NILE: Formalizing Natural-Language Descriptions of Formal Languages

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Kneisel, Tristan, Schmellenkamp, Marko, Vehlken, Fabian, Zeume, Thomas
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910030099382272
author Kneisel, Tristan
Schmellenkamp, Marko
Vehlken, Fabian
Zeume, Thomas
author_facet Kneisel, Tristan
Schmellenkamp, Marko
Vehlken, Fabian
Zeume, Thomas
contents This paper explores how natural-language descriptions of formal languages can be compared to their formal representations and how semantic differences can be explained. This is motivated from educational scenarios where learners describe a formal language (presented, e.g., by a finite state automaton, regular expression, pushdown automaton, context-free grammar or in set notation) in natural language, and an educational support system has to (1) judge whether the natural-language description accurately describes the formal language, and to (2) provide explanations why descriptions are not accurate. To address this question, we introduce a representation language for formal languages, Nile, which is designed so that Nile expressions can mirror the syntactic structure of natural-language descriptions of formal languages. Nile is sufficiently expressive to cover a broad variety of formal languages, including all regular languages and fragments of context-free languages typically used in educational contexts. Generating Nile expressions that are syntactically close to natural-language descriptions then allows to provide explanations for inaccuracies in the descriptions algorithmically. In experiments on an educational data set, we show that LLMs can translate natural-language descriptions into equivalent, syntactically close Nile expressions with high accuracy - allowing to algorithmically provide explanations for incorrect natural-language descriptions. Our experiments also show that while natural-language descriptions can also be translated into regular expressions (but not context-free grammars), the expressions are often not syntactically close and thus not suitable for providing explanations.
format Preprint
id arxiv_https___arxiv_org_abs_2602_19743
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle NILE: Formalizing Natural-Language Descriptions of Formal Languages
Kneisel, Tristan
Schmellenkamp, Marko
Vehlken, Fabian
Zeume, Thomas
Formal Languages and Automata Theory
Computation and Language
Logic in Computer Science
This paper explores how natural-language descriptions of formal languages can be compared to their formal representations and how semantic differences can be explained. This is motivated from educational scenarios where learners describe a formal language (presented, e.g., by a finite state automaton, regular expression, pushdown automaton, context-free grammar or in set notation) in natural language, and an educational support system has to (1) judge whether the natural-language description accurately describes the formal language, and to (2) provide explanations why descriptions are not accurate. To address this question, we introduce a representation language for formal languages, Nile, which is designed so that Nile expressions can mirror the syntactic structure of natural-language descriptions of formal languages. Nile is sufficiently expressive to cover a broad variety of formal languages, including all regular languages and fragments of context-free languages typically used in educational contexts. Generating Nile expressions that are syntactically close to natural-language descriptions then allows to provide explanations for inaccuracies in the descriptions algorithmically. In experiments on an educational data set, we show that LLMs can translate natural-language descriptions into equivalent, syntactically close Nile expressions with high accuracy - allowing to algorithmically provide explanations for incorrect natural-language descriptions. Our experiments also show that while natural-language descriptions can also be translated into regular expressions (but not context-free grammars), the expressions are often not syntactically close and thus not suitable for providing explanations.
title NILE: Formalizing Natural-Language Descriptions of Formal Languages
topic Formal Languages and Automata Theory
Computation and Language
Logic in Computer Science
url https://arxiv.org/abs/2602.19743