Position: Natural Language Should Not Fully Replace Formal Languages

• URL: http://arxiv.org/abs/2607.20432v1
• Date: Sun, 10 May 2026 15:01:16 GMT
• Title: Position: Natural Language Should Not Fully Replace Formal Languages
• Abstract summary: We argue that natural language is optimized for underspecification in open-ended contexts.<n>We show that natural language excels at low specificity tasks, while formal languages are advantageous on tasks with stricter requirements.
• Score: 11.90605417129287
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Symbolic Informalization: Fluent, Productive, Multilingual [0.0]
  Symbolic informalization enables a reliable conversion of formal mathematics to natural language.<n>This paper outlines the project Informath, which aims to show how symbolic informalization can produce fluent text.
  arXiv  Detail & Related papers  (2026-06-15T16:06:21Z)
• Coherency through formalisations of Structured Natural Language, A case study on FRETish [0.0]
  Formalisation is the process of writing system requirements in a formal language.<n>In this paper we propose a new guideline: Coherency through Formalisations.<n>We analyze NASA's Formal Requirement Elicitation Tool FRET and propose an alternative automated translation of the Controlled Natural Language FRETish to the formal language of MTL.
  arXiv  Detail & Related papers  (2026-05-11T12:30:53Z)
• Between Circuits and Chomsky: Pre-pretraining on Formal Languages Imparts Linguistic Biases [47.920937001420505]
  Pretraining language models on formal language can improve their acquisition of natural language.<n>We show that languages capturing hierarchical dependencies indeed enable language models to achieve lower loss on natural language.<n>We also give mechanistic evidence of transfer from formal to natural language.
  arXiv  Detail & Related papers  (2025-02-26T15:55:55Z)
• Soft Language Clustering for Multilingual Model Pre-training [57.18058739931463]
  We propose XLM-P, which contextually retrieves prompts as flexible guidance for encoding instances conditionally. Our XLM-P enables (1) lightweight modeling of language-invariant and language-specific knowledge across languages, and (2) easy integration with other multilingual pre-training methods.
  arXiv  Detail & Related papers  (2023-06-13T08:08:08Z)
• nl2spec: Interactively Translating Unstructured Natural Language to Temporal Logics with Large Language Models [3.1143846686797314]
  We present nl2spec, a framework for applying Large Language Models (LLMs) derive formal specifications from unstructured natural language. We introduce a new methodology to detect and resolve the inherent ambiguity of system requirements in natural language. Users iteratively add, delete, and edit these sub-translations to amend erroneous formalizations, which is easier than manually redrafting the entire formalization.
  arXiv  Detail & Related papers  (2023-03-08T20:08:53Z)
• Language Models as Inductive Reasoners [125.99461874008703]
  We propose a new paradigm (task) for inductive reasoning, which is to induce natural language rules from natural language facts. We create a dataset termed DEER containing 1.2k rule-fact pairs for the task, where rules and facts are written in natural language. We provide the first and comprehensive analysis of how well pretrained language models can induce natural language rules from natural language facts.
  arXiv  Detail & Related papers  (2022-12-21T11:12:14Z)
• Transparency Helps Reveal When Language Models Learn Meaning [71.96920839263457]
  Our systematic experiments with synthetic data reveal that, with languages where all expressions have context-independent denotations, both autoregressive and masked language models learn to emulate semantic relations between expressions. Turning to natural language, our experiments with a specific phenomenon -- referential opacity -- add to the growing body of evidence that current language models do not well-represent natural language semantics.
  arXiv  Detail & Related papers  (2022-10-14T02:35:19Z)
• Formal Specifications from Natural Language [3.1806743741013657]
  We study the ability of language models to translate natural language into formal specifications with complex semantics. In particular, we fine-tune off-the-shelf language models on three datasets consisting of structured English sentences.
  arXiv  Detail & Related papers  (2022-06-04T10:49:30Z)
• Linking Emergent and Natural Languages via Corpus Transfer [98.98724497178247]
  We propose a novel way to establish a link by corpus transfer between emergent languages and natural languages. Our approach showcases non-trivial transfer benefits for two different tasks -- language modeling and image captioning. We also introduce a novel metric to predict the transferability of an emergent language by translating emergent messages to natural language captions grounded on the same images.
  arXiv  Detail & Related papers  (2022-03-24T21:24:54Z)
• Towards Zero-shot Language Modeling [90.80124496312274]
  We construct a neural model that is inductively biased towards learning human languages. We infer this distribution from a sample of typologically diverse training languages. We harness additional language-specific side information as distant supervision for held-out languages.
  arXiv  Detail & Related papers  (2021-08-06T23:49:18Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.