for Language Model Detoxification","created":"2026-04-16","cited_by_count":3,"area":null},{"id":"2502.11380","title":"From the New World of Word Embeddings: A Comparative Study of Small-World Lexico-Semantic Networks in LLMs","created":"2025-02-17","cited_by_count":2,"area":null},{"id":"2503.16334","title":"LLM Braces: Straightening Out LLM Predictions with Relevant Sub-Updates","created":"2025-03-20","cited_by_count":2,"area":null},{"id":"2505.18562","title":"From Word to World: Evaluate and Mitigate Culture Bias in LLMs via Word Association Test","created":"2025-05-24","cited_by_count":2,"area":null},{"id":"2505.22664","title":"Zero-Shot Vision Encoder Grafting via LLM Surrogates","created":"2025-05-28","cited_by_count":2,"area":"mllm"},{"id":"2508.04530","title":"Balancing Stylization and Truth via Disentangled Representation Steering","created":"2025-08-06","cited_by_count":2,"area":"mechinterp"},{"id":"2508.06065","title":"ThematicPlane: Bridging Tacit User Intent and Latent Spaces for Image Generation","created":"2025-08-08","cited_by_count":2,"area":null},{"id":"2509.15759","title":"On Optimal Steering to Achieve Exact Fairness","created":"2025-09-19","cited_by_count":2,"area":"mechinterp"},{"id":"2510.26200","title":"Don't Let It Fade: Preserving Edits in Diffusion Language Models via Token Timestep Allocation","created":"2025-10-30","cited_by_count":2,"area":"diffusion"},{"id":"2602.02498","title":"Test-Time Detoxification without Training or Learning Anything","created":"2026-01-14","cited_by_count":2,"area":null},{"id":"2602.03402","title":"Risk Awareness Injection: Calibrating Vision-Language Models for Safety without Compromising Utility","created":"2026-02-03","cited_by_count":2,"area":"lr"},{"id":"2410.02284","title":"Correlation and Navigation in the Vocabulary Key Representation Space of Language Models","created":"2024-10-03","cited_by_count":1,"area":null},{"id":"2502.18644","title":"Steered Generation via Gradient Descent on Sparse Features","created":"2025-02-25","cited_by_count":1,"area":null},{"id":"2505.19528","title":"AmpleHate: Amplifying the Attention for Versatile Implicit Hate Detection","created":"2025-05-26","cited_by_count":1,"area":null},{"id":"2511.20233","title":"REFLEX: Self-Refining Explainable Fact-Checking via Verdict-Anchored Style Control","created":"2025-11-25","cited_by_count":1,"area":null},{"id":"2512.18554","title":"Enhancing Medical Large Vision-Language Models via Alignment Distillation","created":"2025-12-21","cited_by_count":1,"area":"mllm"},{"id":"2601.12758","title":"VISPA: Pluralistic Alignment via Automatic Value Selection and Activation","created":"2026-01-19","cited_by_count":1,"area":"alignment"},{"id":"2604.06263","title":"Incentive-Aware Multi-Fidelity Optimization for Generative Advertising in Large Language Models","created":"2026-04-07","cited_by_count":1,"area":null},{"id":"2604.25580","title":"Bye Bye Perspective API: Lessons for Building and Governing Measurement Infrastructure","created":"2026-04-28","cited_by_count":1,"area":null},{"id":"2311.15642","title":"InfoPattern: Unveiling Information Propagation Patterns in Social Media","created":"2023-11-27","cited_by_count":0,"area":null},{"id":"2602.22351","title":"Decoder-based Sense Knowledge Distillation","created":"2026-02-25","cited_by_count":0,"area":"distill"},{"id":"2604.19124","title":"Detoxification for LLM: From Dataset Itself","created":"2026-04-21","cited_by_count":0,"area":null},{"id":"2605.23040","title":"Steered Generation via Gradient-Based Optimization on Sparse Query Features","created":"2026-05-21","cited_by_count":0,"area":"mechinterp"},{"id":"2607.26017","title":"UniMem: Complementary Episodic-to-Parametric Memory for Boundary-Agnostic Task Streams","created":"2026-07-28","cited_by_count":0,"area":"agents"},{"id":"2608.13538","title":"SAEVerbalizer: Generating Explanations for Sparse Autoencoder Features via Representation Verbalization","created":"2026-08-13","cited_by_count":0,"area":"mechinterp"},{"id":"2608.23124","title":"LITERARYBIGFIVE: Author-Personalized Text Generation in a Unified Interpretable Space","created":"2026-08-24","cited_by_count":0,"area":null}],"next_cursor":null}