# Neurosymbolic AI for Enhancing Instructability in Generative AI

arXiv: https://arxiv.org/abs/2407.18722 · HTML: https://mlsanity.com/paper/2407.18722/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 16 references that are in the map.
- First posted on arXiv 26 Jul 2024.

## Builds on (most cited first, 10 of 10)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [TravelPlanner: A Benchmark for Real-World Planning with Language Agents](https://mlsanity.com/paper/2402.01622/) (2024)
- [The False Promise of Imitating Proprietary LLMs](https://mlsanity.com/paper/2305.15717/) (2023)
- [Do Models Really Learn to Follow Instructions? An Empirical Study of Instruction Tuning](https://mlsanity.com/paper/2305.11383/) (2023)
- [On the Prospects of Incorporating Large Language Models (LLMs) in Automated Planning and Scheduling (APS)](https://mlsanity.com/paper/2401.02500/) (2024)
- [Understanding the Capabilities of Large Language Models for Automated Planning](https://mlsanity.com/paper/2305.16151/) (2023)
- [Process Knowledge-Infused AI: Towards User-level Explainability, Interpretability, and Safety](https://mlsanity.com/paper/2206.13349/) (2022)
- [Building Trustworthy NeuroSymbolic AI Systems: Consistency, Reliability, Explainability, and Safety](https://mlsanity.com/paper/2312.06798/) (2023)
- [Grounding from an AI and Cognitive Science Lens](https://mlsanity.com/paper/2402.13290/) (2024)
- [The Case for Developing a Foundation Model for Planning-like Tasks from Scratch](https://mlsanity.com/paper/2404.04540/) (2024)

## Built on by (most cited first, 3 of 3)

- [Towards Alignment-Centric Paradigm: A Survey of Instruction Tuning in Large Language Models](https://mlsanity.com/paper/2508.17184/) (2025)
- [NeuroLit Navigator: A Neurosymbolic Approach to Scholarly Article Searches for Systematic Reviews](https://mlsanity.com/paper/2503.00278/) (2025)
- [Model-Grounded Symbolic Artificial Intelligence Systems Learning and Reasoning with Model-Grounded Symbolic Artificial Intelligence Systems](https://mlsanity.com/paper/2507.09854/) (2025)

## Abstract (arXiv)

Generative AI, especially via Large Language Models (LLMs), has transformed content creation across text, images, and music, showcasing capabilities in following instructions through prompting, largely facilitated by instruction tuning. Instruction tuning is a supervised fine-tuning method where LLMs are trained on datasets formatted with specific tasks and corresponding instructions. This method systematically enhances the model's ability to comprehend and execute the provided directives. Despite these advancements, LLMs still face challenges in consistently interpreting complex, multi-step instructions and generalizing them to novel tasks, which are essential for broader applicability in real-world scenarios. This article explores why neurosymbolic AI offers a better path to enhance the instructability of LLMs. We explore the use a symbolic task planner to decompose high-level instructions into structured tasks, a neural semantic parser to ground these tasks into executable actions, and a neuro-symbolic executor to implement these actions while dynamically maintaining an explicit representation of state. We also seek to show that neurosymbolic approach enhances the reliability and context-awareness of task execution, enabling LLMs to dynamically interpret and respond to a wider range of instructional contexts with greater precision and flexibility.