Not Your Diary, Just Your Topic: Grading the Wrong-User Control
cs.AI
Submitted: 2026-11-06
Updated: 2026-11-06
Project page: https://lamp-benchmark.github.io/download
Terminology
Sources
- Flamingo: a Visual Language Model for Few-Shot Learning
- Substrate Asymmetry in User-Side Memory: A Diagnostic Framework
- Towards a Unified View of Parameter-Efficient Transfer Learning
- PERSOMA: PERsonalized SOft ProMpt Adapter Architecture for Personalized Language Prompting
- Embedding-to-Prefix: Parameter-Efficient Personalization for Pre-Trained Large Language Models
- Trained Persistent Memory for Frozen Decoder-Only LLMs
- REPREC: Representation Driven Parameter-Efficient Recommendation System
- Exact Network Surgery: Functional Invariance and Gradient Plasticity in Reactive Computational Graphs
- Less Is Personal: Learning Minimal Sufficient User Profiles for Personalized Language Models
- Beyond Prefixes: Graph-as-Memory Cross-Attention for Knowledge Graph Completion with Large Language Models
- User-LLM: Efficient LLM Contextualization with User Embeddings
- How Context Affects Language Models' Factual Predictions
- When Do Prompting and Prefix-Tuning Work? A Theory of Capabilities and Limitations
- Are Emergent Abilities of Large Language Models a Mirage?
- Understanding the Role of User Profile in the Personalization of Large Language Models
- Making Retrieval-Augmented Language Models Robust to Irrelevant Context
- Fixup Initialization: Residual Learning Without Normalization
- Is Personalized Modality Weighting Actually Personalized? A Controlled Audit of Per-User Weighting Claims in Multimodal Recommenders
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