IHDec: Divergence-Steered Contrastive Decoding for Securing Multi-Turn Instruction Hierarchies
Large Language Models (LLMs) often fail to maintain instruction hierarchies (IH) when processing multi-source inputs with varying role-level priorities, paradoxically adhering to lower-priority directives during conflicts. While existing defenses mitigate this issue, they are largely restricted to single-turn scenarios and require expensive fine-tuning. In this paper, we formalize this failure mode in multi-turn contexts via a Jensen-Shannon Divergence (JSD) framework, uncovering a pervasive role-influence inversion phenomenon where subordinate inputs override superior roles. To rectify this without training, we propose IHDec (Instruction Hierarchy-steered Decoding). IHDec leverages JSD t...
| Authors | Nicole Geumheon Liu, Haeun Jang, Yonghyun Jun et al. |
|---|---|
| Primary category | cs.CL |
| Published | 29 June 2026 |
| Last updated at source | 17 September 2026 |
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.