# IHDec: Divergence-Steered Contrastive Decoding for Securing Multi-Turn Instruction Hierarchies

arXiv: https://arxiv.org/abs/2606.29960 · HTML: https://mlsanity.com/paper/2606.29960/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 25 references that are in the map.
- First posted on arXiv 29 Jun 2026.

## Builds on (most cited first, 15 of 15)

- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Contrastive Decoding: Open-ended Text Generation as Optimization](https://mlsanity.com/paper/2210.15097/) (2022)
- [The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions](https://mlsanity.com/paper/2404.13208/) (2024)
- [Trusting Your Evidence: Hallucinate Less with Context-aware Decoding](https://mlsanity.com/paper/2305.14739/) (2023)
- [MT-Bench-101: A Fine-Grained Benchmark for Evaluating Large Language Models in Multi-Turn Dialogues](https://mlsanity.com/paper/2402.14762/) (2024)
- [Can LLMs Separate Instructions From Data? And What Do We Even Mean By That?](https://mlsanity.com/paper/2403.06833/) (2024)
- [Instructional Segment Embedding: Improving LLM Safety with Instruction Hierarchy](https://mlsanity.com/paper/2410.09102/) (2024)
- [IHEval: Evaluating Language Models on Following the Instruction Hierarchy](https://mlsanity.com/paper/2502.08745/) (2025)
- [ChatInject: Abusing Chat Templates for Prompt Injection in LLM Agents](https://mlsanity.com/paper/2509.22830/) (2025)
- [IH-Challenge: A Training Dataset to Improve Instruction Hierarchy on Frontier LLMs](https://mlsanity.com/paper/2603.10521/) (2026)
- [Can Language Models Follow Multiple Turns of Entangled Instructions?](https://mlsanity.com/paper/2503.13222/) (2025)
- [Reasoning Up the Instruction Ladder for Controllable Language Models](https://mlsanity.com/paper/2511.04694/) (2025)
- [Diagnose, Localize, Align: A Full-Stack Framework for Reliable LLM Multi-Agent Systems under Instruction Conflicts](https://mlsanity.com/paper/2509.23188/) (2025)
- [Steer Model beyond Assistant: Controlling System Prompt Strength via Contrastive Decoding](https://mlsanity.com/paper/2601.06403/) (2026)
- [Hierarchical Alignment: Enforcing Hierarchical Instruction-Following in LLMs through Logical Consistency](https://mlsanity.com/paper/2604.09075/) (2026)

## Abstract (arXiv)

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 to automatically detect token-level hierarchy violations and dynamically executes contrastive decoding to suppress misaligned subordinate roles. Extensive evaluations demonstrate that IHDec outperforms training-based baselines in multi-turn conflicts while fully preserving general response quality. Furthermore, IHDec strengthens safety against adversarial prompt injections and exhibits a robust scaling synergy with larger models. The Code is available at https://github.com/nxcolelxu/IHDec.git