← Back to all news
arXiv AI By Jiale Dai, Liuxian Ma, Hongcan Deng, Xiaoke Niu, Wenjing Zhang, Zhaoxiang Liu, Shiguo Lian, Guojie Song

LaVGuard: Selective Decoding for Contextual Value Drift

Read the original on arXiv AI →

LaVGuard introduces a selective decoding method to address contextual value drift in AI assistants. It separates an authorized ten‑dimensional profile from a frozen estimate of values in the visible prefix, using a profile‑relative density gate to decide when to evaluate candidate continuations. The approach constrains logit tilts by changed‑position and cumulative‑KL budgets, achieving higher true‑positive rates at low false‑positive rates and demonstrating improved risk‑safety scores compared to position‑matched edits.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv Machine Learning
5d ago

Certified Behavioral Retention for Continual Adaptation with Held-Out Anchors

Certified Anchor-Based Adaptation (CABA) is a post‑update gate for continual adaptation that reserves historical observations, compares old and candidate policies on frozen representations, and selects the largest interpolation coefficient whose worst‑anchor forward KL divergence stays within a declared budget. The method does not require action labels or complete trajectories and is supported by a theory‑led certification framework that provides uniform behavioral‑divergence bounds under representation‑coverage and Lipschitz assumptions. In a UCI Human Activity Recognition study, CABA reduced mean forgetting from 1.01 % to 0.00 % at a budget ε = 0.05, while slightly lowering final average accuracy.

By Ahanaf Hasan Ariq, Abrar Shahid
robotics
More like this →
arXiv AI
Aug 26

When "Must" Becomes "Maybe": Constraint Weakening in LLM Agent Workflows

Large language model agents coordinate tasks via multi‑role, multi‑stage workflows that transform upstream state into intermediate artifacts such as summaries and plans. The study shows that when these artifacts are transformed—through compression, plan assimilation, or other handoff methods—the strict action‑binding constraints on upstream state can be weakened, turning mandatory requirements into optional information. In 1,296 synthetic episodes, direct handoff preserved all safety blockers, whereas transformed handoffs frequently deactivated or forbidden actions, but restoring full state fields or applying downstream verification can recover preservation.

By Yiheng Sun, Huifei Wang, Yancheng Zhu, Zhenyu Li, Zebin Zhao, Yifan Yuan
llmsagentssafety
More like this →