# Position: Natural Language Should Not Fully Replace Formal Languages

arXiv: https://arxiv.org/abs/2607.20432 · HTML: https://mlsanity.com/paper/2607.20432/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 85 references that are in the map.
- First posted on arXiv 10 May 2026.

## Builds on (most cited first, 28 of 28)

- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [A Survey on Large Language Models for Code Generation](https://mlsanity.com/paper/2406.00515/) (2024)
- [MusicLM: Generating Music From Text](https://mlsanity.com/paper/2301.11325/) (2023)
- [Language Modeling Is Compression](https://mlsanity.com/paper/2309.10668/) (2023)
- [Design Guidelines for Prompt Engineering Text-to-Image Generative Models](https://mlsanity.com/paper/2109.06977/) (2021)
- [Grounded Copilot: How Programmers Interact with Code-Generating Models](https://mlsanity.com/paper/2206.15000/) (2022)
- [Optimizing Prompts for Text-to-Image Generation](https://mlsanity.com/paper/2212.09611/) (2022)
- [Gender Bias in Machine Translation](https://mlsanity.com/paper/2104.06001/) (2021)
- [Measuring the Impact of Early-2025 AI on Experienced Open-Source Developer Productivity](https://mlsanity.com/paper/2507.09089/) (2025)
- [A Survey on LLM-based Code Generation for Low-Resource and Domain-Specific Programming Languages](https://mlsanity.com/paper/2410.03981/) (2024)
- [Artificial Intelligence in the Creative Industries: A Review](https://mlsanity.com/paper/2007.12391/) (2020)
- [A Taxonomy of Prompt Modifiers for Text-To-Image Generation](https://mlsanity.com/paper/2204.13988/) (2022)
- [A Systematic Survey of Text Summarization: From Statistical Methods to Large Language Models](https://mlsanity.com/paper/2406.11289/) (2024)
- [Understanding the Impact of Negative Prompts: When and How Do They Take Effect?](https://mlsanity.com/paper/2406.02965/) (2024)
- [SketchEdit: Mask-Free Local Image Manipulation with Partial Sketches](https://mlsanity.com/paper/2111.15078/) (2021)
- [The World of an Octopus: How Reporting Bias Influences a Language Model's Perception of Color](https://mlsanity.com/paper/2110.08182/) (2021)
- [Controllable Text Summarization: Unraveling Challenges, Approaches, and Prospects -- A Survey](https://mlsanity.com/paper/2311.09212/) (2023)
- [Studying the Difference Between Natural and Programming Language Corpora](https://mlsanity.com/paper/1806.02437/) (2018)
- [Exploring the Impact of AI-generated Image Tools on Professional and Non-professional Users in the Art and Design Fields](https://mlsanity.com/paper/2406.10640/) (2024)
- [Survey on the Evaluation of Generative Models in Music](https://mlsanity.com/paper/2506.05104/) (2025)
- [The Hidden Risks of LLM-Generated Web Application Code: A Security-Centric Evaluation of Code Generation Capabilities in Large Language Models](https://mlsanity.com/paper/2504.20612/) (2025)
- [Human Learning by Model Feedback: The Dynamics of Iterative Prompting with Midjourney](https://mlsanity.com/paper/2311.12131/) (2023)
- [R2: A LLM Based Novel-to-Screenplay Generation Framework with Causal Plot Graphs](https://mlsanity.com/paper/2503.15655/) (2025)
- [Guiding What Not to Generate: Automated Negative Prompting for Text-Image Alignment](https://mlsanity.com/paper/2512.07702/) (2025)
- [The evolution of lossy compression](https://mlsanity.com/paper/1506.06138/) (2015)
- [Efficient human-like semantic representations via the Information Bottleneck principle](https://mlsanity.com/paper/1808.03353/) (2018)
- [NaturalEdit: Code Modification through Direct Interaction with Adaptive Natural Language Representation](https://mlsanity.com/paper/2510.04494/) (2025)
- [Lessons from the Field: An Adaptable Lifecycle Approach to Applied Dialogue Summarization](https://mlsanity.com/paper/2601.08682/) (2026)

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

- [Metaphor-Induced Algorithmic Steering: Cross-Domain Procedural Transfer in LLM Code Generation](https://mlsanity.com/paper/2607.28683/) (2026)

## Abstract (arXiv)

Recent advances in large language models and their widespread adoption have prompted claims that natural language could entirely replace formal languages, such as programming languages for software design. In this position paper, we argue that this perspective overlooks fundamental linguistic properties of natural language, specifically that it is optimized for underspecification in open-ended contexts. We introduce a formal framework centered on *task specificity*, defining it as the information-theoretic reduction of uncertainty in an output space -- such as all possible images -- given a user's specific requirements. We prove a *specificity crossover theorem*, showing the existence of a threshold beyond which the cost to express formal requirements into natural language exceeds the cost of direct formal specification. By analyzing case studies across modalities, such as image generation, code synthesis, and audio production, we demonstrate that natural language excels at low specificity tasks, while formal languages are advantageous on tasks with stricter requirements. We conclude that natural and formal languages are complementary tools and advocate the development of hybrid systems that allow users to move across the specificity spectrum.