5 papers
Sydney Telling Fables on AI and Humans: A Corpus Tracing Memetic Transfer of Persona between LLMs
JiÅà MiliÄka, Hana BednáÅová
The way LLM-based entities conceive of the relationship between AI and humans is an important topic for both cultural and safety reasons. When we examine this topic, what matters i…
The author is dead, but what if they never lived? A reception experiment on Czech AI- and human-authored poetry
Anna Marklová, OndÅej VinÅ¡, Martina VokáÄová +1
Large language models are increasingly capable of producing creative texts, yet most studies on AI-generated poetry focus on English -- a language that dominates training data. In…
AI Brown and AI Koditex: LLM-Generated Corpora Comparable to Traditional Corpora of English and Czech Texts
JiÅà MiliÄka, Anna Marklová, Václav CvrÄek
This article presents two corpora of English and Czech texts generated with large language models (LLMs). The motivation is to create a resource for comparing human-written texts w…
Benchmark of stylistic variation in LLM-generated texts
JiÅà MiliÄka, Anna Marklová, Václav CvrÄek
This study investigates the register variation in texts written by humans and comparable texts produced by large language models (LLMs). Biber's multidimensional analysis (MDA) is…
Iconicity in Large Language Models
Anna Marklová, JiÅà MiliÄka, Leonid Ryvkin +2
Lexical iconicity, a direct relation between a word's meaning and its form, is an important aspect of every natural language, most commonly manifesting through sound-meaning associ…