Signals 4 · free daily AI digest

User Model Extraction via Belief Self-Distillation

Paper recorded by Signals 4 on 2026-09-25 in cs.LG. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-25 on arXiv · recorded by Signals 4 on 2026-09-28

Category: cs.LG · 机器学习 · first seen 2026-09-28

Abstract

Large language models (LLMs) implicitly infer attributes of their users and adapt their behavior accordingly, yet these beliefs remain difficult to inspect and causally manipulate. We introduce Belief Self-Distillation (BSD), a unified read-write framework that bridges linear and causal probing by learning a compact user representation that can be both decoded and written back into the model. The

Read on arXiv →

#3 most recent of 310 cs.LG papers we have recorded · ↑ newer: First-Order Stationarity of Reverse Diffusions · ↓ older: New LoRA Skills Should Read but Never Write
Cite this page: User Model Extraction via Belief Self-Distillation: the #3 most recent of 310 cs.LG papers we have recorded (as of 2026-09-25). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/user-model-extraction-via-belief-self-distillation.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.LG papers · arXiv signals · All papers · Today in AI
Get 4 AI signals a day by email — free.
Subscribe free → See all plans →
Get 4 AI signals a day by email — free
All models · All repos · By company · Daily editions