# LLASP: Fine-tuning Large Language Models for Answer Set Programming

arXiv: https://arxiv.org/abs/2407.18723 · HTML: https://mlsanity.com/paper/2407.18723/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 32 references that are in the map.
- First posted on arXiv 26 Jul 2024.

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

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [A Systematic Evaluation of Large Language Models of Code](https://mlsanity.com/paper/2202.13169/) (2022)
- [The Impact of AI on Developer Productivity: Evidence from GitHub Copilot](https://mlsanity.com/paper/2302.06590/) (2023)
- [Neural Machine Translation: A Review and Survey](https://mlsanity.com/paper/1912.02047/) (2019)
- [Improving Coherence and Consistency in Neural Sequence Models with Dual-System, Neuro-Symbolic Reasoning](https://mlsanity.com/paper/2107.02794/) (2021)
- [Coupling Large Language Models with Logic Programming for Robust and General Reasoning from Text](https://mlsanity.com/paper/2307.07696/) (2023)
- [LLaMoCo: Instruction Tuning of Large Language Models for Optimization Code Generation](https://mlsanity.com/paper/2403.01131/) (2024)
- [A Survey and Classification of Controlled Natural Languages](https://mlsanity.com/paper/1507.01701/) (2015)
- [AI-driven Development Is Here: Should You Worry?](https://mlsanity.com/paper/2204.07560/) (2022)
- [Towards Automatic Composition of ASP Programs from Natural Language Specifications](https://mlsanity.com/paper/2403.04541/) (2024)
- [CNL2ASP: converting controlled natural language sentences into ASP](https://mlsanity.com/paper/2311.10505/) (2023)
- [Specifying and Verbalising Answer Set Programs in Controlled Natural Language](https://mlsanity.com/paper/1804.10765/) (2018)

## Built on by (most cited first, 8 of 8)

- [Intermediate Languages Matter: Formal Languages and LLMs affect Neurosymbolic Reasoning](https://mlsanity.com/paper/2509.04083/) (2025)
- [Bridging Natural Language and ASP: A Hybrid Approach Using LLMs and AMR Parsing](https://mlsanity.com/paper/2511.08715/) (2025)
- [XAI-LAW: A Logic Programming Tool for Modeling, Explaining, and Learning Legal Decisions](https://mlsanity.com/paper/2601.03844/) (2026)
- [ASP-Bench: From Natural Language to Logic Programs](https://mlsanity.com/paper/2602.01171/) (2026)
- [Streamliners for Answer Set Programming](https://mlsanity.com/paper/2604.19251/) (2026)
- [Distilling Answer-Set Programming Rules from LLMs for Neurosymbolic Visual Question Answering](https://mlsanity.com/paper/2606.03269/) (2026)
- [Driving, Fast or Slow? Neuro-Symbolic Guidance for Motion Prediction in Multi-Modal Ground Mobility](https://mlsanity.com/paper/2606.15251/) (2026)
- [Automatic Conversion of NICE Guidelines to an Executable Computational Model Using Large Language Models](https://mlsanity.com/paper/2608.30022/) (2026)

## Abstract (arXiv)

Recently, Large Language Models (LLMs) have showcased their potential in various natural language processing tasks, including code generation. However, while significant progress has been made in adapting LLMs to generate code for several imperative programming languages and tasks, there remains a notable gap in their application to declarative formalisms, such as Answer Set Programming (ASP). In this paper, we move a step towards exploring the capabilities of LLMs for ASP code generation. First, we perform a systematic evaluation of several state-of-the-art LLMs. Despite their power in terms of number of parameters, training data and computational resources, empirical results demonstrate inadequate performances in generating correct ASP programs. Therefore, we propose LLASP, a fine-tuned lightweight model specifically trained to encode fundamental ASP program patterns. To this aim, we create an ad-hoc dataset covering a wide variety of fundamental problem specifications that can be encoded in ASP. Our experiments demonstrate that the quality of ASP programs generated by LLASP is remarkable. This holds true not only when compared to the non-fine-tuned counterpart but also when compared to the majority of eager LLM candidates, particularly from a semantic perspective. All the code and data used to perform the experiments are publicly available at https://anonymous.4open.science/r/LLASP-D86C/.