UPSHIFT: User Preference Steering from Human-AI Interaction Feedback Traces
cs.AI
Submitted: 2026-11-02
Updated: 2026-11-02
Terminology
Sources
- Steerable Chatbots: Exploring Personalization Control Interfaces via LLM Activation Steering
- From Profiles to Steering Vectors: Global Sparse Priors and Local Semantic Calibration for Personalized Text Generation
- Naturally Occurring Feedback is Common, Extractable and Useful
- Towards Natural Personalization: Evaluating Long-Horizon Preference Following in Personalized User-LLM Interactions
- Know Me, Respond to Me: Benchmarking LLMs for Dynamic User Profiling and Personalized Responses at Scale
- User Feedback in Human-LLM Dialogues: A Lens to Understand Users But Noisy as a Learning Signal
- Steering Llama 2 via Contrastive Activation Addition
- On the Limits of Steering Vectors for Preference-Aligned Generation
- Step-Back Profiling: Distilling User History for Personalized Scientific Writing
- Steering Language Models With Activation Engineering
- Personalized Text Generation with Contrastive Activation Steering
- SteerX: Disentangled Steering for LLM Personalization
- Representation Engineering: A Top-Down Approach to AI Transparency
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents