Auditing Multi-Proxy Explanations of Web User Preferences: Identification Boundaries and Abstention
cs.LG, cs.IR
Submitted: 2026-11-03
Updated: 2026-11-03
Terminology
Sources
- LLM-based User Profile Management for Recommender System
- End-to-end Training for Recommendation with Language-based User Profiles
- Aggregating explanation methods for stable and robust explainability
- EnsembleSHAP: Faithful and Certifiably Robust Attribution for Random Subspace Method
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis