Large Language Models Preserve Semantic Isotopies in Story Continuations

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autore principale: Cavazza, Marc
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908577321451520
author Cavazza, Marc
author_facet Cavazza, Marc
contents In this work, we explore the relevance of textual semantics to Large Language Models (LLMs), extending previous insights into the connection between distributional semantics and structural semantics. We investigate whether LLM-generated texts preserve semantic isotopies. We design a story continuation experiment using 10,000 ROCStories prompts completed by five LLMs. We first validate GPT-4o's ability to extract isotopies from a linguistic benchmark, then apply it to the generated stories. We then analyze structural (coverage, density, spread) and semantic properties of isotopies to assess how they are affected by completion. Results show that LLM completion within a given token horizon preserves semantic isotopies across multiple properties.
format Preprint
id arxiv_https___arxiv_org_abs_2510_04400
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Large Language Models Preserve Semantic Isotopies in Story Continuations
Cavazza, Marc
Computation and Language
Artificial Intelligence
In this work, we explore the relevance of textual semantics to Large Language Models (LLMs), extending previous insights into the connection between distributional semantics and structural semantics. We investigate whether LLM-generated texts preserve semantic isotopies. We design a story continuation experiment using 10,000 ROCStories prompts completed by five LLMs. We first validate GPT-4o's ability to extract isotopies from a linguistic benchmark, then apply it to the generated stories. We then analyze structural (coverage, density, spread) and semantic properties of isotopies to assess how they are affected by completion. Results show that LLM completion within a given token horizon preserves semantic isotopies across multiple properties.
title Large Language Models Preserve Semantic Isotopies in Story Continuations
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2510.04400