# Hierarchical Alignment: Enforcing Hierarchical Instruction-Following in LLMs through Logical Consistency

arXiv: https://arxiv.org/abs/2604.09075 · HTML: https://mlsanity.com/paper/2604.09075/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 34 references that are in the map.
- First posted on arXiv 10 Apr 2026.

## Builds on (most cited first, 29 of 29)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection](https://mlsanity.com/paper/2302.12173/) (2023)
- [CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society](https://mlsanity.com/paper/2303.17760/) (2023)
- [HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face](https://mlsanity.com/paper/2303.17580/) (2023)
- [Prompt Injection attack against LLM-integrated Applications](https://mlsanity.com/paper/2306.05499/) (2023)
- [The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions](https://mlsanity.com/paper/2404.13208/) (2024)
- [Logic-LM: Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoning](https://mlsanity.com/paper/2305.12295/) (2023)
- [DeepResearcher: Scaling Deep Research via Reinforcement Learning in Real-world Environments](https://mlsanity.com/paper/2504.03160/) (2025)
- [CodeAgent: Enhancing Code Generation with Tool-Integrated Agent Systems for Real-World Repo-level Coding Challenges](https://mlsanity.com/paper/2401.07339/) (2024)
- [A Semantic Loss Function for Deep Learning with Symbolic Knowledge](https://mlsanity.com/paper/1711.11157/) (2017)
- [Benchmarking and Defending Against Indirect Prompt Injection Attacks on Large Language Models](https://mlsanity.com/paper/2312.14197/) (2023)
- [Maieutic Prompting: Logically Consistent Reasoning with Recursive Explanations](https://mlsanity.com/paper/2205.11822/) (2022)
- [Personalization of Large Language Models: A Survey](https://mlsanity.com/paper/2411.00027/) (2024)
- [Effective Prompt Extraction from Language Models](https://mlsanity.com/paper/2307.06865/) (2023)
- [Instructional Segment Embedding: Improving LLM Safety with Instruction Hierarchy](https://mlsanity.com/paper/2410.09102/) (2024)
- [TPTU: Large Language Model-based AI Agents for Task Planning and Tool Usage](https://mlsanity.com/paper/2308.03427/) (2023)
- [IHEval: Evaluating Language Models on Following the Instruction Hierarchy](https://mlsanity.com/paper/2502.08745/) (2025)
- [Enhancing Self-Consistency and Performance of Pre-Trained Language Models through Natural Language Inference](https://mlsanity.com/paper/2211.11875/) (2022)
- [Logically Consistent Language Models via Neuro-Symbolic Integration](https://mlsanity.com/paper/2409.13724/) (2024)
- [Large Language Models Meet Symbolic Provers for Logical Reasoning Evaluation](https://mlsanity.com/paper/2502.06563/) (2025)
- [Neuro-Symbolic Artificial Intelligence: Towards Improving the Reasoning Abilities of Large Language Models](https://mlsanity.com/paper/2508.13678/) (2025)
- [Silent Leaks: Implicit Knowledge Extraction Attack on RAG Systems through Benign Queries](https://mlsanity.com/paper/2505.15420/) (2025)
- [Language Models with Rationality](https://mlsanity.com/paper/2305.14250/) (2023)

## Built on by (most cited first, 1 of 1)

- [IHDec: Divergence-Steered Contrastive Decoding for Securing Multi-Turn Instruction Hierarchies](https://mlsanity.com/paper/2606.29960/) (2026)

## Abstract (arXiv)

Large language models increasingly operate under multiple instructions from heterogeneous sources with different authority levels, including system policies, user requests, tool outputs, and retrieved context. While prior work on instruction hierarchy highlights the importance of respecting instruction priorities, it mainly focuses on adversarial attacks and overlooks the benign but common instruction conflicts that arise in real-world applications. In such settings, models must not only avoid security violations but also preserve task utility and behavioral consistency when instructions partially or implicitly conflict. We propose Neuro-Symbolic Hierarchical Alignment (NSHA) for hierarchical instruction-following by explicitly modeling and enforcing instruction priorities. At inference time, we introduce solver-guided reasoning that formulates instruction resolution as a constraint satisfaction problem, enabling the model to derive a maximally consistent set of applicable instructions under hierarchical constraints. At training time, NSHA distills solver-based decisions into model parameters using automatically constructed supervision. We evaluate our approach on rule following, task execution, tool use, and safety, covering both single-turn and multi-turn interactions, and show that NSHA significantly improves performance under such conflicts while maintaining competitive utility in reference settings.