Reading Between the Prompts: How Stereotypes Shape LLM's Implicit Personalization
Paper
• 2505.16467 • Published
User Modeling
Note ✅
IP-Dialog: Evaluating Implicit Personalization in Dialogue Systems with Synthetic Data
Paper • 2506.02449 • Published • 1Note ✅
Localizing Persona Representations in LLMs
Paper • 2505.24539 • PublishedNote ✅
Persona Vectors: Monitoring and Controlling Character Traits in Language Models
Paper • 2507.21509 • Published • 33Note ✅
Know Me, Respond to Me: Benchmarking LLMs for Dynamic User Profiling and Personalized Responses at Scale
Paper • 2504.14225 • Published • 1Note ✅
Language Models Change Facts Based on the Way You Talk
Paper • 2507.14238 • Published • 1Note ✅
Learning a Generative Meta-Model of LLM Activations
Paper • 2602.06964 • Published • 3Note keyword: latent user attributes probing LLM activations - def. check out
CLaS-Bench: A Cross-Lingual Alignment and Steering Benchmark
Paper • 2601.08331 • PublishedNote keyword: linear probes demographic inference language model residual stream
Bi-directional Bias Attribution: Debiasing Large Language Models without Modifying Prompts
Paper • 2602.04398 • PublishedNote recommended (similar to seeds)
Reasoning Beyond Chain-of-Thought: A Latent Computational Mode in Large Language Models
Paper • 2601.08058 • PublishedNote recommended (similar to seeds)
YaPO: Learnable Sparse Activation Steering Vectors for Domain Adaptation
Paper • 2601.08441 • Published • 8Note recommended (similar to seeds)
Steer2Edit: From Activation Steering to Component-Level Editing
Paper • 2602.09870 • Published • 1Note recommended (similar to seeds)
Endogenous Resistance to Activation Steering in Language Models
Paper • 2602.06941 • PublishedNote recommended (similar to seeds)
BLOCK-EM: Preventing Emergent Misalignment by Blocking Causal Features
Paper • 2602.00767 • PublishedNote recommended (similar to seeds)
AntiPaSTO: Self-Supervised Steering of Moral Reasoning
Paper • 2601.07473 • Published • 1Note recommended (similar to seeds)
Why Steering Works: Toward a Unified View of Language Model Parameter Dynamics
Paper • 2602.02343 • Published • 13Note recommended (similar to seeds)
-
Who's asking? User personas and the mechanics of latent misalignment
Paper • 2406.12094 • Published