Steering Frozen LLMs: Adaptive Social Alignment via Online Prompt Routing

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Zeyu, Dai, Xiangxiang, Han, Ziyi, Liu, Xutong, Lui, John C. S.
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

HiLoRA: Adaptive Hierarchical LoRA Routing for Training-Free Domain Generalization
by: Han, Ziyi, et al.
Published: (2025)

Cost-Effective Online Multi-LLM Selection with Versatile Reward Models
by: Dai, Xiangxiang, et al.
Published: (2024)

Demystifying Online Clustering of Bandits: Enhanced Exploration Under Stochastic and Smoothed Adversarial Contexts
by: Li, Zhuohua, et al.
Published: (2025)

Faster, Smaller, and Smarter: Task-Aware Expert Merging for Online MoE Inference
by: Han, Ziyi, et al.
Published: (2025)

Leveraging the Power of Conversations: Optimal Key Term Selection in Conversational Contextual Bandits
by: Liu, Maoli, et al.
Published: (2025)

AxiomVision: Accuracy-Guaranteed Adaptive Visual Model Selection for Perspective-Aware Video Analytics
by: Dai, Xiangxiang, et al.
Published: (2024)

A Unified Online-Offline Framework for Co-Branding Campaign Recommendations
by: Dai, Xiangxiang, et al.
Published: (2025)

Batch-Size Independent Regret Bounds for Combinatorial Semi-Bandits with Probabilistically Triggered Arms or Independent Arms
by: Liu, Xutong, et al.
Published: (2022)

Contextual Combinatorial Bandits with Probabilistically Triggered Arms
by: Liu, Xutong, et al.
Published: (2023)

Fusing Reward and Dueling Feedback in Stochastic Bandits
by: Wang, Xuchuang, et al.
Published: (2025)

Federated Contextual Cascading Bandits with Asynchronous Communication and Heterogeneous Users
by: Yang, Hantao, et al.
Published: (2024)

Online Clustering of Dueling Bandits
by: Wang, Zhiyong, et al.
Published: (2025)

Self-Exploring Language Models: Active Preference Elicitation for Online Alignment
by: Zhang, Shenao, et al.
Published: (2024)

Steering LLMs via Scalable Interactive Oversight
by: Zhou, Enyu, et al.
Published: (2026)

Combinatorial Logistic Bandits
by: Liu, Xutong, et al.
Published: (2024)

Sysformer: Safeguarding Frozen Large Language Models with Adaptive System Prompts
by: Sharma, Kartik, et al.
Published: (2025)

CAP: Controllable Alignment Prompting for Unlearning in LLMs
by: Wang, Zhaokun, et al.
Published: (2026)

Near-Optimal Online Deployment and Routing for Streaming LLMs
by: Li, Shaoang, et al.
Published: (2025)

Focus On This, Not That! Steering LLMs with Adaptive Feature Specification
by: Lamb, Tom A., et al.
Published: (2024)

Memory Inception: Latent-Space KV Cache Manipulation for Steering LLMs
by: Liu, Andy Zeyi, et al.
Published: (2026)

Prompt Learning for Generalized Vehicle Routing
by: Liu, Fei, et al.
Published: (2024)

Whispering to a Blackbox: Bootstrapping Frozen OCR with Visual Prompts
by: Samandarov, Samandar, et al.
Published: (2026)

Provably Mitigating Corruption, Overoptimization, and Verbosity Simultaneously in Offline and Online RLHF/DPO Alignment
by: Chen, Ziyi, et al.
Published: (2025)

Trained Persistent Memory for Frozen Decoder-Only LLMs
by: Jeong, Hong
Published: (2026)

TARo: Token-level Adaptive Routing for LLM Test-time Alignment
by: Rai, Arushi, et al.
Published: (2026)

Enhancing Prompt Injection Attacks to LLMs via Poisoning Alignment
by: Shao, Zedian, et al.
Published: (2024)

Sample Efficient Preference Alignment in LLMs via Active Exploration
by: Mehta, Viraj, et al.
Published: (2023)

FedConPE: Efficient Federated Conversational Bandits with Heterogeneous Clients
by: Li, Zhuohua, et al.
Published: (2024)

Beyond Experience Retrieval: Learning to Generate Utility-Optimized Structured Experience for Frozen LLMs
by: Li, Xuancheng, et al.
Published: (2026)

Enhancing Instruction Following of LLMs via Activation Steering with Dynamic Rejection
by: Kang, Minjae, et al.
Published: (2026)

Steer2Adapt: Dynamically Composing Steering Vectors Elicits Efficient Adaptation of LLMs
by: Han, Pengrui, et al.
Published: (2026)

Scalable Prompt Routing via Fine-Grained Latent Task Discovery
by: Zhang, Yunyi, et al.
Published: (2026)

Steer Like the LLM: Activation Steering that Mimics Prompting
by: Heyman, Geert, et al.
Published: (2026)

Multi-Value Alignment for LLMs via Value Decorrelation and Extrapolation
by: Xu, Hefei, et al.
Published: (2025)

RoBoN: Routed Online Best-of-n for Test-Time Scaling with Multiple LLMs
by: Geuter, Jonathan, et al.
Published: (2025)

Adaptive Online Mirror Descent for Tchebycheff Scalarization in Multi-Objective Learning
by: Liu, Meitong, et al.
Published: (2024)

Trained Persistent Memory for Frozen Encoder--Decoder LLMs: Six Architectural Methods
by: Jeong, Hong
Published: (2026)

COGNOS: Universal Enhancement for Time Series Anomaly Detection via Constrained Gaussian-Noise Optimization and Smoothing
by: Shang, Wenlong, et al.
Published: (2025)

APPA: Adaptive Preference Pluralistic Alignment for Fair Federated RLHF of LLMs
by: Srewa, Mahmoud, et al.
Published: (2026)

Semantic Caching for Low-Cost LLM Serving: From Offline Learning to Online Adaptation
by: Liu, Xutong, et al.
Published: (2025)